Interpretation and constraints on matrix coefficients in cicp

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP). A conversion is performed between a visual media data and a bitstream based on the CICP.

Description

Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) Interpretation And Constraints On Matrix Coefficients In CICP CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the priority to and benefits of U.S. Provisional Patent Application No.63 / 637,213, filed on April 22, 2024, U.S. Provisional Patent Application No. 63 / 637,744, filed on April 23, 2024, and U.S. Provisional Patent Application No. 63 / 637,815, filed on April 23, 2024. All of these applications are herein incorporated by reference in their entireties. TECHNICAL FIELD

[0002] The present disclosure relates to generation, storage, and consumption of digital audio video media information in a file format. BACKGROUND

[0003] Digital video accounts for the largest bandwidth used on the Internet and other digital communication networks. As the number of connected user devices capable of receiving and displaying video increases, the bandwidth demand for digital video usage is likely to continue to grow. SUMMARY

[0004] A first aspect relates to a method for processing video data comprising: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); and performing a conversion between a visual media data and a bitstream based on the CICP.

[0005] A second aspect relates to an apparatus for processing video data comprising: a processor; and a non- transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform any of the preceding aspects.

[0006] A third aspect relates to non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of the preceding aspects.

[0007] A fourth aspect relates to a non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); and generating the bitstream based on the determining.

[0008] A fifth aspect relates to a method for storing bitstream of a video comprising: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo- R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer- readable recording medium.

[0009] A sixth aspect relates to a method, apparatus, or system described in the present disclosure.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0010] For the purpose of clarity, any one of the foregoing embodiments may be combined with any one or more of the other foregoing embodiments to create a new embodiment within the scope of the present disclosure.

[0011] These and other features will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For a more complete understanding of this disclosure, reference is now made to the following brief description, taken in connection with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0013] FIG.1 illustrates a location of chroma samples for top and bottom fields for ChromaFormatIdc equal to 1 as a function of vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field in the range of 0 to 5, inclusive.

[0014] FIG.2 illustrates nominal vertical and horizontal locations of 4:2:2 luma and chroma samples in a picture.

[0015] FIG. 3 illustrates nominal vertical and horizontal locations of 4:4:4 luma and chroma samples in a picture.

[0016] FIG. 4 illustrates a location of the top-left chroma sample when ChromaFormatIdc is equal to 1 and Chroma420LocType is equal to 0 to 5, inclusive, from left to right.

[0017] FIG. 5 illustrates a location of the top-left chroma sample when ChromaFormatIdc is equal to 1 when Chroma420LocType is equal to 1.

[0018] FIG.6 illustrates deriving the four luma channels (right) from the luma component (left) when nnpfc_inp_order_idc is equal to 3.

[0019] FIG.7 is a block diagram showing an example video processing system.

[0020] FIG.8 is a block diagram of an example video processing apparatus.

[0021] FIG.9 is a flowchart for an example method of video processing.

[0022] FIG.10 is a block diagram that illustrates an example video coding system.

[0023] FIG.11 is a block diagram that illustrates an example encoder.

[0024] FIG.12 is a block diagram that illustrates an example decoder.

[0025] FIG.13 is a schematic diagram of an example encoder. DETAILED DESCRIPTION

[0026] It should be understood at the outset that although an illustrative implementation of one or more embodiments are provided below, the disclosed systems and / or methods may be implemented using any number of techniques, whether currently known or yet to be developed. The disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary designs and implementations illustrated and described herein, but may be modified within the scope of the appended claims along with their full scope of equivalents.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 1. Initial discussion

[0027] This disclosure is related to image / video coding technologies. Specifically, this disclosure is related to constraints during referencing MatrixCoefficients described in Rec. ITU-T H.273 | ISO / IEC 23091-2 [1] (or CICP in short) by H.264[2] / H.265[3] / H.266[4]. The ideas may be applied individually or in various combinations, for image / video bitstreams coded by any codec, e.g., the versatile video coding (VVC) standard [4] and / or the versatile supplemental enhancement information (SEI) messages for coded video bitstreams (VSEI) [5] standard. 2. Abbreviations

[0028] The following abbreviations are used herein: Adaptation Parameter Set (APS), Access Unit (AU), Coding-independent code points (CICP), Coded Layer Video Sequence (CLVS), Coded Layer Video Sequence Start (CLVSS), Cyclic Redundancy Check (CRC), Coded Video Sequence (CVS), Finite Impulse Response (FIR), Intra Random Access Point (IRAP), Network Abstraction Layer (NAL), neural-network post-processing filter (NNPF), neural-network post-filter activation (NNPFA), neural-network post-filter characteristics (NNPFC), Picture Parameter Set (PPS), Picture Unit (PU), Random Access Skipped Leading (RASL), Society of Motion Picture and Television Engineers (SMPTE), Supplemental Enhancement Information (SEI), Step-wise Temporal Sublayer Access (STSA), uniform resource identifier (URI), Video Coding Layer (VCL), Versatile Supplemental Enhancement Information (Rec. ITU-T H.274 | ISO / IEC 23002-7) (VSEI), Video Usability Information (VUI), Versatile Video Coding (Rec. ITU-T H.266 | ISO / IEC 23090-3) (VVC). 3. Further Discussion 3.1 Video coding standards

[0029] Video coding standards have evolved primarily through the development of the International Telecommunication Union Telecommunication Standardization Sector (ITU-T) and International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) standards. The ITU-T produced H.261 and H.263, ISO / IEC produced Moving Picture Experts Group (MPEG)-1 and MPEG-4 Visual, and the two organizations jointly produced the H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Coding (AVC) [2] and H.265 / HEVC [3] standards. Since H.262, the video coding standards are based on the hybrid video coding structure wherein temporal prediction plus transform coding are utilized. To explore the future video coding technologies beyond HEVC, the Joint Video Exploration Team (JVET) was founded by video coding experts group (VCEG) and MPEG jointly. The JVET was later renamed to be the Joint Video Experts Team (JVET) when the Versatile Video Coding (VVC) project officially started. VVC [4] is a coding standard, targeting a 50% bitrate reduction as compared to HEVC, that is managed by the JVET.

[0030] The Versatile Video Coding (VVC) standard (ITU-T H.266 | ISO / IEC 23090-3) [4] and the associated Versatile Supplemental Enhancement Information for coded video bitstreams (VSEI) standard (ITU-T H.274 | ISO / IEC 23002-7) [5] have been designed for use in a maximally broad range of applications, including both simple uses such as television broadcast, video conferencing, or playback from storage media, and also more advanced use cases such as adaptive bit rate streaming, video region extraction, composition and merging of content from multiple coded video bitstreams, multiview video, scalable layered coding, and viewport-adaptive 360° immersive media.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0031] The Essential Video Coding (EVC) standard (ISO / IEC 23094-1) is another video coding standard that has been developed by MPEG. 3.2 Coding-independent code points

[0032] Rec. ITU-T H.273 | ISO / IEC 23091-2 [1] specifies different coding-independent code points for video signal type identification to identify some characteristics of video (or still image) media content that are logically independent of the compression format. These characteristics can include, for example, aspects that relate to the sourcing or presentation, or the role of the video (or still image) media component. These characteristics are documented by fields that take an encoded value or item selected from an enumerated list, herein called code points.

[0033] Rec. ITU-T H.273 | ISO / IEC 23091-2 [1] provides a central definition of such code points for video and image applications to address these issues. The standard can be used to provide universal descriptions to assist interpretation of video and image signals following decoding, or to describe the properties of these signals before they are encoded. 3.3 Video usability information

[0034] In [5], the video usability information (VUI) uses the following syntax table. vui_parameters( payloadSize ) { Descriptor i i flAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) vui_matrix_coeffs u(8) vui_full_range_flag u(1) 3

[0035] VUI parameters apply to one or more CLVSs.

[0036] NOTE 1. The interpretation of several syntax elements of the VUI parameters are specified by reference to coding-independent code points specified in Rec. ITU-T H.273 | ISO / IEC 23091-2. Further information about the usage of such code points is found in ITU-T H-Suppl.19 | ISO / IEC TR 23091-4.

[0037] Use of the VUI parameters requires the definition of the following variables: — A chroma format indicator, denoted herein by ChromaFormatIdc, such that the value 0 indicates that the picture has only a luma component and other values indicate that the picture has three colour components that consist of a luma component and two associated chroma components, such that the width and height of each chroma component are the width and height of the luma component divided by SubWidthC and SubHeightC, respectively, where SubWidthC and SubHeightC are determined from ChromaFormatIdc as specified by Table 1. — A bit depth for the samples of the luma component, denoted herein by BitDepthY, and when ChromaFormatIdc is not equal to 0, a bit depth for the samples of the two associated chroma components, denoted herein by BitDepthC. Table 1 — SubWidthC and SubHeightC values derived from ChromaFormatIdc ChromaFormatIdc Chroma format SubWidthC SubHeightCAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0038] vui_progressive_source_flag and vui_interlaced_source_flag are interpreted as follows: — If vui_progressive_source_flag is equal to 1 and vui_interlaced_source_flag is equal to 0, the source scan type of the pictures should be interpreted as progressive only. — Otherwise, if vui_progressive_source_flag is equal to 0 and vui_interlaced_source_flag is equal to 1, the source scan type of the pictures should be interpreted as interlaced only. — Otherwise, if vui_progressive_source_flag is equal to 0 and vui_interlaced_source_flag is equal to 0, the source scan type of the pictures should be interpreted as unknown or unspecified or specified by external means not specified in this document. — Otherwise (vui_progressive_source_flag is equal to 1 and vui_interlaced_source_flag is equal to 1), the source scan type of each picture is indicated at the picture level using the syntax element ffi_source_scan_type in a frame-field information SEI message.

[0039] vui_non_packed_constraint_flag equal to 1 specifies that there shall not be any frame packing arrangement SEI messages present in the bitstream that apply to the CLVS. vui_non_packed_constraint_flag equal to 0 does not impose such a constraint.

[0040] vui_non_projected_constraint_flag equal to 1 specifies that there shall not be any equirectangular projection SEI messages or generalized cubemap projection SEI messages present in the bitstream that apply to the CLVS. vui_non_projected_constraint_flag equal to 0 does not impose such a constraint.

[0041] vui_aspect_ratio_info_present_flag equal to 1 specifies that vui_aspect_ratio_idc is present. vui_aspect_ratio_info_present_flag equal to 0 specifies that vui_aspect_ratio_idc is not present.

[0042] vui_aspect_ratio_constant_flag equal to 1 specifies that the values of vui_aspect_ratio_idc, SarWidth, and SarHeight apply to all pictures in the CLVS and there is no sample aspect ratio information (SARI) SEI message present in the CLVS. vui_aspect_ratio_constant_flag equal to 0 specifies that the values of vui_aspect_ratio_idc, SarWidth, and SarHeight might or might not apply to all pictures in the CLVS and that SARI SEI messages could be present in the CLVS indicating a different sample aspect ratio applicable to the pictures associated with SARI SEI messages. When the vui_aspect_ratio_constant_flag syntax element is not present, the value of vui_aspect_ratio_constant_flag is inferred to be equal to 0.

[0043] vui_aspect_ratio_idc, when not equal to 255, indicates the sample aspect ratio (SAR) of the luma samples of decoded pictures in the CLVS, unless indicated otherwise by associated SARI SEI messages when vui_aspect_ratio_constant_flag is equal to 0. Its semantics are as specified for the SampleAspectRatio parameter in Rec. ITU-T H.273 | ISO / IEC 23091-2. When the vui_aspect_ratio_idc syntax element is not present, the value of vui_aspect_ratio_idc is inferred to be equal to 0. Values of vui_aspect_ratio_idc that are specified as reserved for future use in Rec. ITU-T H.273 | ISO / IEC 23091-2 shall not be present in bitstreams conforming to this edition of this document. Decoders shall interpret values of vui_aspect_ratio_idc that are reserved for future use in Rec. ITU- T H.273 | ISO / IEC 23091-2 as equivalent to the value 0.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0044] vui_sar_width, when present, indicates the horizontal size of the SAR (in arbitrary units) of the luma samples of decoded pictures in the CLVS, unless indicated otherwise by associated SARI SEI messages when vui_aspect_ratio_constant_flag is equal to 0.

[0045] vui_sar_height, when present, indicates the vertical size of the SAR (in the same arbitrary units as vui_sar_width) of the luma samples of decoded pictures in the CLVS, unless indicated otherwise by associated SARI SEI messages when vui_aspect_ratio_constant_flag is equal to 0.

[0046] When present, vui_sar_width and vui_sar_height shall be relatively prime or equal to 0. When vui_aspect_ratio_idc is equal to 0 or vui_sar_width is equal to 0 or vui_sar_height is equal to 0, the SAR is unknown or unspecified in this document or may be determined by other means, such as the SARI SEI message.

[0047] vui_overscan_info_present_flag equal to 1 specifies that the vui_overscan_appropriate_flag is present. When vui_overscan_info_present_flag is equal to 0 or is not present, the preferred display method for the video signal is unknown or unspecified or specified by external means.

[0048] vui_overscan_appropriate_flag equal to 1 indicates that the cropped decoded pictures output are suitable for display using overscan. vui_overscan_appropriate_flag equal to 0 indicates that the cropped decoded pictures output contain visually important information in the entire region out to the edges of the conformance cropping window of the picture, such that the cropped decoded pictures output should not be displayed using overscan. Instead, they should be displayed using either an exact match between the display area and the conformance cropping window, or using underscan. As used in this paragraph, the term "overscan" refers to display processes in which some parts near the borders of the cropped decoded pictures are not visible in the display area. The term "underscan" describes display processes in which the entire cropped decoded pictures are visible in the display area, but they do not cover the entire display area. For display processes that neither use overscan nor underscan, the display area exactly matches the area of the cropped decoded pictures.

[0049] NOTE 2. For example, vui_overscan_appropriate_flag equal to 1 could be used for entertainment television programming or for a live view of people in a videoconference, and vui_overscan_appropriate_flag equal to 0 could be used for computer screen capture or security camera content.

[0050] vui_colour_description_present_flag equal to 1 specifies that vui_colour_primaries, vui_transfer_characteristics, and vui_matrix_coeffs are present. vui_colour_description_present_flag equal to 0 specifies that vui_colour_primaries, vui_transfer_characteristics, and vui_matrix_coeffs are not present.

[0051] vui_colour_primaries indicates the chromaticity coordinates of the source colour primaries. Its semantics are as specified for the ColourPrimaries parameter in Rec. ITU-T H.273 | ISO / IEC 23091-2. When the vui_colour_primaries syntax element is not present, the value of vui_colour_primaries is inferred to be equal to 2 (the chromaticity is unknown or unspecified or determined by other means not specified in this document). Values of vui_colour_primaries that are identified as reserved for future use in Rec. ITU-T H.273 | ISO / IEC 23091-2 shall not be present in bitstreams conforming to this edition of this document. Decoders shall interpret reserved values of vui_colour_primaries as equivalent to the value 2.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0052] vui_transfer_characteristics indicates the transfer characteristics function of the colour representation. Its semantics are as specified for the TransferCharacteristics parameter in Rec. ITU-T H.273 | ISO / IEC 23091-2. When the vui_transfer_characteristics syntax element is not present, the value of vui_transfer_characteristics is inferred to be equal to 2 (the transfer characteristics are unknown or unspecified or determined by other means not specified in this document). Values of vui_transfer_characteristics that are identified as reserved for future use in Rec. ITU- T H.273 | ISO / IEC 23091-2 shall not be present in bitstreams conforming to this edition of this document. Decoders shall interpret reserved values of vui_transfer_characteristics as equivalent to the value 2.

[0053] vui_matrix_coeffs describes the equations used in deriving luma and chroma signals from the green, blue, and red, or Y, Z, and X primaries. Its semantics are as specified for MatrixCoefficients in Rec. ITU- T H.273 | ISO / IEC 23091-2.

[0054] vui_matrix_coeffs shall not be equal to 0 unless both of the following conditions are true: — BitDepthCis equal to BitDepthY, and — ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format).

[0055] The specification of the use of vui_matrix_coeffs equal to 0 under all other conditions is reserved for future use by ITU-T | ISO / IEC.

[0056] vui_matrix_coeffs shall not be equal to 8 unless one of the following conditions is true: — BitDepthC is equal to BitDepthY, and — BitDepthC is equal to BitDepthY + 1 and ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format).

[0057] The specification of the use of vui_matrix_coeffs equal to 8 under all other conditions is reserved for future use by ITU-T | ISO / IEC.

[0058] When the vui_matrix_coeffs syntax element is not present, the value of vui_matrix_coeffs is inferred to be equal to 2 (unknown or unspecified or determined by other means not specified in this document).

[0059] vui_full_range_flag indicates the scaling and offset values applied in association with the matrix coefficients. Its semantics are as specified for the VideoFullRangeFlag parameter in Rec. ITU- T H.273 | ISO / IEC 23091-2. When not present, the value of vui_full_range_flag is inferred to be equal to 0.

[0060] vui_chroma_loc_info_present_flag equal to 1 specifies that either vui_chroma_sample_loc_type_frame or both vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field are present. vui_chroma_loc_info_present_flag equal to 0 specifies that vui_chroma_sample_loc_type_frame, vui_chroma_sample_loc_type_top_field, and vui_chroma_sample_loc_type_bottom_field are not present.

[0061] When ChromaFormatIdc is not equal to 1, vui_chroma_loc_info_present_flag should be equal to 0.

[0062] vui_chroma_sample_loc_type_frame, vui_chroma_sample_loc_type_top_field, and vui_chroma_sample_loc_type_bottom_field, when present, specify the location of chroma samples as follows: — If GeneralProgressiveSourceFlag is equal to 1, GeneralInterlacedSourceFlag is equal to 0, and ChromaFormatIdc is equal to 1 (4:2:0 chroma format), vui_chroma_sample_loc_type_frame specifies the location of chroma samples for both fields of each frame of the CLVS as shown in FIG.1.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) — Otherwise, if ChromaFormatIdc is equal to 1 (4:2:0 chroma format), vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field specify the location of chroma samples for each top field and bottom field of the CLVS, respectively, as shown in FIG.1. — Otherwise (ChromaFormatIdc is not equal to 1), the values of the syntax elements chroma_sample_loc_type, vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field shall be ignored.

[0063] FIG.1 illustrates a location of chroma samples for top and bottom fields for ChromaFormatIdc equal to 1 (4:2:0 chroma format) as a function of vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field in the range of 0 to 5, inclusive.

[0064] When ChromaFormatIdc is equal to 2 (4:2:2 chroma format), the nominal positions of the chroma samples are co-sited with the corresponding luma samples and the nominal locations in a picture are as shown in FIG.2.

[0065] FIG.2 illustrates nominal vertical and horizontal locations of 4:2:2 luma and chroma samples in a picture.

[0066] When ChromaFormatIdc is equal to 3 (4:4:4 chroma format), the nominal positions of the chroma samples are such that all array samples are co-sited for all cases of pictures and the nominal locations in a picture are as shown in FIG.3.

[0067] FIG. 3 illustrates nominal vertical and horizontal locations of 4:4:4 luma and chroma samples in a picture.

[0068] When ChromaFormatIdc is equal to 0, there is no chroma sample array.

[0069] When present, the values of vui_chroma_sample_loc_type_frame, vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field shall be in the range of 0 to 6, inclusive.

[0070] When ChromaFormatIdc is equal to 1 and vui_chroma_loc_info_present_flag is equal to 0, vui_chroma_sample_loc_type_frame is not present and is inferred to be equal to 6, which indicates that the location of the chroma samples is unknown or unspecified or specified by other means not specified in this document. When vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field are not present, the values of vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field are inferred to be equal to vui_chroma_sample_loc_type_frame.

[0071] NOTE 3. In Rec. ITU-T H.266 | ISO / IEC 23090-3 and Rec. ITU-T H.265 | ISO / IEC 23008-2, a nominal chroma sampling type is identified for ChromaFormatIdc equal to 1 that corresponds to vui_chroma_sample_loc_type_frame, vui_chroma_sample_loc_type_top_field and vui_chroma_sample_loc_type_bottom_field equal to 0.

[0072] FIG.4 illustrates the indicated relative position of the top-left chroma sample when ChromaFormatIdc is equal to 1 (i.e., the 4:2:0 chroma format), and vui_chroma_sample_loc_type_top_field or vui_chroma_sample_loc_type_bottom_field is equal to the value of a variable Chroma420LocType. The region represented by the top-left 4:2:0 chroma sample (depicted as a large grey, solid-line square with a large grey dot at its center) is shown relative to the region represented by the top-left luma sample (depicted as a small black square with a small black dot at its center). The regions represented by neighboring luma samples are depicted as small grey, dotted- line squares with small grey dots at their centers.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0073] FIG.4 illustrates a location of the top-left chroma sample when ChromaFormatIdc is equal to 1 (4:2:0 chroma format) and Chroma420LocType is equal to 0 to 5, inclusive, from left to right.

[0074] The relative spatial positioning of the chroma samples, as illustrated in FIG. 5, can be expressed by defining two variables HorizontalOffsetC and VerticalOffsetC as a function of ChromaFormatIdc and the variable Chroma420LocType as given by Table 2, where HorizontalOffsetC is the horizontal (x in FIG.5) position of the center of the top-left chroma sample relative to the center of the top-left luma sample in units of luma samples and VerticalOffsetC is the vertical (y in FIG.5) position of the center of the top-left chroma sample relative to the center of the top-left luma sample in units of luma samples.

[0075] In a typical finite impulse response (FIR) filter design, when ChromaFormatIdc is equal to 1 (4:2:0 chroma format) or 2 (4:2:2 chroma format), HorizontalOffsetC and VerticalOffsetC would serve as the phase offsets for the horizontal and vertical filter operations, respectively, for separable downsampling from 4:4:4 chroma format to the chroma format indicated by ChromaFormatIdc.

[0076] FIG.5 illustrates a location of the top-left chroma sample when ChromaFormatIdc is equal to 1 (4:2:0 chroma format) when Chroma420LocType is equal to 1. Table 2 — Definition of HorizontalOffsetC and VerticalOffsetC as a function of ChromaFormatIdc and Chroma420LocType ChromaFormatIdc Chroma420LocTyp HorizontalOffsetC VerticalOffsetC

[0077] tendedfor interpretation according to Rec. ITU-R BT.2020 or Rec. ITU-R BT.2100, vui_chroma_loc_info_present_flag should be equal to 1, and vui_chroma_sample_loc_type_frame, vui_chroma_sample_loc_type_top_field, and vui_chroma_sample_loc_type_bottom_field (as applicable) should be equal to 2.

[0078] VUI parameters apply to one or more CLVSs.

[0079] NOTE 1. The interpretation of several syntax elements of the VUI parameters are specified by reference to coding-independent code points specified in Rec. ITU-T H.273 | ISO / IEC 23091-2. Further information about the usage of such code points is found in ITU-T H-Suppl.19 | ISO / IEC TR 23091-4.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 3.4 SEI messages referencing MatrixCoefficients

[0080] In VSEI [5], besides VUI, there are some SEI messages that reference MatrixCoefficients in CICP. Specifically, they include Colour transform information SEI message, Film grain characteristics SEI message and Neural-network post-filter characteristics SEI message. 3.4.1. Film grain characteristics SEI message 3.4.1.1 Film grain characteristics SEI message syntax film_grain_characteristics( payloadSize ) { Descriptor fg characteristics cancel flag u(1)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) } } 3

[0081] This SEI message provides the decoder with a parameterized model for a film grain synthesis. The film grain synthesis process should be applied to the decoded pictures prior to their display.

[0082] NOTE 1. For example, an encoder can use the film grain characteristics SEI message to characterize film grain that was present in the original source video material and was removed by pre-processing filtering techniques. Synthesis of simulated film grain on the input images, which could be the decoded pictures or converted from the decoded pictures, for the display process is optional and does not necessarily exactly follow the specified semantics of the film grain characteristics SEI message. When synthesis of simulated film grain on the input images for the display process is performed, there is no requirement that the method by which the synthesis is performed be the same as the parameterized model for the film grain as provided in the film grain characteristics SEI message.

[0083] NOTE 2. The display process is not specified in this document.

[0084] NOTE 3. SMPTE RDD 5 (2006) specifies a film grain simulator based on the information provided in the film grain characteristics SEI message.

[0085] Use of this SEI message requires the definition of the following variables: — A picture width and picture height in units of luma samples, denoted herein by PicWidthInLumaSamples and PicHeightInLumaSamples, respectively. — When the syntax element fg_separate_colour_description_present_flag of the film grain characteristics SEI message is equal to 0, the following additional variables: — A chroma format indicator, denoted herein by ChromaFormatIdc, as described in subclause 7.3. — A bit depth for the samples of the luma component, denoted herein by BitDepthY, and when ChromaFormatIdc is not equal to 0, a bit depth for the samples of the two associated chroma components, denoted herein by BitDepthC.

[0086] The film grain models specified in the film grain characteristics SEI message are expressed for application to decoded pictures that have 4:4:4 colour format with luma and chroma bit depths corresponding to the luma and chroma bit depths of the film grain model and use the same colour representation domain as the identified film grain model. When the colour format of the decoded video is not 4:4:4 or the decoded video uses a different luma or chroma bit depth from that of the film grain model or uses a different colour representation domain from that of the identified film grain model, an unspecified conversion process is expected to be applied to convert the decoded pictures to the form that is expressed for application of the film grain model.

[0087] NOTE 4. Because the use of a specific method is not required for performing the film grain generation function used by the display process, a decoder could, if desired, down-convert the model information for chroma in order to simulate film grain for other chroma formats (4:2:0 or 4:2:2) rather than up-converting the decoded video (using a method not specified in this document) before performing film grain generation.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0088] fg_characteristics_cancel_flag equal to 1 indicates that the SEI message cancels the persistence of any previous film grain characteristics SEI message in output order that applies to the current layer. fg_characteristics_cancel_flag equal to 0 indicates that film grain modelling information follows.

[0089] fg_model_id identifies the film grain simulation model as specified in Table 5. The value of fg_model_id shall be in the range of 0 to 1, inclusive. The values of 2 and 3 for fg_model_id are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders shall ignore film grain characteristic SEI messages with fg_model_id equal to 2 or 3. Table 5 — fg_model_id values Value Description 0 Fre uenc filterin

[0090] fg_separate_colour__ _ hat a distinct combination of luma bit depth, chroma bit depth, video full range flag, colour primaries, transfer characteristics, and matrix coefficients for the film grain characteristics specified in the SEI message is present in the film grain characteristics SEI message syntax. fg_separate_colour_description_present_flag equal to 0 indicates that the combination of luma bit depth, chroma bit depth, video full range flag, colour primaries, transfer characteristics, and matrix coefficients for the film grain characteristics specified in the SEI message are the same as indicated in VUI parameters for the CLVS.

[0091] NOTE 5. When fg_separate_colour_description_present_flag is equal to 1, any of the luma bit depth, chroma bit depth, video full range flag, colour primaries, transfer characteristics, and matrix coefficients specified for the film grain characteristics specified in the SEI message could differ from that for the pictures in the CLVS.

[0092] When VUI parameters are not present for the CLVS or the value of vui_colour_description_present_flag is equal to 0, and equivalent information to that conveyed when vui_colour_description_present_flag is equal to 1 is not conveyed by external means, fg_separate_colour_description_present_flag shall be equal to 1.

[0093] The input image Î, which may be the decoded picture or converted from the decoded picture, used in the equations in this subclause is in the same colour representation domain as the simulated film grain signal. Therefore, when any of these parameters does differ from that for the pictures in CLVS, the input image Î used in the equations in this subclause would be in a different colour representation domain than that for the pictures in the CLVS. For example, when the value of fg_bit_depth_luma_minus8 + 8 is greater than BitDepthY (i.e., the bit depth of the luma component of the pictures in the CLVS), the bit depth of the input image Î used in the equations in this subclause is also greater than BitDepthY. In such a case, the input image Î corresponding to an actual decoded picture would be generated by converting the actual decoded picture to be in the same colour representation domain as the simulated film grain signal. The process for converting an actual decoded picture to the 4:4:4 colour format with same colour representation domain as the simulated film grain signal is not specified in this document.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0094] fg_bit_depth_luma_minus8 plus 8 specifies the bit depth used for the luma component of the film grain characteristics specified in the SEI message. When fg_bit_depth_luma_minus8 is not present in the film grain characteristics SEI message, the value of fg_bit_depth_luma_minus8 is inferred to be equal to BitDepthY − 8.

[0095] The value of fgBitDepth

[0000] is derived as follows: fgBitDepth

[0000] = fg_bit_depth_luma_minus8 + 8 (19)

[0096] fg_bit_depth_chroma_minus8 plus 8 specifies the bit depth used for the Cb and Cr components of the film grain characteristics specified in the SEI message. When fg_bit_depth_chroma_minus8 is not present in the film grain characteristics SEI message, the value of fg_bit_depth_chroma_minus8 is inferred to be equal to BitDepthC − 8.

[0097] The value of fgBitDepth[ c ] for c = 1 and 2 is derived as follows: fgBitDepth[ c ] = fg_bit_depth_chroma_minus8 + 8, with c = 1, 2 (20)

[0098] fg_full_range_flag has the same semantics as specified in subclause 7.3 for the vui_full_range_flag syntax element, except as follows: — fg_full_range_flag specifies the video full range flag of the film grain characteristics specified in the SEI message, rather than the video full range flag used for the CLVS. — When fg_full_range_flag is not present in the film grain characteristics SEI message, the value of fg_full_range_flag is inferred to be equal to vui_full_range_flag.

[0099] fg_colour_primaries has the same semantics as specified in subclause 7.3 for the vui_colour_primaries syntax element, except as follows: — fg_colour_primaries specifies the colour primaries of the film grain characteristics specified in the SEI message, rather than the colour primaries used for the CLVS. — When fg_colour_primaries is not present in the film grain characteristics SEI message, the value of fg_colour_primaries is inferred to be equal to vui_colour_primaries.

[0100] fg_transfer_characteristics has the same semantics as specified in subclause 7.3 for the vui_transfer_characteristics syntax element, except as follows: — fg_transfer_characteristics specifies the transfer characteristics of the film grain characteristics specified in the SEI message, rather than the transfer characteristics used for the CLVS. — When fg_transfer_characteristics is not present in the film grain characteristics SEI message, the value of fg_transfer_characteristics is inferred to be equal to vui_transfer_characteristics.

[0101] fg_matrix_coeffs has the same semantics as specified in subclause 7.3 for the vui_matrix_coeffs syntax element, except as follows: — fg_matrix_coeffs specifies the matrix coefficients of the film grain characteristics specified in the SEI message, rather than the matrix coefficients used for the CLVS. — When fg_matrix_coeffs is not present in the film grain characteristics SEI message, the value of fg_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. — The values allowed for fg_matrix_coeffs are not constrained by the chroma format of the decoded video pictures that is indicated by the value of ChromaFormatIdc for the semantics of the VUI parameters.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0102] fg_blending_mode_id identifies the blending mode used to blend the simulated film grain with the input images as specified in Table 6. fg_blending_mode_id shall be in the range of 0 to 1, inclusive. The values of 2 and 3 for fg_blending_mode_id are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders shall ignore film grain characteristic SEI messages with fg_blending_mode_id equal to 2 or 3. Table 6 — fg_blending_mode_id values Value Description 0 Additive

[0103] Depending on the va_ _ _ , de is specified as follows: If fg_blending_mode_id is equal to 0, the blending mode is additive as specified by: Igrain[ c ][ x ][ y ] = Clip3( 0, ( 1 << fgBitDepth[ c ] ) − 1, Î[ c ][ x ][ y ] + G[ c ][ x ][ y ] ) Otherwise (fg_blending_mode_id is equal to 1), the blending mode is multiplicative as specified by: Igrain[ c ][ x ][ y ] = Clip3( 0, ( 1 << fgBitDepth[ c ] ) − 1, Î[ c ][ x ][ y ] + (22) Round( ( Î[ c ][ x ][ y ] * G[ c ][ x ][ y ] ) ÷ ( ( 1 << fgBitDepth[ c ] ) − 1 ) ) ) where Î[ c ][ x ][ y ] represents the sample value at coordinates x, y of the colour component c of the input image Î, G[ c ][ x ][ y ] is the simulated film grain value at the same position and colour component, and fgBitDepth[ c ] is the number of bits used for each sample in a fixed-length unsigned binary representation of the arrays Igrain[ c ][ x ][ y ], Î[ c ][ x ][ y ], and G[ c ][ x ][ y ], where c = 0..2, x = 0..PicWidthInLumaSamples − 1, and y = 0..PicHeightInLumaSamples − 1.

[0104] fg_log2_scale_factor specifies a scale factor used in the film grain characterization equations.

[0105] fg_comp_model_present_flag[ c ] equal to 0 indicates that film grain is not modelled on the c-th colour component, where c equal to 0 refers to the luma component, c equal to 1 refers to the Cb component, and c equal to 2 refers to the Cr component. fg_comp_model_present_flag[ c ] equal to 1 indicates that syntax elements specifying modelling of film grain on colour component c are present in the SEI message.

[0106] When fg_separate_colour_description_present_flag is equal to 0 and ChromaFormatIdc is equal to 0, the value of fg_comp_model_present_flag

[0001] and fg_comp_model_present_flag

[0002] shall be equal to 0.

[0107] fg_num_intensity_intervals_minus1[ c ] plus 1 specifies the number of intensity intervals for which a specific set of model values has been estimated.

[0108] NOTE 6. The intensity intervals could overlap in order to simulate multi-generational film grain.

[0109] fg_num_model_values_minus1[ c ] plus 1 specifies the number of model values present for each intensity interval in which the film grain has been modelled. The value of fg_num_model_values_minus1[ c ] shall be in the range of 0 to 5, inclusive.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0110] fg_intensity_interval_lower_bound[ c ][ i ] specifies the lower bound of the i-th intensity interval for which the set of model values applies.

[0111] fg_intensity_interval_upper_bound[ c ][ i ] specifies the upper bound of the i-th intensity interval for which the set of model values applies.

[0112] The variable intensityIntervalIdx[ c ][ x ][ y ][ j ] represents the j-th index to the list of intensity intervals selected for the sample value Î[ c ][ x ][ y ] for c = 0..2, x = 0..PicWidthInLumaSamples − 1, y = 0..PicHeightInLumaSamples − 1, and j = 0..numApplicableIntensityIntervals[ c ][ x ][ y ] − 1, where numApplicableIntensityIntervals[ c ][ x ][ y ] is derived below.

[0113] Depending on the value of fg_model_id, the selection of the one or more intensity intervals for the sample value Î[ c ][ x ][ y ] is specified as follows: — The variable numApplicableIntensityIntervals[ c ][ x ][ y ] is initially set equal to 0.

[0114] If fg_model_id is equal to 0, the following applies: — The top-left sample location ( xB, yB ) of the current 8x8 block b that contains the sample value Î[ c ][ x ][ y ] is derived as ( xB, yB ) = ( x / 8, y / 8 ). — The average value bavgof the current 8x8 block b is derived as follows: sum8x8 = 0 for( i = 0; i < 8; i++ ) for( j = 0; j < 8; j++ ) * * j ] [ c ] − 3 ) ) ) >> ( fgBitDepth[ c ] − 2 ) )— c x y derived as follows: for( i = 0, j = 0; i <= fg_num_intensity_intervals_minus1[ c ]; i++ ) [ c ][ i ] && fg_intensity_interval_upper_bound[ c ][ i ] )[ c ][ x ][ y ][ j ] = i j++ } numApplicableIntensityIntervals[ c ][ x ][ y ] = j

[0115] Otherwise (fg_model_id is equal to 1), the value of intensityIntervalIdx[ c ][ x ][ y ][ j ] is derived as follows: I8[ c ][ x ][ y ] = ( fgBitDepth[ c ] == 8 ) ? ( Î[ c ][ x ][ y ] : Clip3( 0, 255, ( Î[ c ][ x ][ y ] + ( 1 << ( fgBitDepth[ c ] − 9 ) ) ) >> ( fgBitDepth[ c ] − 8 )) for( i = 0, j = 0; i <= fg_num_intensity_intervals_minus1[ c ]; i++ ) if( I8[ c ][ x ][ y ] >= fg_intensity_interval_lower_bound[ c ][ i ] && I8[ c ][ x ][ y ] <= fg_intensity_interval_upper_bound[ c ][ i ] )Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) { intensityIntervalIdx[ c ][ x ][ y ][ j ] = i j++ } numApplicableIntensityIntervals[ c ][ x ][ y ] = j

[0116] Samples that do not fall into any of the defined intervals (i.e., those samples for which the value of numApplicableIntensityIntervals[ c ][ x ][ y ] is equal to 0) are not modified by the grain generation function. Samples that fall into more than one interval (i.e., those samples for which the value of numApplicableIntensityIntervals[ c ][ x ][ y ] is greater than 1) will originate multi-generation grain. Multi-generation grain results from adding the grain computed independently for each of the applicable intensity intervals.

[0117] In the equations in the remainder of this subclause, the variable sj in each instance of the list fg_comp_model_value[ c ][ sj ] is the value of intensityIntervalIdx[ c ][ x ][ y ][ j ] derived for the sample value Î[ c ][ x ][ y ].

[0118] fg_comp_model_value[ c ][ i ][ j ] specifies the j-th model value for the colour component c and the i-th intensity interval. The set of model values has different meaning depending on the value of fg_model_id.

[0119] The value of fg_comp_model_value[ c ][ i ][ j ] is constrained as follows, and could be additionally constrained as specified elsewhere in this subclause: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ][ j ] shall be in the range of 0 to 2fgBitDepth[ c ]− 1, inclusive. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ][ j ] shall be in the range of −2( fgBitDepth[ c ] − 1 )to 2( fgBitDepth[ c ] − 1 )− 1, inclusive.

[0120] Depending on the value of fg_model_id, the synthesis of the film grain is modelled as follows: — If fg_model_id is equal to 0, a frequency filtering model enables simulating the original film grain for c = 0..2, x = 0..PicWidthInLumaSamples − 1, and y = 0..PicHeightInLumaSamples − 1 as specified by: G[ c ][ x ][ y ] = ( fg_comp_model_value[ c ][ sj]

[0000] * Q[ c ][ x ][ y ] + fg_comp_model_value[ c ][ sj]

[0005] *blocks gaussRv with random-valued elements gaussRvij generated with a normalized Gaussian distribution (independent and identically distributed Gaussian random variable samples with zero mean and unity variance) and where the value of an element G[ c − 1 ][ x ][ y ] used in the right-hand side of the equation is inferred to be equal to 0 when c − 1 is less than 0.

[0121] NOTE 7. A normalized Gaussian random variable can be generated from two independent, uniformly distributed random values over the interval from 0 to 1 (and not equal to 0), denoted as uRv0 and uRv1, using the Box- Muller transformation specified by: gaussRvi,j = Sqrt( −2 * Ln( uRv0 ) ) * Cos( 2 * π * uRv1 ) (27) where π is Archimedes' constant 3.141592653589793....Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) The band-pass filtering of blocks gaussRv can be performed in the discrete cosine transform (DCT) domain as follows: for( y = 0; y < 16; y++ ) for( x = 0; x < 16; x++ ) if( ( x < fg_comp_model_value[ c ][ sj ][3] && y < fg_comp_model_value[ c ][ sj ][4]) | |where IDCT16x16( z ) refers to a unitary inverse discrete cosine transformation (IDCT) operating on a 16x16 matrix argument z as specified by: IDCT16x16( z ) = r * z * rT(29) where the superscript T indicates a matrix transposition and r is the 16x16 matrix with elements rijspecified by: r= ( ^ i ^ ^ 0 ^ ? 1 : Sqrt ^ 2 ^* Cos^ i * ^ 2 * j + 1 ^ * ^ ^i ,j 4 ^^ 32 ^(30) ^ where π isQ[ c ] is formed by the frequency-filtered blocks filteredRv.

[0122] NOTE 8. Coded model values are based on blocks of size 16x16, but a decoder implementation could use other block sizes. For example, decoders implementing the IDCT on 8x8 blocks could down-convert by a factor of two the set of coded model values fg_comp_model_value[ c ][ sj ][ i ] for i equal to 1..4.

[0123] NOTE 9 . To reduce the degree of visible blocks that result from mosaicking the frequency-filtered blocks filteredRv, decoders could apply a low-pass filter to the boundaries between frequency-filtered blocks. — Otherwise (fg_model_id is equal to 1), an auto-regression model enables simulating the original film grain for c = 0..2, x = 0..PicWidthInLumaSamples − 1, and y = 0..PicHeightInLumaSamples − 1 as specified by: G[ c ][ x ][ y ] = ( fg_comp_model_value[ c ][ sj ]

[0000] * n[ c ][ x][ y ] + fg_comp_model_value[ c ][ sj ][1] * ( G[ c ][ x − 1 ][ y ] + ( ( fg_comp_model_value[ c ][ sj ][4] * G[ c ][ x ][ y − 1 ] ) >> fg_log2_scale_factor ) ) + fg_comp_model_value[ c ][ sj ][3] * ( ( fg_comp_model_value[ c ][ sj ][4] * ( G[ c ][ x − 1 ][ y − 1 ] + (31) G[ c ][ x + 1 ][ y − 1 ] ) ) >> fg_log2_scale_factor ) + fg_comp_model_value[ c ][ sj ][5] * ( G[ c ][ x − 2 ][ y ] + ( ( fg_comp_model_value[ c ][ sj ][4] * fg_comp_model_value[ c ][ sj ][4] * G[ c ][ x ][ y − 2 ] ) >> ( 2 * fg_log2_scale_factor ) ) ) +Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) fg_comp_model_value[ c ][ sj ][2] * G[ c − 1 ][ x ][ y ] ) >> fg_log2_scale_factor where n[ c ][ x ][ y ] is a random value with normalized Gaussian distribution (independent and identically distributed Gaussian random variable samples with zero mean and unity variance for each value of c, x, and y) and where the value of an element G[ c ][ x ][ y ] used in the right-hand side of the equation is inferred to be equal to 0 when any of the following conditions are true: — c is less than 0, — x is less than 0, — y is less than 0.

[0124] fg_comp_model_value[ c ][ i ]

[0000] provides the first model value for the model as specified by fg_model_id. fg_comp_model_value[ c ][ i ]

[0000] corresponds to the standard deviation of the Gaussian noise term in the generation functions specified in Formulae 26 through 31.

[0125] fg_comp_model_value[ c ][ i ]

[0001] provides the second model value for the model as specified by fg_model_id. When fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0001] shall be greater than or equal to 0 and less than 16.

[0126] When not present in the film grain characteristics SEI message, fg_comp_model_value[ c ][ i ]

[0001] is inferred as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0001] is inferred to be equal to 8. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0001] is inferred to be equal to 0.

[0127] fg_comp_model_value[ c ][ i ]

[0001] is interpreted as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0001] indicates the horizontal high cut frequency to be used to filter the DCT of a block of 16x16 random values. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0001] indicates the first order spatial correlation for neighboring samples ( x − 1, y ) and ( x, y − 1 ).

[0128] fg_comp_model_value[ c ][ i ]

[0002] provides the third model value for the model as specified by fg_model_id. When fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0002] shall be greater than or equal to 0 and less than 16.

[0129] When not present in the film grain characteristics SEI message, fg_comp_model_value[ c ][ i ]

[0002] is inferred as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0002] is inferred to be equal to fg_comp_model_value[ c ][ i ]

[0001] — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0002] is inferred to be equal to 0.

[0130] fg_comp_model_value[ c ][ i ]

[0002] is interpreted as follows:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0002] indicates the vertical high cut frequency to be used to filter the DCT of a block of 16x16 random values. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0002] indicates the colour correlation between consecutive colour components.

[0131] fg_comp_model_value[ c ][ i ]

[0003] provides the fourth model value for the model as specified by fg_model_id. When fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0003] shall be greater than or equal to 0 and less than or equal to fg_comp_model_value[ c ][ i ]

[0001] .

[0132] When not present in the film grain characteristics SEI message, fg_comp_model_value[ c ][ i ]

[0003] is inferred to be equal to 0.

[0133] fg_comp_model_value[ c ][ i ]

[0003] is interpreted as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0003] indicates the horizontal low cut frequency to be used to filter the DCT of a block of 16x16 random values. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0003] indicates the first order spatial correlation for neighboring samples ( x − 1, y − 1 ) and ( x + 1, y − 1 ).

[0134] fg_comp_model_value[ c ][ i ]

[0004] provides the fifth model value for the model as specified by fg_model_id. When fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0004] shall be greater than or equal to 0 and less than or equal to fg_comp_model_value[ c ][ i ]

[0002] .

[0135] When not present in the film grain characteristics SEI message, fg_comp_model_value[ c ][ i ]

[0004] is inferred to be equal to fg_model_id.

[0136] fg_comp_model_value[ c ][ i ]

[0004] is interpreted as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0004] indicates the vertical low cut frequency to be used to filter the DCT of a block of 16x16 random values. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0004] indicates the aspect ratio of the modelled grain.

[0137] fg_comp_model_value[ c ][ i ]

[0005] provides the sixth model value for the model as specified by fg_model_id.

[0138] When not present in the film grain characteristics SEI message, fg_comp_model_value[ c ][ i ]

[0005] is inferred to be equal to 0.

[0139] fg_comp_model_value[ c ][ i ]

[0005] is interpreted as follows: — If fg_model_id is equal to 0, fg_comp_model_value[ c ][ i ]

[0005] indicates the colour correlation between consecutive colour components. — Otherwise (fg_model_id is equal to 1), fg_comp_model_value[ c ][ i ]

[0005] indicates the second order spatial correlation for neighboring samples ( x, y − 2 ) and ( x − 2, y ).

[0140] fg_characteristics_persistence_flag specifies the persistence of the film grain characteristics SEI message for the current layer.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0141] fg_characteristics_persistence_flag equal to 0 specifies that the film grain characteristics SEI message applies to the current decoded picture only.

[0142] fg_characteristics_persistence_flag equal to 1 specifies that the film grain characteristics SEI message applies to the current decoded picture and persists for all subsequent pictures of the current layer in output order until one or more of the following conditions are true: — A new CLVS of the current layer begins. — The bitstream ends. — A picture in the current layer in an AU associated with a film grain characteristics SEI message is output that follows the current picture in output order. 3.4.2 Colour transform information SEI message 3.4.2.1 Colour transform information SEI message syntax colour_transform_info( payloadSize ) { Descriptor colour transform id ue(v)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) if( colour_transform_lut2_present_flag ) for( i = 0; i < colourTransformSize; i++ ) 3

[0143] Use of this SEI message requires the definition of the following variable: — A chroma format indicator, denoted herein by ChromaFormatIdc, as described in subclause 7.3.

[0144] The colour transform information (CTI) SEI message provides information to enable remapping of the reconstructed colour samples of the output pictures for purposes such as converting the output pictures to a representation that is more suitable for an alternative display. The colour transform model used in the CTI SEI message is composed of a first piece-wise linear function applied to the first colour component. Depending on the values of syntax elements colour_transform_cross_component_flag, colour_transform_cross_comp_inferred_flag, and colour_transform_lut2_present_flag, one or two additional piece-wise linear functions may be signalled for the second and third colour components.

[0145] When ChromaFormatIdc is equal to 0 (monochrome), the CTI SEI message shall not be present, although decoders shall also allow such messages to be present and shall ignore any such CTI SEI messages when present.

[0146] colour_transform_id contains an identifying number that may be used to identify the purpose of the CTI. The value of colour_transform_id may be used (in a manner not specified in this document) to indicate that the input to the remapping process is the output of some conversion process that is not specified in this document, such as a conversion of the picture to some alternative colour representation (e.g., conversion from a YCbCr colour representation to a GBR colour representation). When more than one CTI SEI message is present with the same value of colour_transform_id, the content of these CTI SEI messages shall be the same. When CTI SEI messages are present that have more than one value of colour_transform_id, this may indicate that the remapping processes indicated by the different values of colour_transform_id are alternatives that are provided for different purposes or that a cascading of remapping processes is to be applied in a sequential order (an order that is not specified in this document). The value of colour_transform_id shall be in the range of 0 to 232− 2, inclusive.

[0147] Values of colour_transform_id from 0 to 255 and from 512 to 231− 1 may be used as determined by the application. Values of colour_transform_id from 256 to 511, inclusive, and from 231to 232− 2, inclusive, are reserved for future use by ITU-T | ISO / IEC. Decoders shall ignore the CTI SEI messages containing a value of colour_transform_id in the range of 256 to 511, inclusive, or in the range of 231to 232− 2, inclusive, and bitstreams conforming to this edition of this document shall not contain colour_transform_id with such values.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0148] NOTE: The colour_transform_id can be used to support different remapping processes that are suitable for different display scenarios. For example, different values of colour_transform_id may correspond to different remapped colour spaces supported by displays.

[0149] colour_transform_cancel_flag equal to 1 indicates that the CTI SEI message cancels the persistence of any previous CTI SEI message in output order that applies to the current layer. colour_transform_cancel_flag equal to 0 indicates that CTI follows.

[0150] colour_transform_persistence_flag specifies the persistence of the CTI SEI message for the current layer.

[0151] colour_transform_persistence_flag equal to 0 specifies that the CTI SEI message applies to the current decoded picture only.

[0152] colour_transform_persistence_flag equal to 1 specifies that the CTI SEI message applies to the current decoded picture and persists for all subsequent pictures of the current layer in output order until one or more of the following conditions are true: — A new CLVS of the current layer begins. — The bitstream ends. — A picture in the current layer in an AU associated with a CTI SEI message is output that follows the current picture in output order.

[0153] colour_transform_video_signal_info_present_flag equal to 1 specifies that syntax elements colour_transform_full_range_flag, colour_transform_primaries, colour_transform_transfer_function and colour_transform_matrix_coefficients are present, colour_transform_video_signal_info_present_flag equal to 0 specifies that syntax elements colour_transform_full_range_flag, colour_transform_primaries, colour_transform_transfer_function and colour_transform_matrix_coefficients are not present.

[0154] colour_transform_full_range_flag has the same semantics as specified in subclause 7.3 for the vui_full_range_flag syntax element, except that colour_transform_full_range_flag identifies the colour space of the remapped reconstructed picture, rather than the colour space used for the CLVS. When not present, the value of colour_transform_full_range_flag is inferred to be equal to the value of vui_full_range_flag.

[0155] colour_transform_primaries has the same semantics as specified in subclause 7.3 for the vui_colour_primaries syntax element, except that colour_transform_primaries identifies the colour space of the remapped reconstructed picture, rather than the colour space used for the CLVS. When not present, the value of colour_transform_primaries is inferred to be equal to the value of vui_colour_primaries.

[0156] colour_transform_transfer_function has the same semantics as specified in subclause 7.3 for the vui_transfer_characteristics syntax element, except that colour_transform_transfer_function identifies the colour space of the remapped reconstructed picture, rather than the colour space used for the CLVS. When not present, the value of colour_transform_transfer_function is inferred to be equal to the value of vui_transfer_characteristics.

[0157] colour_transform_matrix_coefficients has the same semantics as specified in subclause 7.3 for the vui_matrix_coeffs syntax element, except that colour_transform_matrix_coefficients identifies the colour space of theAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) remapped reconstructed picture, rather than the colour space used for the CLVS. When not present, the value of colour_transform_matrix_coefficients is inferred to be equal to the value of vui_matrix_coeffs.

[0158] colour_transform_bit_depth_minus8 plus 8 specifies the bit depth of the colour components of the associated pictures for purposes of interpretation of the CTI SEI message. When any CTI SEI message is present with the value of colour_transform_bit_depth plus 8 not equal to the bit depth of the decoded colour components, the SEI message refers to the hypothetical result of a conversion operation performed to convert the decoded colour component samples to the bit depth equal to colour_transform_input_bit_depth plus 8.

[0159] The value of colour_transform_bit_depth plus 8 shall be in the range of 8 to 16, inclusive. Values of colour_transform_bit_depth from in the range of 17 to 23, inclusive, are reserved for future use by ITU-T | ISO / IEC. Decoders shall ignore the CTI SEI messages that contain a value of colour_transform_bit_depth in the range of 17 to 23, inclusive, and bitstreams conforming to this edition of this document shall not contain colour_transform_bit_depth with such values.

[0160] bitDepth is set equal to ( colour_transform_bit_depth + 8 ).

[0161] colour_transform_log2_number_of_points_per_lut_minus1 specifies the log2 of the number of pivot points in the piece-wise linear remapping functions minus 1.

[0162] log2numLutPoints is set equal to ( colour_transform_log2_number_of_points_per_lut_minus1 + 1 ).

[0163] numLutPoints is set equal to ( 1 << log2numLutPoints ).

[0164] colourTransformSize is set equal to ( numLutPoints + 1 ).

[0165] log2distX is set equal to ( bitDepth − log2numLutPoints ).

[0166] colour_transform_cross_component_flag equal to 1 indicates that the remapping of the second and third colour components is performed as cross-component remapping based on the first colour component. colour_transform_cross_component_flag equal to 0 indicates that intra-component remapping is applied to the second and third colour components.

[0167] maxIntraComp is set equal to ( 2 * ( 1 − colour_transform_cross_component_flag ) ).

[0168] colour_transform_cross_comp_inferred_flag equal to 1 indicates that the remapping piece-wise linear functions of the second and third colour components are inferred from the remapping piece-wise linear function of the first colour component. colour_transform_cross_comp_inferred_flag equal to 0 indicates that the remapping piece- wise linear functions of the second and third colour components are signalled. When not present, the value of colour_transform_cross_comp_inferred_flag is inferred to be equal to 0.

[0169] colour_transf_lut[ c ][ i ] specifies the piecewise linear remapping function of the colour component of index c. When colour_transf_lut

[0001] [ i ] is present and colour_transf_lut

[0002] [ i ] is not present, the value of colour_transf_lut

[0002] [ i ] is inferred to be equal to colour_transf_lut

[0001] [ i ]. The length of colour_transf_lut[ c ][ i ] is 2 + bitDepth − log2numLutPoints bits.

[0170] colour_transform_lut2_present_flag equal to 1 specifies that colour_transf_lut

[0002] [ i ] is present in the CTI SEI message. colour_transform_lut2_present_flag equal to 0 specifies that colour_transf_lut

[0002] [ i ] is not presentAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) in the CTI SEI message. When not present, the value of colour_transform_lut2_present_flag is inferred to be equal to 0.

[0171] colour_transform_chroma_offset specifies the CTI chroma offset. When not present, colour_transform_chroma_offset is inferred to be equal to 0. The length of colour_transform_chroma_offset is 2 + bitDepth − log2numLutPoints bits.

[0172] The remapping process of the input picture components rec[ c ], with width and height equal to picWidth[ c ] and picHeight[ c ], respectively, to the output remapped picture components map[ c ], for c=0..2, is performed as follows.

[0173] The array pivotPointX is derived as follows. — For j=0..( numLutPoints − 1 ), pivotPointX[ j ] is set equal to ( j << log2distX ). For c=0..maxIntraComp, the arrays pivotPointY[ c ] and slope[ c ] are derived as follows: — pivotPointY[ c ]

[0000] is set equal to colour_transf_lut[ c ]

[0000] — For j=1..( numLutPoints − 1 ), pivotPointY[ c ][ j ] is derived as follows: pivotPointY[ c ][ j ] = pivotPointY[ c ][ j − 1 ] + colour_transf_lut[ c ][ j ] (68) — For j=0..( numLutPoints − 1 ), slope[ c ][ j ] is derived as follows: slope[ c ][ j ] = ( ( colour_transf_lut[ c ][ j + 1 ] << 11 ) + ( 1 << ( log2distX − 1 ) ) ) >> log2distX (69)

[0174] When colour_transform_cross_component_flag is equal to 1, the arrays ccPivotPointY[ c ] and ccSlope[ c ] are derived as follows, for c=1..2: — If colour_transform_cross_comp_inferred_flag is equal to 0, ccPivotPointY[ c ] is derived as follows: — For j=0..numLutPoints, ccPivotPointY[ c ][ j ] is set equal to ( colour_transf_lut[ c ][ j ] << ( 11 − log2distX ) ). — Otherwise (colour_transform_cross_comp_inferred_flag is equal to 1), ccPivotPointY[ c ] is derived as follows: Otherwise (colour_transform_cross_comp_inferred_flag is equal to 1), ccPivotPointY[ c ] is derived as follows: For j=0..( numLutPoints − 1 ), tmpPivotPt[ j ] is derived as follows: If colour_transf_lut

[0000] [ j + 1 ] is equal to 0, tmpPivotPt[ j ] is set equal to ( 1 << 11 ). Otherwise, tmpPivotPt[ j ] is derived as follows: tmpPivotPt[ j ] = ( colour_transf_lut

[0000] [ j + 1 ] + colour_transform_chroma_offset ) << ( 11 − log2distX ) The array ccPivotPointY[ c ] is derived as follows: For j=1..( numLutPoints − 1 ), ccPivotPointY[ c ][ j ] is derived as follows:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) ccPivotPointY[ c ][ j ] = ( tmpPivotPt[ j ] + tmpPivotPt[ j − 1 ] + 1 ) / 2 ccPivotPointY[ c ]

[0000] is set equal to tmpPivotPt

[0000] . ccPivotPointY[ c ][ numLutPoints ] is set equal to tmpPivotPt[ numLutPoints − 1 ]. For j=0..( numLutPoints − 1 ), the value of ccSlope[ c ][ j ] is set equal to ( ccPivotPointY[ c ][ j + 1 ] − ccPivotPointY[ c ][ j ] ). For c=0..maxIntraComp, the intra-component remapping process of the input samples picture rec[ c ] into the remapped samples picture map[ c ] is performed as follows. for i=0..picWidth[ c ] − 1, j=0..picHeight[ c ] − 1, the following applies: idx = rec[ c ][ i ][ j ] >> log2distX map[ c ][ i ][ j ] = Clip3( 0, ( 1 << bitDepth ) − 1, pivotPointY[ c ][ idx ] + ( ( slope[ c ][ idx ] * ( rec[ i ][ j ] − pivotPointX[ idx ] ) + ( 1 << 10 ) ) >> 11 ) ) When colour_transform_cross_component_flag is equal to 1, for c=1..2, the cross-component remapping process of the input samples picture rec[ c ] into the remapped samples picture map[ c ] is performed as follows: — offset is set equal to ( 1 << ( bitDepth − 1 ) ). — subWc and subHc are set equal to ( picWidth

[0000] / picWidth[ c ] ) and ( picHeight

[0000] / picHeight[ c ] ), respectively. For i=0..picWidth[ c ] − 1, j=0..picHeight[ c ] − 1, the following applies: coloc = rec

[0000] [ i * SubWc ][ j * SubHc ] idx = coloc >> log2distX scale = ccPivotPointY[ c ][ idx ] + ( ( ccSlope[ c ][ idx ] * ( coloc − pivotPointX[ idx ] ) ) >> log2distX ) map[ c ][ i ][ j ] = Clip3( 0, ( 1 << bitDepth ) − 1, ( ( offset << 11 ) + scale * ( rec[ c ][ i ][ j ] − offset ) + ( 1 << 10 ) ) >> 11 ) 3.4.3. Neural-network post-filter characteristics SEI message 3.4.3.1. Neural-network post-filter characteristics SEI message syntax nn_post_filter_characteristics( payloadSize ) { DescriptorAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) nnpfc_tag_uri st(v) nnpfc_uri st(v)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) nnpfc_out_format_idc ue(v) nnpfc_out_order_idc ue(v)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) nnpfc_cb_padding_val ue(v) nnpfc_cr_padding_val ue(v)3.4.3.2. Neural-network post-filter characteristics SEI message semantics

[0175] The neural-network post-filter characteristics (NNPFC) SEI message specifies a neural network that may be used as a post-processing filter. The use of specified neural-network post-processing filters (NNPFs) for specific pictures is indicated with neural-network post-filter activation (NNPFA) SEI messages.

[0176] Use of this SEI message requires the definition of the following variables: — Input picture width and height in units of luma samples, denoted herein by CroppedWidth and CroppedHeight, respectively. — Luma sample array CroppedYPic[ idx ] and chroma sample arrays CroppedCbPic[ idx ] and CroppedCrPic[ idx ], when present, of the input pictures with index idx in the range of 0 to numInputPics − 1, inclusive, that are used as input for the NNPF.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) — Bit depth BitDepthY for the luma sample array of the input pictures. — Bit depth BitDepthC for the chroma sample arrays, if any, of the input pictures. — A chroma format indicator, denoted herein by ChromaFormatIdc, as described in subclause 7.3. — When nnpfc_auxiliary_inp_idc is equal to 1, a filtering strength control value array StrengthControlVal[ idx ] that shall contain real numbers in the range of 0 to 1, inclusive, of the input pictures with index idx in the range of 0 to numInputPics − 1, inclusive.

[0177] Input picture with index 0 corresponds to the picture for which the NNPF defined by this NNPFC SEI message is activated by an NNPFA SEI message. Input picture with index i in the range of 1 to numInputPics − 1, inclusive, precedes the input picture with index i − 1 in output order.

[0178] The variables SubWidthC and SubHeightC are derived from ChromaFormatIdc as specified by Table 2.

[0179] NOTE 1. More than one NNPFC SEI message can be present for the same picture. When more than one NNPFC SEI message with different values of nnpfc_id is present or activated for the same picture, they can have the same value or different values of nnpfc_purpose and the same value or different values of nnpfc_mode_idc.

[0180] nnpfc_purpose indicates the purpose of the NNPF as specified in Table 20, where ( nnpfc_purpose & bitMask ) not equal to 0 indicates that the NNPF has the purpose associated with the bitMask value in Table 20. When nnpfc_purpose is greater than 0 and ( nnpfc_purpose & bitMask ) is equal to 0, the purpose associated with the bitMask value is not applicable to the NNPF. When nnpfc_pupose is equal to 0, the NNPF may be used as determined by the application.

[0181] All NNPFC SEI messages with a particular value of nnpfc_id within a CLVS shall have the same value of nnpfc_purpose.

[0182] The value of nnpfc_purpose shall be in the range of 0 to 63, inclusive, in bitstreams conforming to this edition of this document. Values of 64 to 65535, inclusive, for nnpfc_purpose are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_purpose in the range of 64 to 65535, inclusive. Table 20 — Definition of nnpfc_purpose bitMask Interpretation orAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0183] The variables ChromaUpsamplingFlag, ResolutionResamplingFlag, PictureRateUpsamplingFlag, BitDepthUpsamplingFlag, and ColourizationFlag, specifying whether nnpfc_purpose indicates the purpose of the NNPF to include chroma upsampling, resolution resampling, picture rate upsampling, bit depth upsampling, and colorization, respectively, are derived as follows: ChromaUpsamplingFlag = ( ( nnpfc_purpose & 0x02 ) > 0 ) ? 1 : 0 ResolutionResamplingFlag = ( ( nnpfc_purpose & 0x04 ) > 0 ) ? 1 : 0 PictureRateUpsamplingFlag = ( ( nnpfc_purpose & 0x08 ) > 0 ) ? 1 : 0 (75) BitDepthUpsamplingFlag = ( ( nnpfc_purpose & 0x10 ) > 0 ) ? 1 : 0 ColourizationFlag = ( ( nnpfc_purpose & 0x20 ) > 0 ) ? 1 : 0

[0184] NOTE 2. When a reserved value of nnpfc_purpose is taken into use in the future by ITU-T | ISO / IEC, the syntax of this SEI message could be extended with syntax elements whose presence is conditioned by nnpfc_purpose being equal to that value or any one of a set of values including that value.

[0185] When ChromaFormatIdc is equal to 3, ChromaUpsamplingFlag shall be equal to 0.

[0186] When ChromaUpsamplingFlag is equal to 1, ColourizationFlag shall be equal to 0.

[0187] When PictureRateUpsamplingFlag is equal to 1 and the input picture with index 0 is associated with a frame packing arrangement SEI message with fp_arrangement_type equal to 5, all input pictures are associated with a frame packing arrangement SEI message with fp_arrangement_type equal to 5 and the same value of fp_current_frame_is_frame0_flag.

[0188] nnpfc_id contains an identifying number that may be used to identify an NNPF. The value of nnpfc_id shall be in the range of 0 to 232 − 2, inclusive. Values of nnpfc_id from 256 to 511, inclusive, and from 231 to 232 − 2, inclusive, are reserved for future use by ITU-T | ISO / IEC. Decoders conforming to this edition of this document encountering an NNPFC SEI message with nnpfc_id in the range of 256 to 511, inclusive, or in the range of 231 to 232 − 2, inclusive, shall ignore the SEI message.

[0189] When an NNPFC SEI message is the first NNPFC SEI message, in decoding order, that has a particular nnpfc_id value within the current CLVS, the following applies: — This SEI message specifies a base NNPF. — This SEI message pertains to the current decoded picture and all subsequent decoded pictures of the current layer, in output order, until the end of the current CLVS.

[0190] nnpfc_base_flag equal to 1 specifies that the SEI message specifies the base NNPF. nnpfc_base_flag equal to 0 specifies that the SEI message specifies an update relative to the base NNPF.

[0191] The following constraints apply to the value of nnpfc_base_flag: — When an NNPFC SEI message is the first NNPFC SEI message, in decoding order, that has a particular nnpfc_id value within the current CLVS, the value of nnpfc_base_flag shall be equal to 1. — All NNPFC SEI messages in a CLVS that have a particular nnpfc_id value and nnpfc_base_flag equal to 1 shall have identical SEI payload content.

[0192] When nnpfc_base_flag is equal to 0, the following applies:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) — This SEI message defines an update relative to the preceding base NNPF in decoding order with the same nnpfc_id value. Updates are not cumulative but rather each update is applied on the base NNPF, which is the NNPF specified by the first NNPFC SEI message, in decoding order, that has a particular nnpfc_id value within the current CLVS. The NNPF defined by this SEI message is obtained by applying the update defined by this SEI message relative to the base NNPF with the same nnpfc_id value. — This SEI message pertains to the current decoded picture and all subsequent decoded pictures of the current layer, in output order, until the end of the current CLVS or up to but excluding the decoded picture that follows the current decoded picture in output order within the current CLVS and is associated with a subsequent NNPFC SEI message, in decoding order, having nnpfc_base_flag equal to 0 and that particular nnpfc_id value within the current CLVS, whichever is earlier.

[0193] nnpfc_mode_idc, when equal to 0, indicates that the neural network information is contained in the NNPFC SEI message, and the neural network information is in the format of an ISO / IEC 15938-17 bitstream. nnpfc_mode_idc equal to 1 indicates that the neural network information is identified by the URI indicated by nnpfc_uri with the format identified by the tag URI nnpfc_tag_uri.

[0194] The value of nnpfc_mode_idc shall be in the range of 0 to 255, inclusive. Values of 2 to 255, inclusive, for nnpfc_mode_idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_mode_idc in the range of 2 to 255, inclusive.

[0195] nnpfc_alignment_zero_bit_a shall be equal to 0.

[0196] nnpfc_tag_uri contains a tag URI with syntax and semantics as specified in IETF RFC 4151 identifying the format and associated information about the neural network used as a base NNPF or an update relative to the base NNPF with the same nnpfc_id value specified by nnpfc_uri.

[0197] NOTE 3. nnpfc_tag_uri enables uniquely identifying the format of neural network data specified by nnrpf_uri without needing a central registration authority.

[0198] nnpfc_tag_uri equal to "tag:iso.org,2023:15938-17" indicates that the neural network data identified by nnpfc_uri conforms to ISO / IEC 15938-17.

[0199] nnpfc_uri contains a URI with syntax and semantics as specified in IETF Internet Standard 66 identifying the neural network used as a base NNPF or an update relative to the base NNPF with the same nnpfc_id value.

[0200] nnpfc_property_present_flag equal to 1 specifies that syntax elements related to the filter properties including purpose, input formatting, output formatting, and complexity are present. nnpfc_property_present_flag equal to 0 specifies that no syntax elements related to the filter properties are present.

[0201] When nnpfc_base_flag is equal to 1, nnpfc_property_present_flag shall be equal to 1.

[0202] When nnpfc_property_present_flag is equal to 0, the values of all syntax elements that may be present only when nnpfc_property_present_flag is equal to 1 are inferred to be equal to their corresponding syntax elements, respectively, in the NNPFC SEI message that contains the base NNPF for which this SEI message provides an update.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0203] When an NNPFC SEI message nnpfcCurr is not the first NNPFC SEI message, in decoding order, that has a particular nnpfc_id value within the current CLVS, is not a repetition of the first NNPFC SEI message with that particular nnpfc_id value (in this case the value of nnpfc_base_flag is equal to 0), and the value of nnpfc_property_present_flag is equal to 1, the following constraints apply: — The values of syntax elements following nnpfc_property_present_flag and preceding nnpfc_complexity_info_present_flag, in decoding order, in the NNPFC SEI message shall be the same as the values of corresponding syntax elements in the first NNPFC SEI message, in decoding order, that has that particular nnpfc_id value within the current CLVS. — Either nnpfc_complexity_info_present_flag shall be equal to 0 or both nnpfc_complexity_info_present_flag shall be equal to 1 in the first NNPFC SEI message, in decoding order, that has that particular nnpfc_id value within the current CLVS (denoted as nnpfcBase below) and all the following constraints apply: — nnpfc_parameter_type_idc in nnpfcCurr shall be equal to nnpfc_parameter_type_idc in nnpfcBase. — nnpfc_log2_parameter_bit_length_minus3 in nnpfcCurr, when present, shall be less than or equal to nnpfc_log2_parameter_bit_length_minus3 in nnpfcBase. — If nnpfc_num_parameters_idc in nnpfcBase is equal to 0, nnpfc_num_parameters_idc in nnpfcCurr shall be equal to 0. — Otherwise (nnpfc_num_parameters_idc in nnpfcBase is greater than 0), nnpfc_num_parameters_idc in nnpfcCurr shall be greater than 0 and less than or equal to nnpfc_num_parameters_idc in nnpfcBase. — If nnpfc_num_kmac_operations_idc in nnpfcBase is equal to 0, nnpfc_num_kmac_operations_idc in nnpfcCurr shall be equal to 0. — Otherwise (nnpfc_num_kmac_operations_idc in nnpfcBase is greater than 0), nnpfc_num_kmac_operations_idc in nnpfcCurr shall be greater than 0 and less than or equal to nnpfc_num_kmac_operations_idc in nnpfcBase. — If nnpfc_total_kilobyte_size in nnpfcBase is equal to 0, nnpfc_total_kilobyte_size in nnpfcCurr shall be equal to 0. — Otherwise (nnpfc_total_kilobyte_size in nnpfcBase is greater than 0), nnpfc_total_kilobyte_size in nnpfcCurr shall be greater than 0 and less than or equal to nnpfc_total_kilobyte_size in nnpfcBase.

[0204] nnpfc_num_input_pics_minus1 plus 1 specifies the number of pictures used as input for the NNPF. The value of nnpfc_num_input_pics_minus1 shall be in the range of 0 to 63, inclusive. When PictureRateUpsamplingFlag is equal to 1, the value of nnpfc_num_input_pics_minus1 shall be greater than 0.

[0205] The variable numInputPics, specifying the number of pictures used as input for the NNPF, is derived as follows: numInputPics = nnpfc_num_input_pics_minus1 + 1 (76)

[0206] nnpfc_input_pic_filtering_flag[ i ] equal to 1 indicates that for the i-th input picture the NNPF generates a corresponding output picture. nnpfc_input_pic_filtering_flag[ i ] equal to 0 indicates that for the i-th input picture the NNPF does not generate a corresponding output picture. Each NNPF-generated picture is stored in the output tensorAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) of the NNPF. When nnpfc_num_input_pics_minus1 is equal to 0, nnpfc_input_pic_filtering_flag

[0000] is inferred to be equal to 1. When PictureRateUpsamplingFlag is equal to 0 and nnpfc_num_input_pics_minus1 is greater than 0, nnpfc_input_pic_filtering_flag[ i ] shall be equal to 1 for at least one value of i in the range of 0 to nnpfc_num_input_pics_minus1, inclusive.

[0207] nnpfc_absent_input_pic_zero_flag equal to 1 indicates that the NNPF expects an input picture that is not present in the bitstream to be represented by sample arrays with sample values equal to 0. nnpfc_absent_input_pic_zero_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the bitstream to be represented by the input picture inputPicB that is the closest to inputPicA in output order and is present in the bitstream.

[0208] nnpfc_out_sub_c_flag specifies the values of the variables outSubWidthC and outSubHeightC when ChromaUpsamplingFlag is equal to 1. nnpfc_out_sub_c_flag equal to 1 specifies that outSubWidthC is equal to 1 and outSubHeightC is equal to 1. nnpfc_out_sub_c_flag equal to 0 specifies that outSubWidthC is equal to 2 and outSubHeightC is equal to 1. When ChromaFormatIdc is equal to 2 and nnpfc_out_sub_c_flag is present, the value of nnpfc_out_sub_c_flag shall be equal to 1.

[0209] nnpfc_out_colour_format_idc, when ColourizationFlag is equal to 1, specifies the colour format of the NNPF-generated pictures and consequently the values of the variables outSubWidthC and outSubHeightC. nnpfc_out_colour_format_idc equal to 1 specifies that the colour format of the NNPF-generated pictures is the 4:2:0 format and outSubWidthC and outSubHeightC are both equal to 2. nnpfc_out_colour_format_idc equal to 2 specifies that the colour format of the NNPF-generated pictures is the 4:2:2 format and outSubWidthC is equal to 2 and outSubHeightC is equal to 1. nnpfc_out_colour_format_idc equal to 3 specifies that the colour format of the NNPF- generated pictures is the 4:4:4 format and outSubWidthC and outSubHeightC are both equal to 1. The value of nnpfc_out_colour_format_idc shall not be equal to 0.

[0210] When ChromaUpsamplingFlag and ColourizationFlag are both equal to 0, outSubWidthC and outSubHeightC are inferred to be equal to SubWidthC and SubHeightC, respectively.

[0211] nnpfc_pic_width_num_minus1 plus 1 and nnpfc_pic_width_denom_minus1 plus 1 specify the numerator and denominator, respectively, for the resampling ratio of the width of the NNPF-generated pictures relative to CroppedWidth. Both nnpfc_pic_width_num_minus1 and nnpfc_pic_width_denom_minus1 shall be in the range of 0 to 65535, inclusive.

[0212] The value of ( nnpfc_pic_width_num_minus1 + 1 ) ÷ ( nnpfc_pic_width_denom_minus1 + 1 ) shall be in the range of 1 ÷ 16 to 16, inclusive. When nnpfc_pic_width_num_minus1 and nnpfc_pic_width_denom_minus1 are not present, the values of nnpfc_pic_width_num_minus1 and nnpfc_pic_width_denom_minus1 are both inferred to be equal to 0.

[0213] The variable nnpfcOutputPicWidth, representing the width of the luma sample arrays of the NNPF- generated pictures, is derived as follows: nnpfcOutputPicWidth = Ceil( CroppedWidth * (77) ( nnpfc_pic_width_num_minus1 + 1 ) ÷ ( nnpfc_pic_width_denom_minus1 + 1 ) )Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0214] It is a requirement of bitstream conformance that the value of nnpfcOutputPicWidth % outSubWidthC shall be equal to 0.

[0215] nnpfc_pic_height_num_minus1 plus 1 and nnpfc_pic_height_denom_minus1 plus 1 specify the numerator and denominator, respectively, for the resampling ratio of the height of the NNPF-generated pictures relative to CroppedHeight. Both nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denom_minus1 shall be in the range of 0 to 65535, inclusive.

[0216] The value of ( nnpfc_pic_height_num_minus1 + 1 ) ÷ ( nnpfc_pic_height_denom_minus1 + 1 ) shall be in the range of 1 ÷ 16 to 16, inclusive. When nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denom_minus1 are not present, the values of nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denom_minus1 are both inferred to be equal to 0.

[0217] The variable nnpfcOutputPicHeight, representing the height of the luma sample arrays of the NNPF- generated pictures, is derived as follows: nnpfcOutputPicHeight = Ceil( CroppedHeight *(78) ( nnpfc_pic_height_num_minus1 + 1 ) ÷ ( nnpfc_pic_height_denom_minus1 + 1 ) )

[0218] It is a requirement of bitstream conformance that the value of nnpfcOutputPicHeight % outSubHeightC shall be equal to 0.

[0219] When ResolutionResamplingFlag is equal to 1, at least one the following conditions shall be true: — The value of nnpfcOutputPicWidth is not equal to CroppedWidth. — The value of nnpfcOutputPicHeight is not equal to CroppedHeight.

[0220] nnpfc_interpolated_pics[ i ] specifies the number of interpolated pictures generated by the NNPF between the i-th and the ( i + 1 )-th input picture for the NNPF. The value of nnpfc_interpolated_pics[ i ] shall be in the range of 0 to 63, inclusive. When the nnpfc_interpolated_pics[ i ] syntax elements are present, the value of nnpfc_interpolated_pics[ i ] shall be greater than 0 for at least one value of i in the range of 0 to nnpfc_num_input_pics_minus1 − 1, inclusive.

[0221] NOTE 4. When PictureRateUpsamplingFlag is equal to 1 for an NNPF and the NNPFA SEI message that activated this NNPF has nnpfa_persistence_flag equal to 1, only for a single value of i in the range of 0 to numInputPics − 1, inclusive, the value of nnpfc_interpolated_pics[ i ] is greater than 0.

[0222] The variables NumInpPicsInOutputTensor, specifying the number of pictures that have a corresponding input picture and are present in the output tensor of the NNPF, InpIdx[ idx ], specifying the input picture index, to the list of input pictures in reverse output order, of the idx-th picture that is present in the output tensor of the NNPF and has a corresponding input picture, and numPicsInOutputTensor, specifying the total number of pictures present in the output tensor of the NNPF, are derived as follows: for( i = 0, numPicsInOutputTensor = 0; i < numInputPics; i++ ) if( nnpfc_input_pic_filtering_flag[ i ] ) { InpIdx[ numPicsInOutputTensor ] = i numPicsInOutputTensor++Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) } (79) NumInpPicsInOutputTensor = numPicsInOutputTensor if( PictureRateUpsamplingFlag ) for( i = 0; i <= numInputPics − 2; i++ ) numPicsInOutputTensor += nnpfc_interpolated_pics[ i ]

[0223] nnpfc_component_last_flag equal to 1 indicates that the last dimension in the input tensor inputTensor to the NNPF and the output tensor outputTensor of the NNPF is used for a current channel. nnpfc_component_last_flag equal to 0 indicates that the third dimension in the input tensor inputTensor to the NNPF and the output tensor outputTensor of the NNPF is used for a current channel.

[0224] NOTE 5. The first dimension in the input tensor and in the output tensor is used for the batch index, which is a common practice in some neural network frameworks. While the formulae in the semantics of this SEI message use the batch size corresponding to the batch index equal to 0, it is up to the post-processing implementation to determine the batch size used as the input to the neural network inference process.

[0225] NOTE 6. For example, when nnpfc_inp_order_idc is equal to 3 and nnpfc_auxiliary_inp_idc is equal to 1, there are 7 channels in the input tensor, including four luma matrices, two chroma matrices, and one auxiliary input matrix. In this case, the process DeriveInputTensors( ) would derive each of these 7 channels of the input tensor one by one, and when a particular channel of these channels is processed, that channel is referred to as the current channel during the process.

[0226] nnpfc_inp_format_idc indicates the method of converting a sample value of the input picture to an input value to the NNPF. The value of nnpfc_inp_format_idc shall be in the range of 0 to 255, inclusive. Values of nnpfc_inp_format_idc in the range of 2 to 255, inclusive, are reserved for future specification by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_inp_format_idc in the range of 2 to 255, inclusive.

[0227] When nnpfc_inp_format_idc is equal to 0, the input values to the NNPF are real numbers and the functions InpY( ) and InpC( ) are specified as follows: InpY( x ) = x ÷ ( ( 1 << BitDepthY) − 1 ) (80)BitDepthC) − 1 ) (81)

[0228] is equal to 1, the input values to the NNPF are unsigned integer numbers and the functions InpY( ) and InpC( ) are specified as follows: shiftY = BitDepthY− inpTensorBitDepthYif( inpTensorBitDepthY>= BitDepthY) InpY( x ) = x << ( inpTensorBitDepthY− BitDepthY) (82) else InpY( x ) = Clip3(0, ( 1 << inpTensorBitDepthY ) − 1, ( x + ( 1 << ( shiftY − 1 ) ) ) >> shiftY )Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) shiftC = BitDepthC − inpTensorBitDepthC if( inpTensorBitDepthC >= BitDepthC ) InpC( x ) = x << ( inpTensorBitDepthC − BitDepthC ) (83) else InpC( x ) = Clip3(0, ( 1 << inpTensorBitDepthC) − 1, ( x + ( 1 << ( shiftC − 1 ) ) ) >> shiftC )

[0229] The variable inpTensorBitDepthY is derived from the syntax element nnpfc_inp_tensor_luma_bitdepth_minus8 as specified below. The variable inpTensorBitDepthC is derived from the syntax element nnpfc_inp_tensor_chroma_bitdepth_minus8 as specified below.

[0230] nnpfc_auxiliary_inp_idc greater than 0 indicates that auxiliary input data is present in the input tensor of the NNPF. nnpfc_auxiliary_inp_idc equal to 0 indicates that auxiliary input data is not present in the input tensor. nnpfc_auxiliary_inp_idc equal to 1 specifies that auxiliary input data is derived as specified in Formula 95.

[0231] The value of nnpfc_auxiliary_inp_idc shall be in the range of 0 to 255, inclusive. Values of 2 to 255, inclusive, for nnpfc_auxiliary_inp_idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_auxiliary_inp_idc in the range of 2 to 255, inclusive.

[0232] nnpfc_inp_order_idc indicates the method of ordering the sample arrays of an input picture to form an input tensor to the NNPF.

[0233] The value of nnpfc_inp_order_idc shall be in the range of 0 to 255, inclusive. Values of 4 to 255, inclusive, for nnpfc_inp_order_idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_inp_order_idc in the range of 4 to 255, inclusive.

[0234] When ChromaFormatIdc is not equal to 1, nnpfc_inp_order_idc shall not be equal to 3.

[0235] When ChromaFormatIdc is equal to 0, nnpfc_inp_order_idc shall be equal to 0.

[0236] When ChromaUpsamplingFlag is equal to 1, nnpfc_inp_order_idc shall not be equal to 0.

[0237] Table 21 contains an informative description of nnpfc_inp_order_idc values. Table 21 — Description of nnpfc_inp_order_idc values nnpfc_inp_ Description or en re or, woAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) chroma matrices and one auxiliary input matrix are present, and the number of channels is 3. in dc re re en ne he is [02. g g p ) when nnpfc_inp_order_idc is equal to 3.

[0239] nnpfc_inp_tensor_luma_bitdepth_minus8 plus 8 specifies the bit depth of luma sample values in the input integer tensor. The value of inpTensorBitDepthY is derived as follows: inpTensorBitDepthY = nnpfc_inp_tensor_luma_bitdepth_minus8 + 8 (84)

[0240] It is a requirement of bitstream conformance that the value of nnpfc_inp_tensor_luma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive.

[0241] nnpfc_inp_tensor_chroma_bitdepth_minus8 plus 8 specifies the bit depth of chroma sample values in the input integer tensor. The value of inpTensorBitDepthC is derived as follows: inpTensorBitDepthC= nnpfc_inp_tensor_chroma_bitdepth_minus8 + 8 (85)

[0242] It is a requirement of bitstream conformance that the value of nnpfc_inp_tensor_chroma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive.

[0243] nnpfc_out_format_idc equal to 0 indicates that the sample values output by the NNPF are real numbers where the value range of 0 to 1, inclusive, maps linearly to the unsigned integer value range of 0 to ( 1 << bitDepth ) − 1, inclusive, for any desired bit depth bitDepth for subsequent post-processing or displaying.

[0244] nnpfc_out_format_idc equal to 1 indicates that the luma sample values output by the NNPF are unsigned integer numbers in the range of 0 to ( 1 << outTensorBitDepthY ) − 1, inclusive, and the chroma sample values output by the NNPF are unsigned integer numbers in the range of 0 to ( 1 << outTensorBitDepthC ) − 1, inclusive.

[0245] The value of nnpfc_out_format_idc shall be in the range of 0 to 255, inclusive. Values of 2 to 255, inclusive, for nnpfc_out_format_idc are reserved for future specification by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_out_format_idc in the range of 2 to 255, inclusive.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0246] nnpfc_out_order_idc indicates the output order of samples resulting from the NNPF.

[0247] The value of nnpfc_out_order_idc shall be in the range of 0 to 255, inclusive. Values of 4 to 255, inclusive, for nnpfc_out_order_idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_out_order_idc in the range of 4 to 255, inclusive.

[0248] When ChromaUpsamplingFlag is equal to 1, nnpfc_out_order_idc shall not be equal to 0 or 3.

[0249] When ColourizationFlag is equal to 1, nnpfc_out_order_idc shall not be equal to 0.

[0250] Table 22 contains an informative description of nnpfc_out_order_idc values. Table 22 — Description of nnpfc_out_order_idc values nnpfc_out_ Description order idc 3. of :0. [0] nnp c_out_tensor_ uma_btdept _mnus8 pus 8 spec es t e b t dept o uma sampe va ues n the output integer tensor. The value of nnpfc_out_tensor_luma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive. The value of outTensorBitDepthY is derived as follows: outTensorBitDepthY = nnpfc_out_tensor_luma_bitdepth_minus8 + 8 (86)

[0252] nnpfc_out_tensor_chroma_bitdepth_minus8 plus 8 specifies the bit depth of chroma sample values in the output integer tensor. The value of nnpfc_out_tensor_chroma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive. The value of outTensorBitDepthC is derived as follows: outTensorBitDepthC = nnpfc_out_tensor_chroma_bitdepth_minus8 + 8 (87)

[0253] When BitDepthUpsamplingFlag is equal to 1, the value of nnpfc_out_format_idc shall be equal to 1 and at least one of the following conditions shall be true: — nnpfc_out_tensor_luma_bitdepth_minus8 is present and outTensorBitDepthY is greater than BitDepthY. — nnpfc_out_tensor_chroma_bitdepth_minus8 is present and outTensorBitDepthC is greater than BitDepthC.

[0254] When nnpfc_inp_tensor_luma_bitdepth_minus8, nnpfc_inp_tensor_chroma_bitdepth_minus8, nnpfc_out_tensor_luma_bitdepth_minus8, and nnpfc_out_tensor_chroma_bitdepth_minus8 are present and outTensorBitDepthY is greater than inpTensorBitDepthY, outTensorBitDepthC shall not be less than inpTensorBitDepthC. When nnpfc_inp_tensor_luma_bitdepth_minus8, nnpfc_inp_tensor_chroma_bitdepth_minus8, nnpfc_out_tensor_luma_bitdepth_minus8, and nnpfc_out_tensor_chroma_bitdepth_minus8 are present andAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) outTensorBitDepthC is greater than inpTensorBitDepthC, outTensorBitDepthY shall not be less than inpTensorBitDepthY.

[0255] nnpfc_separate_colour_description_present_flag equal to 1 indicates that a distinct combination of colour primaries, transfer characteristics, matrix coefficients, and scaling and offset values applied in association with the matrix coefficients for the picture resulting from the NNPF is specified in the SEI message syntax structure. nnpfc_separate_colour_description_present_flag equal to 0 indicates that the combination of colour primaries, transfer characteristics, matrix coefficients, and scaling and offset values applied in association with the matrix coefficients for the picture resulting from the NNPF is the same as implied by the VUI parameters vui_colour_primaries, vui_tranfer_characteristics, vui_matrix_coeffs, and vui_full_range_flag that are indicated or inferred for the CLVS.

[0256] nnpfc_colour_primaries has the same semantics as specified in subclause 7.3 for the vui_colour_primaries syntax element, except as follows: — nnpfc_colour_primaries specifies the colour primaries of the picture resulting from applying the NNPF specified in the SEI message, rather than the colour primaries used for the CLVS. — When nnpfc_colour_primaries is not present in the NNPFC SEI message, the value of nnpfc_colour_primaries is inferred to be equal to vui_colour_primaries.

[0257] nnpfc_transfer_characteristics has the same semantics as specified in subclause 7.3 for the vui_transfer_characteristics syntax element, except as follows: — nnpfc_transfer_characteristics specifies the transfer characteristics of the picture resulting from applying the NNPF specified in the SEI message, rather than the transfer characteristics used for the CLVS. — When nnpfc_transfer_characteristics is not present in the NNPFC SEI message, the value of nnpfc_transfer_characteristics is inferred to be equal to vui_transfer_characteristics.

[0258] nnpfc_matrix_coeffs describes the equations used in deriving luma and chroma signals from the green, blue, and red, or Y, Z, and X primaries. Its semantics apply to the pictures resulting from applying the NNPF specified in this SEI message and are as specified for MatrixCoefficients in Rec. ITU-T H.273 | ISO / IEC 23091-2 with BitDepthY and BitDepthC being equal to outTensorBitDepthY and outTensorBitDepthC, respectively.

[0259] When nnpfc_matrix_coeffs is not present in the NNPFC SEI message, the value of nnpfc_matrix_coeffs is inferred to be equal to vui_matrix_coeffs.

[0260] nnpfc_matrix_coeffs shall not be equal to 0 unless both of the following conditions are true: — nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8. — nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0261] nnpfc_matrix_coeffs shall not be equal to 8 unless one of the following conditions is true: — nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8. — nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8 + 1, nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0262] nnpfc_full_range_flag indicates the scaling and offset values applied in association with the matrix coefficients as specified by nnpfc_matrix_coeffs. Its semantics are as specified for the VideoFullRangeFlag parameterAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) in Rec. ITU-T H.273 | ISO / IEC 23091-2. When not present, the value of nnpfc_full_range_flag is inferred to be equal to 0.

[0263] nnpfc_chroma_loc_info_present_flag equal to 1 indicates the presence of the nnpfc_chroma_sample_loc_type_frame syntax element in the NNPFC SEI message. nnpfc_chroma_loc_info_present_flag equal to 0 indicates the absence of the nnpfc_chroma_sample_loc_type_frame syntax element in the NNPFC SEI message. When nnpfc_chroma_loc_info_present_flag is not present, its value is inferred to be equal to 0. When ColourizationFlag is equal to 0 or nnpfc_out_colour_format_idc is not equal to 1, the value of nnpfc_chroma_loc_info_present_flag shall be equal to 0.

[0264] nnpfc_chroma_sample_loc_type_frame, when not equal to 6 and nnpfc_out_colour_format_idc is equal to 1, specifies the location of chroma samples of the output pictures, as shown in FIG. 1. nnpfc_chroma_sample_loc_type_frame equal to 6 and nnpfc_out_colour_format_idc equal to 1 indicates that the location of the chroma samples is unknown or unspecified or specified by other means not specified in this document. The value of nnpfc_chroma_sample_loc_type_frame shall be in the range of 0 to 6, inclusive.

[0265] nnpfc_overlap indicates the overlapping horizontal and vertical sample counts of adjacent input tensors of the NNPF. The value of nnpfc_overlap shall be in the range of 0 to 16383, inclusive.

[0266] nnpfc_constant_patch_size_flag equal to 1 indicates that the NNPF accepts exactly the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1 as input. nnpfc_constant_patch_size_flag equal to 0 indicates that the NNPF accepts as input any patch size with width inpPatchWidth and height inpPatchHeight such that the width of an extended patch (i.e., a patch plus the overlapping area), which is equal to inpPatchWidth + 2 * nnpfc_overlap, is a positive integer multiple of nnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap, and the height of the extended patch, which is equal to inpPatchHeight + 2 * nnpfc_overlap, is a positive integer multiple of nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap.

[0267] nnpfc_patch_width_minus1 plus 1, when nnpfc_constant_patch_size_flag equal to 1, indicates the horizontal sample counts of the patch size required for the input to the NNPF. The value of nnpfc_patch_width_minus1 shall be in the range of 0 to Min( 32766, CroppedWidth − 1 ), inclusive.

[0268] nnpfc_patch_height_minus1 plus 1, when nnpfc_constant_patch_size_flag equal to 1, indicates the vertical sample counts of the patch size required for the input to the NNPF. The value of nnpfc_patch_height_minus1 shall be in the range of 0 to Min( 32766, CroppedHeight − 1 ), inclusive.

[0269] nnpfc_extended_patch_width_cd_delta_minus1 plus 1 plus 2 * nnpfc_overlap, when nnpfc_constant_patch_size_flag equal to 0, indicates a common divisor of all allowed values of the width of an extended patch required for the input to the NNPF. The value of nnpfc_extended_patch_width_cd_delta_minus1 shall be in the range of 0 to Min( 32766, CroppedWidth − 1 ), inclusive.

[0270] nnpfc_extended_patch_height_cd_delta_minus1 plus 1 plus 2 * nnpfc_overlap, when nnpfc_constant_patch_size_flag equal to 0, indicates a common divisor of all allowed values of the height of anAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) extended patch required for the input to the NNPF. The value of nnpfc_extended_patch_height_cd_delta_minus1 shall be in the range of 0 to Min( 32766, CroppedHeight − 1 ), inclusive.

[0271] Let the variables inpPatchWidth and inpPatchHeight be the patch size width and the patch size height, respectively.

[0272] If nnpfc_constant_patch_size_flag is equal to 0, the following applies: — The values of inpPatchWidth and inpPatchHeight are either provided by external means not specified in this document or set by the post-processor itself. — The value of inpPatchWidth + 2 * nnpfc_overlap shall be a positive integer multiple of nnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap and inpPatchWidth shall be less than or equal to CroppedWidth. The value of inpPatchHeight + 2 * nnpfc_overlap shall be a positive integer multiple of nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap and inpPatchHeight shall be less than or equal to CroppedHeight.

[0273] Otherwise (nnpfc_constant_patch_size_flag is equal to 1), the value of inpPatchWidth is set equal to nnpfc_patch_width_minus1 + 1 and the value of inpPatchHeight is set equal to nnpfc_patch_height_minus1 + 1.

[0274] The variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, and outPatchCHeight are derived as follows: outPatchWidth = ( nnpfcOutputPicWidth * inpPatchWidth ) / CroppedWidth (88) outPatchHeight = ( nnpfcOutputPicHeight * inpPatchHeight ) / CroppedHeight (89) horCScaling = SubWidthC / outSubWidthC (90) verCScaling = SubHeightC / outSubHeightC (91) outPatchCWidth = outPatchWidth * horCScaling(92) outPatchCHeight = outPatchHeight * verCScaling (93)

[0275] It is a requirement of bitstream conformance that outPatchWidth * CroppedWidth shall be equal to nnpfcOutputPicWidth * inpPatchWidth and outPatchHeight * CroppedHeight shall be equal to nnpfcOutputPicHeight * inpPatchHeight.

[0276] nnpfc_padding_type indicates the process of padding when referencing sample locations outside the boundaries of the input picture as described in Table 23. The value of nnpfc_padding_type shall be in the range of 0 to 15, inclusive. Values of 5 to 15, inclusive, for nnpfc_padding_type are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_padding_type in the range of 5 to 15, inclusive. Table 23 —Informative description of nnpfc_padding_type values nnpfc_padding_type DescriptionAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 3 Wrap-around padding 4 Fixed padding [_ _ _ _ _ pe is equal to 4. The value of nnpfc_luma_padding_val shall be in the range of 0 to ( 1 << BitDepthY ) − 1, inclusive.

[0278] nnpfc_cb_padding_val indicates the Cb value to be used for padding when nnpfc_padding_type is equal to 4. The value of nnpfc_cb_padding_val shall be in the range of 0 to ( 1 << BitDepthC ) − 1, inclusive.

[0279] nnpfc_cr_padding_val indicates the Cr value to be used for padding when nnpfc_padding_type is equal to 4. The value of nnpfc_cr_padding_val shall be in the range of 0 to ( 1 << BitDepthC ) − 1, inclusive.

[0280] The function InpSampleVal( y, x, picHeight, picWidth, croppedPic, cIdx ) with inputs being a vertical sample location y, a horizontal sample location x, a picture height picHeight, a picture width picWidth, sample array croppedPic, and component index cIdx (equal to 0 for luma, 1 for Cb, and 2 for Cr) returns the value of sampleVal derived as follows:

[0281] NOTE 7. For the inputs to the function InpSampleVal( ), the vertical location is listed before the horizontal location for compatibility with input tensor conventions of some inference engines. if( nnpfc_padding_type = = 0 ) if( y < 0 | | x < 0 | | y >= picHeight | | x >= picWidth ) sampleVal = 0 else sampleVal = croppedPic[ x ][ y ] (94) else if( nnpfc_padding_type = = 1 ) sampleVal = croppedPic[ Clip3( 0, picWidth − 1, x ) ][ Clip3( 0, picHeight − 1, y ) ] else if( nnpfc_padding_type = = 2 ) sampleVal = croppedPic[ Reflect( picWidth − 1, x ) ][ Reflect( picHeight − 1, y ) ] else if( nnpfc_padding_type = = 3 ) { if( y >= 0 && y < picHeight ) sampleVal = croppedPic[ Wrap( picWidth − 1, x ) ][ y ] } else if( nnpfc_padding_type = = 4 ) if( y < 0 | | x < 0 | | y >= picHeight | | x >= picWidth ) sampleVal = ( cIdx = = 0 ? nnpfc_luma_padding_val : ( cIdx = = 1 ? nnpfc_cb_padding_val : nnpfc_cr_padding_val ) ) else sampleVal = croppedPic[ x ][ y ]

[0282] When nnpfc_auxiliary_inp_idc is equal to 1, the variable strengthControlScaledVal is derived as follows:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) for( i = 0; i < numInputPics; i++ ) if( nnpfc_inp_format_idc = = 1 ) (95) if( nnpfc_inp_order_idc = = 0 | | nnpfc_inp_order_idc = = 2 | | nnpfc_inp_order_idc = = 3 ) strengthControlScaledVal[ i ] = Floor ( StrengthControlVal[ i ] * ( ( 1 << inpTensorBitDepthY) − 1 ) ) else if( nnpfc_inp_order_idc = = 1 ) strengthControlScaledVal[ i ] = Floor ( StrengthControlVal[ i ] * ( ( 1 << inpTensorBitDepthC ) − 1 ) ) else strengthControlScaledVal[ i ] = StrengthControlVal[ i ]

[0283] A patch is a rectangular array of samples from a component (e.g., a luma or chroma component) of a picture.

[0284] The process DeriveInputTensors( ), for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and a horizontal sample coordinate cLeft specifying the top-left sample location for the patch of samples included in the input tensor, is specified as follows: for( i = 0; i < numInputPics; i++ ) { if( nnpfc_inp_order_idc = = 0 ) for( yP = −nnpfc_overlap; yP < inpPatchHeight + nnpfc_overlap; yP++) for( xP = −nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { inpVal = InpY( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) yPovlp = yP + nnpfc_overlap xPovlp = xP + nnpfc_overlap if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

[0000] [ yPovlp ][ xPovlp ] = inpVal else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0000] = inpVal if( nnpfc_auxiliary_inp_idc = = 1 ) if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

[0001] [ yPovlp ][ xPovlp ] = strengthControlScaledVal[ i ] else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0001] = strengthControlScaledVal[ i ] } else if( nnpfc_inp_order_idc = = 1 ) (96) for( yP = −nnpfc_overlap; yP < inpPatchHeight + nnpfc_overlap; yP++)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) for( xP = −nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { inpCbVal = InpC( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCbPic[ i ], 1 ) ) inpCrVal = InpC( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCrPic[ i ], 2 ) ) yPovlp = yP + nnpfc_overlap xPovlp = xP + nnpfc_overlap if( !nnpfc_component_last_flag ) { inputTensor

[0000] [ i ]

[0000] [ yPovlp ][ xPovlp ] = inpCbVal inputTensor

[0000] [ i ]

[0001] [ yPovlp ][ xPovlp ] = inpCrVal } else { inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0000] = inpCbVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0001] = inpCrVal } if( nnpfc_auxiliary_inp_idc = = 1 ) if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

[0002] [ yPovlp ][ xPovlp ] = strengthControlScaledVal[ i ] else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0002] = strengthControlScaledVal[ i ] } else if( nnpfc_inp_order_idc = = 2 ) for( yP = −nnpfc_overlap; yP < inpPatchHeight + nnpfc_overlap; yP++) for( xP = −nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { yY = cTop + yP xY = cLeft + xP yC = yY / SubHeightC xC = xY / SubWidthC inpYVal = InpY( InpSampleVal( yY, xY, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) inpCbVal = InpC( InpSampleVal( yC, xC, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCbPic[ i ], 1 ) ) inpCrVal = InpC( InpSampleVal( yC, xC, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCrPic[ i ], 2 ) ) yPovlp = yP + nnpfc_overlap xPovlp = xP + nnpfc_overlap if( !nnpfc_component_last_flag ) {Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) inputTensor

[0000] [ i ]

[0000] [ yPovlp ][ xPovlp ] = inpYVal inputTensor

[0000] [ i ]

[0001] [ yPovlp ][ xPovlp ] = inpCbVal inputTensor

[0000] [ i ]

[0002] [ yPovlp ][ xPovlp ] = inpCrVal } else { inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0000] = inpYVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0001] = inpCbVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0002] = inpCrVal } if( nnpfc_auxiliary_inp_idc = = 1 ) if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

[0003] [ yPovlp ][ xPovlp ] = strengthControlScaledVal[ i ] else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0003] = strengthControlScaledVal[ i ] } else if( nnpfc_inp_order_idc = = 3 ) for( yP = −nnpfc_overlap; yP < inpPatchHeight + nnpfc_overlap; yP++) for( xP = −nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { yTL = cTop + yP * 2 xTL = 2 yBR =1+ yP xC = cLeft / 2 + xP inpTLVal = InpY( InpSampleVal( yTL, xTL, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) inpTRVal = InpY( InpSampleVal( yTL, xBR, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) inpBLVal = InpY( InpSampleVal( yBR, xTL, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) inpBRVal = InpY( InpSampleVal( yBR, xBR, CroppedHeight, CroppedWidth, CroppedYPic[ i ], 0 ) ) inpCbVal = InpC( InpSampleVal( yC, xC, CroppedHeight / 2, CroppedWidth / 2, CroppedCbPic[ i ], 1 ) ) inpCrVal = InpC( InpSampleVal( yC, xC, CroppedHeight / 2, CroppedWidth / 2, CroppedCrPic[ i ], 2 ) ) yPovlp = yP + nnpfc_overlapAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) xPovlp = xP + nnpfc_overlap if( !nnpfc_component_last_flag ) { inputTensor

[0000] [ i ]

[0000] [ yPovlp ][ xPovlp ] = inpTLVal inputTensor

[0000] [ i ]

[0001] [ yPovlp ][ xPovlp ] = inpTRVal inputTensor

[0000] [ i ]

[0002] [ yPovlp ][ xPovlp ] = inpBLVal inputTensor

[0000] [ i ]

[0003] [ yPovlp ][ xPovlp ] = inpBRVal inputTensor

[0000] [ i ]

[0004] [ yPovlp ][ xPovlp ] = inpCbVal inputTensor

[0000] [ i ]

[0005] [ yPovlp ][ xPovlp ] = inpCrVal } else { inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0000] = inpTLVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0001] = inpTRVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0002] = inpBLVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0003] = inpBRVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0004] = inpCbVal inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0005] = inpCrVal } if( nnpfc_auxiliary_inp_idc = = 1 ) if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

[0006] [ yPovlp ][ xPovlp ] = strengthControlScaledVal[ i ] else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ]

[0006] = strengthControlScaledVal[ i ] } }

[0285] The process StoreOutputTensors( ), for deriving sample values in the sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic, for the NNPF-generated pictures, from the output tensor outputTensor for a given vertical sample coordinate cTop and a horizontal sample coordinate cLeft specifying the top-left sample location for the patch of samples included in the input tensor, is specified as follows: for( i = 0; i < numPicsInOutputTensor; i++ ) { if( nnpfc_out_order_idc = = 0 ) for( yP = 0; yP < outPatchHeight; yP++) for( xP = 0; xP < outPatchWidth; xP++ ) { yY = cTop * outPatchHeight / inpPatchHeight + yP xY = cLeft * outPatchWidth / inpPatchWidth + xP if ( yY < nnpfcOutputPicHeight && xY < nnpfcOutputPicWidth ) if( !nnpfc_component_last_flag ) FilteredYPic[ i ][ xY ][yY ] = outputTensor

[0000] [ i ]

[0000] [ yP ][ xP ]Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) else FilteredYPic[ i ][ xY ][ yY ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0000] } else if( nnpfc_out_order_idc = = 1 ) (97) for( yP = 0; yP < outPatchCHeight; yP++) for( xP = 0; xP < outPatchCWidth; xP++ ) { xSrc = cLeft * horCScaling + xP ySrc = cTop * verCScaling + yP if ( ySrc < nnpfcOutputPicHeight / outSubHeightC && xSrc < nnpfcOutputPicWidth / outSubWidthC ) if( !nnpfc_component_last_flag ) { FilteredCbPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ]

[0000] [ yP ][ xP ] FilteredCrPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ]

[0001] [ yP ][ xP ] } else { FilteredCbPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0000] FilteredCrPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0001] } } else if( nnpfc_out_order_idc = = 2 ) for( yP = 0; yP < outPatchHeight; yP++) for( xP = 0; xP < outPatchWidth; xP++ ) { yY = cTop * outPatchHeight / inpPatchHeight + yP xY = cLeft * outPatchWidth / inpPatchWidth + xP yC = yY / outSubHeightC xC = xY / outSubWidthC yPc = ( yP / outSubHeightC ) * outSubHeightC xPc = ( xP / outSubWidthC ) * outSubWidthC if ( yY < nnpfcOutputPicHeight && xY < nnpfcOutputPicWidth ) if( !nnpfc_component_last_flag ) { FilteredYPic[ i ][ xY ][ yY ] = outputTensor

[0000] [ i ]

[0000] [ yP ][ xP ] FilteredCbPic[ i ][ xC ][ yC ] = outputTensor

[0000] [ i ]

[0001] [ yPc ][ xPc ] FilteredCrPic[ i ][ xC ][ yC ] = outputTensor

[0000] [ i ]

[0002] [ yPc ][ xPc ] } else { FilteredYPic[ i ][ xY ][ yY ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0000] FilteredCbPic[ i ][ xC ][ yC ] = outputTensor

[0000] [ i ][ yPc ][ xPc ]

[0001] FilteredCrPic[ i ][ xC ][ yC ] = outputTensor

[0000] [ i ][ yPc ][ xPc ]

[0002] Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) } } else if(= = 3 ) ( yP = 0; yP < outPatchHeight; yP++ ) for( xP = 0; xP < outPatchWidth; xP++ ) { ySrc = cTop / 2 * outPatchHeight / inpPatchHeight + yP xSrc = cLeft / 2 * outPatchWidth / inpPatchWidth + xP if ( ySrc < nnpfcOutputPicHeight / 2 && xSrc < nnpfcOutputPicWidth / 2 ) if( !nnpfc_component_last_flag ) { FilteredYPic[ i ][ xSrc * 2 ][ * 2 ] = outputTensor

[0000] [ i ]

[0000] [ yP ][ xP ] 2 ] = outputTensor

[0000] [ i ]

[0001] [ yP ][ xP ] 1 ] = outputTensor

[0000] [ i ]

[0002] [ yP ][ xP ] 2 + 1 ] = outputTensor

[0000] [ i ]

[0003] [ yP ][ xP ]

[0000] [ i ]

[0004] [ yP ][ xP ]=

[0000] [ i ]

[0005] [ yP ][ xP ] } else { FilteredYPic[ i ][ xSrc * 2 ][ ySrc * 2 ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0000] * * 2 ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0001] 1 ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0002] 2 + 1 ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0003]

[0000] [ i ][ yP ][ xP ]

[0004] FilteredCrPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ][ yP ][ xP ]

[0005] } } }

[0286] An NNPF PostProcessingFilter( ) is the target NNPF as derived in the semantics of the NNPFA SEI message. The following example process may be used, with the NNPF PostProcessingFilter( ), to generate, in a patch- wise manner, the filtered and / or interpolated picture(s), which contain Y, Cb, and Cr sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic, respectively, as indicated by nnpfc_out_order_idc: if( nnpfc_inp_order_idc = = 0 | | nnpfc_inp_order_idc = = 2 ) for( cTop = 0; cTop < CroppedHeight; cTop += inpPatchHeight ) for( cLeft = 0; cLeft < CroppedWidth; cLeft += inpPatchWidth ) { inputTensor = DeriveInputTensors( ) outputTensor = PostProcessingFilter( inputTensor ) StoreOutputTensors( outputTensor )Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) } else if( nnpfc_inp_order_idc = = 1 ) for( cTop = 0; cTop < CroppedHeight / SubHeightC; cTop += inpPatchHeight ) for( cLeft = 0; cLeft < CroppedWidth / SubWidthC; cLeft += inpPatchWidth ) { (98) inputTensor = DeriveInputTensors( ) outputTensor = PostProcessingFilter( inputTensor ) StoreOutputTensors( outputTensor ) } else if( nnpfc_inp_order_idc = = 3 ) for( cTop = 0; cTop < CroppedHeight; cTop += inpPatchHeight * 2 ) for( cLeft = 0; cLeft < CroppedWidth; cLeft += inpPatchWidth * 2 ) { inputTensor = DeriveInutTensors( ) outputTensor = PostProcessingFilter( inputTensor ) StoreOutputTensors( outputTensor ) }

[0287] An NNPF-generated picture with index i contains sample arrays FilteredYPic[ i ], FilteredCbPic[ i ], and FilteredCrPic[ i ], when present, that are derived by Formula 98. An NNPF-generated picture does not include the overlap regions.

[0288] The NNPF process consists of the process defined by Formula 98 followed by outputting NNPF- generated pictures in their increasing index order, where all NNPF-generated pictures that were interpolated by the NNPF are output and those NNPF-generated pictures that correspond to any input pictures to the NNPF are output as specified in the semantics of the NNPFA SEI message.

[0289] nnpfc_complexity_info_present_flag equal to 1 specifies that one or more syntax elements that indicate the complexity of the NNPF associated with the nnpfc_id are present. nnpfc_complexity_info_present_flag equal to 0 specifies that no syntax elements that indicates the complexity of the NNPF associated with the nnpfc_id are present.

[0290] nnpfc_parameter_type_idc equal to 0 indicates that the neural network uses only integer parameters. nnpfc_parameter_type_idc equal to 1 indicates that the neural network may use floating point or integer parameters. nnpfc_parameter_type_idc equal to 2 indicates that the neural network uses only binary parameters. nnpfc_parameter_type_idc equal to 3 is reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_parameter_type_idc equal to 3.

[0291] nnpfc_log2_parameter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters of bit length greater than 8, 16, 32, and 64, respectively. When nnpfc_parameter_type_idc is present and nnpfc_log2_parameter_bit_length_minus3 is not present, the neural network does not use parameters of bit length greater than 1.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0292] nnpfc_num_parameters_idc indicates the maximum number of neural network parameters for the NNPF in units of a power of 2048. nnpfc_num_parameters_idc equal to 0 indicates that the maximum number of neural network parameters is unknown. The value nnpfc_num_parameters_idc shall be in the range of 0 to 52, inclusive. Values of nnpfc_num_parameters_idc greater than 52 are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_num_parameters_idc greater than 52.

[0293] If the value of nnpfc_num_parameters_idc is greater than zero, the variable maxNumParameters is derived as follows: maxNumParameters = ( 2048 << nnpfc_num_parameters_idc ) − 1 (99)

[0294] It is a requirement of bitstream conformance that the number of neural network parameters of the NNPF shall be less than or equal to maxNumParameters.

[0295] nnpfc_num_kmac_operations_idc greater than 0 indicates that the maximum number of multiply- accumulate operations per sample of the NNPF is less than or equal to nnpfc_num_kmac_operations_idc * 1000. nnpfc_num_kmac_operations_idc equal to 0 indicates that the maximum number of multiply-accumulate operations of the network is unknown. The value of nnpfc_num_kmac_operations_idc shall be in the range of 0 to 232 − 2, inclusive.

[0296] nnpfc_total_kilobyte_size greater than 0 indicates a total size in kilobytes required to store the uncompressed parameters for the neural network. The total size in bits is a number equal to or greater than the sum of bits used to store each parameter. nnpfc_total_kilobyte_size is the total size in bits divided by 8000, rounded up. nnpfc_total_kilobyte_size equal to 0 indicates that the total size required to store the parameters for the neural network is unknown. The value of nnpfc_total_kilobyte_size shall be in the range of 0 to 232 − 2, inclusive.

[0297] nnpfc_num_metadata_extension_bits equal to 0 specifies that nnpfc_reserved_metadata_extension is not present. nnpfc_num_metadata_extension_bits greater than 0 specifies the length, in bits, of nnpfc_reserved_metadata_extension.

[0298] The value of nnpfc_num_metadata_extension_bits shall be in the range of 0 to 2048, inclusive. Values in the range of 1 to 2048, inclusive, for nnpfc_num_metadata_extension_bits are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall allow any value of nnpfc_num_metadata_extension_bits in the range of 0 to 2048, inclusive.

[0299] nnpfc_reserved_metadata_extension shall not be present in bitstreams conforming to this edition of this document. However, decoders conforming to this edition of this document shall ignore the presence and value of nnpfc_reserved_metadata_extension. When present, the length, in bits, of nnpfc_reserved_metadata_extension is equal to nnpfc_num_metadata_extension_bits.

[0300] nnpfc_alignment_zero_bit_b shall be equal to 0 in bitstreams conforming to this edition of this document. Decoders shall ignore NNPFC SEI messages in which nnpfc_reserved_zero_bit_b is not equal to 0.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0301] nnpfc_payload_byte[ i ] contains the i-th byte of a bitstream conforming to ISO / IEC 15938-17. The byte sequence nnpfc_payload_byte[ i ] for all present values of i shall be a complete bitstream that conforms to ISO / IEC 15938-17. 3.5 CICP 3rd edition

[0302] In the latest proposed CICP specification [6], i.e., the 3rd edition of CICP, two new code point identifiers, referred to as YCgCo-Re and YCgCo-Ro are added. The corresponding descriptions are as follows: Matrix coefficients

[0303] Type: Unsigned integer, enumeration.

[0304] Range: 0 to 255, inclusive, plus associated flag.

[0305] MatrixCoefficients describes the matrix coefficients used in deriving luma and chroma signals from the green, blue, and red, or X, Y, and Z primaries, as specified in Table 7 and the pseudocode operations specified below.

[0306] A flag, VideoFullRangeFlag, may be supplied with this code point (see below).

[0307] VideoFullRangeFlag specifies the scaling and offset values applied in association with the MatrixCoefficients. When not present or not specified, the value 0 for VideoFullRangeFlag would ordinarily be inferred as the default value for video imagery.

[0308] An 8-bit field should be adequate for representation of the MatrixCoefficients code point.

[0309] Certain values of MatrixCoefficients may be disallowed, depending on the application and the characteristics and format of the signal, e.g., with regard to combinations of the chroma format sampling structure and the values of BitDepthY and BitDepthC.

[0310] The interpretation of MatrixCoefficients is specified by the following pseudocode operations. ER, EG, and EB are defined as "linear-domain" real-valued signals based on the indicated colour primaries (see 8.1) before applying the transfer characteristics (see 8.2).

[0311] For purposes of the YZX representation when MatrixCoefficients is equal to 0, the symbols R, G, and B are substituted for X, Y, and Z, respectively, in the following descriptions of pseudocode operations (11) to (19), (27) to (29), (33) to (35), and (48) to (50).

[0312] Nominal peak white is specified as having ER equal to 1, EG equal to 1, and EB equal to 1.

[0313] Nominal black is specified as having ER equal to 0, EG equal to 0, and EB equal to 0.

[0314] The application of the transfer characteristics function is denoted by ( x )′ for an argument x. — If MatrixCoefficients is not equal to 14 or 15, the signals E′R, E′G, and E′B are determined by application of the transfer characteristics function as per pseudocode operations (11) to (13): E′R = (ER)′ (11) E′G = (EG)′ (12) E′B = (EB)′ (13)

[0315] In this case, the range of E′R, E′G, and E′B is specified as follows:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0316] If TransferCharacteristics is equal to 11 or 12, or TransferCharacteristics is equal to 13 and MatrixCoefficients is not equal to 0, E′R, E′G, and E′B are real numbers with values that have a larger range than the range of 0 to 1, inclusive, and their range is not specified in this document.

[0317] Otherwise, E′R, E′G, and E′B are real numbers in the range of 0 to 1, inclusive.

[0318] Otherwise, E′R, E′G, and E′B are real numbers in the range of 0 to 1, inclusive.

[0319] Otherwise (MatrixCoefficients is equal to 14 or 15), the signals E′L,

[0320] E′M, and E′S are determined by the following ordered steps: a) The "linear-domain" real-valued signals EL, EM, and ES are determined as follows:

[0321] If MatrixCoefficients is equal to 14, pseudocode operations (14) to (16) apply: EL= ( 1688 * ER+ 2146 * EG+ 262 * EB) ÷ 4096 (14) EM= ( 683 * ER+ 2951 * EG+ 462 * EB) ÷ 4096 (15) ES= ( 99 * ER+ 309 * EG+ 3688 * EB) ÷ 4096 (16)

[0322] Otherwise (MatrixCoefficients is equal to 15), pseudocode operations (17) to (19) apply: EL = ( 1747 * ER + 2169 * EG + 180 * EB ) ÷ 4096 (17) EM = ( 673 * ER + 3029 * EG + 394 * EB ) ÷ 4096 (18) ES= ( 50 * ER+ 207 * EG+ 3839 * EB) ÷ 4096 (19) b) The signals E′L, E′M, and E′S are determined by application of the transfer characteristics function as per pseudocode operations (20) to (22): E′L= (EL)′ (20) E′M = (EM)′ (21) E′S = (ES)′ (22)

[0323] When MatrixCoefficients is equal to 0, 8, 16, or 17, the variables BitDepthRGB and MaxValRGB are derived using the following ordered steps: a) The variable BitDepthRGBis derived as follows: - If MatrixCoefficients is equal to 0 or 8, the following applies: BitDepthRGB = BitDepthY (23) - Otherwise, if MatrixCoefficients is equal to 16, the following applies: BitDepthRGB = BitDepthY + 2 (24) - Otherwise (MatrixCoefficients is equal to 17), the following applies: BitDepthRGB= BitDepthY+ 1 (25) b) The variable MaxValRGBis derived as follows: MaxValRGB= ( 1 << BitDepthRGB) − 1 (26)

[0324] The interpretation of MatrixCoefficients is specified as follows.

[0325] If VideoFullRangeFlag is equal to 0, the following applies: If MatrixCoefficients is equal to 0, 8, 16, or 17, pseudocode operations (27) to (29) apply: R = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) * ( 219 * E′R + 16 ) ) (27)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) G = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) * ( 219 * E′G + 16 ) ) (28) B = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) * ( 219 * E′B + 16 ) ) (29)

[0326] Otherwise, if MatrixCoefficients is equal to 1, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, or 15, pseudocode operations (30) to (32) apply: Y = Clip1Y ( Round( ( 1 << (BitDepthY − 8 ) ) * ( 219 * E′Y + 16 ) ) ) (30) Cb = Clip1C ( Round( ( 1 << (BitDepthC − 8 ) ) * ( 224 * E′PB + 128 ) ) ) (31) Cr = Clip1C ( Round( ( 1 << (BitDepthC − 8 ) ) * ( 224 * E′PR + 128 ) ) ) (32)

[0327] Otherwise, if MatrixCoefficients is equal to 2, the interpretation of the MatrixCoefficients code point is unknown or is determined by the application.

[0328] Otherwise (MatrixCoefficients is not equal to 0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, or 17), the interpretation of the MatrixCoefficients code point is reserved for future definition by ITU-T | ISO / IEC.

[0329] Otherwise (VideoFullRangeFlag is equal to 1), the following pseudocode operations apply:

[0330] If MatrixCoefficients is equal to 0, 8, 16, or 17, pseudocode operations (33) to (35) apply: R = Clip3( 0, MaxValRGB, MaxValRGB* E′R) (33) = *to Y = Clip1Y( Round( ( ( 1 << BitDepthY ) − 1 ) * E′Y ) ) (36) Cb = Clip1C( Round( ( ( 1 << BitDepthC) − 1 ) * E′PB+ ( 1 << ( BitDepthC− 1 ) ) ) ) (37) Cr = Clip1C( Round( ( ( 1 << BitDepthC) − 1 ) * E′PR+ ( 1 << ( BitDepthC− 1 ) ) ) ) (38)

[0332] Otherwise, if MatrixCoefficients is equal to 2, the interpretation of the MatrixCoefficients code point is unknown or is determined by the application.

[0333] Otherwise (MatrixCoefficients is not equal to 0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, or 17), the interpretation of the MatrixCoefficients code point is reserved for future definition by ITU-T | ISO / IEC.

[0334] When MatrixCoefficients is equal to 1, 4, 5, 6, 7, 9, 10, 11, 12, or 13, the constants KR and KB are specified as follows:

[0335] If MatrixCoefficients is not equal to 12 or 13, the constants KR and KB are specified in Table 7.

[0336] Otherwise (MatrixCoefficients is equal to 12 or 13), the constants KR and KB are computed using the chromaticity coordinates (xR, yR), (xG, yG), (xB, yB), and (xW, yW) as shown below in Equations 39 and 40. ColourPrimaries code point indicates the chromaticity coordinates for the red, green, blue, and white colour primaries, respectively, as specified by Table 3. In some examples, an 8-bit field may represent the ColourPrimaries code point. Table 3 — Interpretation of colour primaries (ColourPrimaries) value Value Colour primaries Informative remarksAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 1 primary x y Rec. ITU-R BT.709-6 green 0.300 0.600 Rec. ITU-R BT.1361-0 conventional colour gamut m re m for ns ns MAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) white C 0.310 0.316 9 primary x y Rec. ITU-R BT.2020-2 ed^^∗^^^∗^^^*z -y *z ^+y ∗^^ *z -x *z ^+z ∗^^ *y -x *y ^^(39) ^^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^zR = 1 − ( xR + yR ) (41) zG = 1 − ( xG + yG ) (42)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) zB = 1 − ( xB + yB ) (43) zW = 1 − ( xW + yW ) (44)

[0337] The variables E′Y, E′PB, and E′PR (for MatrixCoefficients not equal to 0, 8, 16, or 17) or Y, Cb, and Cr (for MatrixCoefficients equal to 0, 8, 16, or 17) are specified as follows.

[0338] If MatrixCoefficients is not equal to 0, 8, 10, 11, 13, 14, 15, 16, or 17, pseudocode operations (45) to (47) apply: E′Y= KR* E′R+ ( 1− KR− KB) * E′G+ KB* E′B(45) E′PB= 0.5 * ( E′B− E′Y) ÷ ( 1 − KB) (46) E′PR= 0.5 * ( E′R− E′Y) ÷ ( 1 − KR) (47)

[0339] the value 0 associated with nominal black and the value 1 associated withnominal numbers with the value 0 associated with both nominal black and nominal white. When TransferCharacteristics is not equal to 11 or 12, E′Y is a real number with values in the range of 0 to 1, inclusive. When TransferCharacteristics is not equal to 11 or 12, E′PB and E′PR are real numbers with values in the range of −0.5 to 0.5, inclusive. When TransferCharacteristics is equal to 11 (IEC 61966-2-4), or 12 (Rec. ITU-R BT.1361-0 extended colour gamut system), E′Y, E′PB, and E′PR are real numbers with a larger range not specified in this document.

[0340] Otherwise, if MatrixCoefficients is equal to 0, pseudocode operations (48) to (50) apply: Y = Round( G ) (48) Cb = Round( B ) (49) Cr = Round( R ) (50)

[0341] Otherwise, if MatrixCoefficients is equal to 8 and BitDepthC is equal to BitDepthY, pseudocode operations (51) to (53) apply: Y = Round( 0.5 * G + 0.25 * ( R + B ) ) (51) Cb = Round( 0.5 * G − 0.25 * ( R + B ) ) + (1 << ( BitDepthC− 1 ) ) (52) Cr = Round( 0.5 * (R − B ) ) + (1 << ( BitDepthC− 1 ) ) (53)

[0342] For purposes of the YCgCo nomenclature used in Table 7, Cb and Cr of pseudocode operations (52) and (53) may be referred to as Cg and Co, respectively. An appropriate inverse conversion for pseudocode operations (51) to (53) is given in pseudocode operations (54) to (57): t = Y − ( Cb − ( 1 << ( BitDepthC− 1 ) ) ) (54) G = Clip1Y( Y + ( Cb − ( 1 << ( BitDepthC− 1 ) ) ) ) (55) B = Clip1Y( t − ( Cr − ( 1 << ( BitDepthC− 1 ) ) ) ) (56) R = Clip1Y( t + ( Cr − ( 1 << ( BitDepthC− 1 ) ) ) ) (57)

[0343] Otherwise, if MatrixCoefficients is equal to 8, 16, or 17, pseudocode operations (58) to (61) apply: Cr = Round( R ) − Round( B ) + (1 << ( BitDepthC− 1 ) ) (58) t = Round( B ) + ( ( Cr − ( 1 << ( BitDepthC− 1 ) ) ) >> 1 ) (59) Cb = Round( G ) − t + (1 << ( BitDepthC− 1 ) ) (60)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) Y = t + ( ( Cb − ( 1 << ( BitDepthC − 1 ) ) ) >> 1 ) (61)

[0344] For purposes of the YCgCo nomenclature used in Table 7, Cb and Cr of pseudocode operations (60) and (58) may be referred to as Cg and Co, respectively. An appropriate inverse conversion for pseudocode operations (58) to (61) is given in pseudocode operation (62) to (65): t = Y − ( ( Cb − ( 1 << ( BitDepthC − 1 ) ) ) >> 1 ) (62) G = Clip3( 0, MaxValRGB, t + ( Cb − ( 1 << ( BitDepthC − 1 ) ) ) ) (63) B = Clip3( 0, MaxValRGB, t − ( ( Cr − ( 1 << ( BitDepthC − 1 ) ) ) >> 1 ) ) (64) R = Clip3( 0, MaxValRGB, B + ( Cr − ( 1 << ( BitDepthC − 1 ) ) ) ) (65)

[0345] Otherwise, if MatrixCoefficients is equal to 10 or 13, the signal E′Y is determined by application of the transfer characteristics function as given in pseudocode operations (66) and (67), and pseudocode operations (68) to (75) apply for specification of the signals E′PB and E′PR: EY = KR * ER + ( 1 − KR − KB ) * EG + KB * EB (66) E′Y = EY ′ ofthe are the value 0 associated with nominal black and the value 1 associated with nominal white. E′PB = ( E′B − E′Y ) ÷ ( 2 * NB ) for −NB <= E′B − E′Y <= 0 (68) − * −function to expressions involving the constants KB and KR as given in pseudocode operations (72) to (75): NB = ( 1 − KB )′ (72) PB = 1 − ( KB )′ (73) NR = ( 1 − KR )′ (74) PR= 1 − ( KR)′ (75)

[0348] Otherwise, if MatrixCoefficients is equal to 11, pseudocode operations (76) to (78) apply: E′Y = E′G (76) E′PB = ( 0.986566 * E′B − E′Y ) ÷ 2.0 (77) E′PR = ( 0.991902 * E′Y ) ÷ 2.0 (78)

[0349] In this case, for purposes of the Y′D′ZD′X nomenclature used in Table 7, E′PB may be referred to as D′Z and E′PR may be referred to as D′X.

[0350] Otherwise, if MatrixCoefficients is equal to 14, the following applies:

[0351] If TransferCharacteristics is not equal to 18, pseudocode operations (79) to (81) apply: E′Y = 0.5 * ( E′L + E′M ) (79) E′PB = ( 6610 * E′L − 13613 * E′M + 7003 * E′S ) ÷ 4096 (80)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) E′PR = ( 17933 * E′L − 17390 * E′M − 543 * E′S ) ÷ 4096 (81)

[0352] Otherwise, pseudocode operations (82) to (84) apply: E′Y= 0.5 * ( E′L+ E′M) (82) E′PB= ( 3625 * E′L− 7465 * E′M+ 3840 * E′S) ÷ 4096 (83) E′PR = ( 9500 * E′L − 9212 * E′M − 288 * E′S ) ÷ 4096 (84)

[0353] In these cases, for purposes of the ICTCP nomenclature used in Table 7, E′Y, E′PB, and E′PR of pseudocode operations (79), (80), and (81) or pseudocode operations (82), (83), and (84) may be referred to as I, CT, and CP, respectively. Pseudocode operation (79), (80), and (81) were designed specifically for use with TransferCharacteristics equal to 16 (PQ), and pseudocode operations (82), (83), and (84) were designed specifically for use with TransferCharacteristics equal to 18 (HLG).

[0354] Otherwise (MatrixCoefficients is equal to 15), the following applies: E′Y= ( 1638 * E′L+ 1638 * E′M+ 820 * E′S) ÷ 4096 (85) E′PB= ( 18248 * E′L− 19870 * E′M+ 1622 * E′S) ÷ 4096 (86) E′PR= ( 3300 * E′L+ 1463 * E′M− 4763 * E′S) ÷ 4096 (87)

[0355] In this case, for purposes of the IPT nomenclature used in Table 7, E′Y, E′PB, and E′PR of pseudocode operations (85), (86), and (87) may be referred to as I, P, and T, respectively. Table 7 — Interpretation of the matrix coefficients (MatrixCoefficients) value Value Matrix coefficients Informative remarks so onAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 5 KR= 0.299; KB= 0.114 Rec. ITU-R BT.470-6 System B, G (historical) Rec. ITU-R BT.601-7625 is hCAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 15 IPT-C2 SMPTE ST 2128 (2023) See pseudocode operations (85) to (87)as corresponding to MatrixCoefficients equal to 1. Closer study later determined that this representation should correspond to MatrixCoefficients equal to 5 instead (which is functionally the same as the value 6). This document was therefore revised to correct the error. 4. Technical problems solved by disclosed embodiments

[0357] Example designs for MatrixCoefficients and its referencing in various video coding standards have the following problems:

[0358] First, in CICP 3rd edition, two YCgCo variants, i.e., YCgCo-Re and YCgCo-Ro, are added. Some constraints should be specified when referencing them.

[0359] Second, in CICP 3rd edition, YCgCo-R, YCgCo-Re and YCgCo-Ro are specified based on the luma bit depth. However, the formulas are defined based on the chroma bit depth. This may lead to undesired interpretation of those formulas.

[0360] Third, some constraints should be set in related SEI messages when referencing MatrixCoeffcients in CICP to prevent using meaningless values.

[0361] Fourth, for some bit depth values, the behavior is undefined in CICP.

[0362] Fifth, the chroma samples in YCgCo may be out of range in CICP.

[0363] Sixth, some parameter combinations in CICP are unreasonable. 5. A listing of solutions and embodiments

[0364] To solve the above-described problems, methods as summarized below are disclosed. The aspects should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these examples can be applied individually or combined in any manner. 1) To address drawbacks of problem 1, one or more of the following aspects are specified: a. When YCgCo-Re or YCgCo-Ro in CICP is used, it is required that the video or image shall be in the 4:4:4 chroma format. b. When YCgCo-Re in CICP is used, it is required that the chroma bit depth shall be equal to the luma bit depth. i. In addition, when YCgCo-Re in CICP is used, it is required that the bit depth is an even number.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) c. When YCgCo-Ro in CICP is used, it is required that the chroma bit depth shall be equal to the luma bit depth. i. In addition, when YCgCo-Ro in CICP is used, it is required that the bit depth is an odd number. 2) To address drawbacks of problem 2, one or more of the following aspects are specified: a. The bit depth and the maximum sample value in RGB domain may be based on the chroma bit depth for the YCgCo format. i. When YCgCo-R is used, the bit depth in RGB domain is equal to the chroma bit depth minus one. ii. When YCgCo-Re is used, the bit depth in RGB domain is equal to the chroma bit depth minus two. iii. When YCgCo-Ro is used, the bit depth in RGB domain is equal to the chroma bit depth minus one. 3) To address drawbacks of problem 3, constraints on using MatrixCoefficients may be specified for various SEI messages for RGB or YCgCo related values: a. Constraints on using MatrixCoefficients in the film grain characteristics SEI message may be specified for RGB or YCgCo related values. i. The matrix coefficients of the film grain characteristics shall not be equal to 0 unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics. ii. The matrix coefficients of the film grain characteristics shall not be equal to 8 unless the luma bit depth of the film grain characteristics plus one is equal to the chroma bit depth of the film grain characteristics. iii. The matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Re unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics. 1. Alternatively, the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Re unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics and both are of even numbers. iv. The matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Ro unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics and both are of odd numbers. 1. Alternatively, the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Ro unless the luma bit depth of the film grainAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) characteristics is equal to the chroma bit depth of the film grain characteristics and both are of odd numbers. b. Constraints on using MatrixCoefficients in the neural-network post-filter characteristics SEI message may be specified for YCgCo-Ro and YCgCo-Re related values. i. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re if the output tensor is not in the 4:4:4 chroma format. ii. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re if either the chroma bit depth or the luma bit depth are not present. iii. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re if the chroma bit depth and the luma bit depth are not equal. iv. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re if either the chroma bit depth or the luma bit depth are not of even number. v. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro if the output tensor is not in the 4:4:4 chroma format. vi. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro if either the chroma bit depth or the luma bit depth are not present. vii. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro if the chroma bit depth and the luma bit depth are not equal. viii. The matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro if either the chroma bit depth or the luma bit depth are not of odd number. 4) To address drawbacks of problem 4, bit depth values less than a certain positive value shall be disallowed in CICP. a. In one example, luma and / or chroma bit depth shall be greater than or equal to N. i. In one example, N is equal to 8 to let the current conversion from signals indicated colour primaries to luma / chroma signals can be applied. ii. Alternatively, in one example, N is greater than 2 to make sure that the bit depth for RGB channel is larger than 0. 1. In one example, N is equal to 3. b. In one example, bit depth values for RGB channels shall be greater than or equal to N. i. In one example, N is equal to 8 to let the current conversion from signals indicated colour primaries to RGB signals can be applied.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) ii. In one example, when MatrixCoefficients indicates YCgCo-Re, luma and / or chroma bit depth shall be greater than or equal to ( N + 2 ). iii. In one example, when MatrixCoefficients indicates YCgCo-Ro, luma and / or chroma bit depth shall be greater than or equal to ( N + 1 ). 5) To address drawbacks of problem 4, alternatively, the conversion from signals indicated colour primaries to RGB or luma / chroma signals may be extended to support cases with bit depth values less than 8 bits following the case where the bit depth value is greater than 8 bits. a. In one example, a division by a constant may be used in the conversion from signals indicated colour primaries to RGB or luma / chroma signals. i. In one example, a division by ( 1 << 8 ) is used in the conversion. 6) To address drawbacks of problem 5, a clipping operator may be used in RGB to YCgCo conversion to guarantee that the chroma values are aligned with its bit depth. 7) To address drawbacks of problem 5, for YCgCo, RGB bit depth is less than luma / chroma bit depth a. In one example, RGB bit depth plus N is equal to luma bit depth. i. In one example, N is equal to 2. ii. In one example, N is equal to 1. 8) To address drawbacks of problem 6, full_range_flag shall be equal to 1 for the case when MatrixCoefficients indicates YCgCo-R. a. full_range_flag shall be equal to 1 for the case when MatrixCoefficients indicates YCgCo-Re. b. full_range_flag shall be equal to 1 for the case when MatrixCoefficients indicates YCgCo-Ro. c. Alternatively, full_range_flag shall be equal to 1 for the case when MatrixCoefficients indicates YCgCo. 9) To address drawbacks of problem 5, an alternative rounding function Round'(x), defined as Round'(x)=Sign(x)*Ceil(x), may be used to replace the current rounding function Round(x), where Ceil(x) is the smallest integer greater than or equal to x. a. In one example, Round(x) is replaced by Round'(x) when calculating Y, Cb and Cr for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal. b. In one example, Round(x) is replaced by Round'(x) when calculating Cb and Cr for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal. c. In one example, Round(x) is replaced by Round'(x) when calculating Y and Cb for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal. i. Alternatively, in one example, Round(x) is replaced by Round'(x) when calculating Y and Cr for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal. d. In one example, Round(x) is replaced by Round'(x) when calculating Cr for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) i. Alternatively, in one example, Round(x) is replaced by Round'(x) when calculating Cb for YCgCo transform, i.e., MatrixCoefficients being 8 and luma and chroma bit depth numbers are equal. e. Alternatively, an alternative rounding function may be defined as Round'(x)=Ceil(x-0.5) and all above sub-items may apply. 10) To address drawbacks of problem 5, Round'(x) defined in the above item and Floor(x), may be used to replace the current rounding function Round(x). a. In one example, Round(x) is replaced by Round'(x) for a first two colour channel calculation and replaced by Floor(x) for a third colour channel calculation. i. In one example, Round(x) is replaced by Round'(x) for Y and Cb calculation and replaced by Floor(x) for Cr calculation. b. In one example, Round(x) is replaced by Round'(x) for a first colour channel calculation and replaced by Floor(x) for a second two colour channel calculation. c. In one example, Round(x) is replaced by Round'(x) for a first colour channel calculation and replaced by Floor(x) for a second colour channel calculation. i. In one example, Round(x) is replaced by Round'(x) for Cb calculation and replaced by Floor(x) for Cr calculation. d. Alternatively, an alternative rounding function may be defined as Round'(x)=Ceil(x-0.5) and all above sub-items may apply. 11) Round'(x) defined as in item 9 may be applied to other integer transform, integer systems, digital systems. a. In one example, Round'(x) may be used to avoid range overflow. b. In one example, Round'(x) may be used with other functions that cast real numbers to integer numbers, e.g., Round(x), Floor(x), Ceil(x) to avoid range overflow or balance error distribution. c. In one example, Round'(x) may be used in integer transforms and / or inverse transforms. d. In one example, Round'(x) may be used in digital random number generation systems. e. Alternatively, an alternative rounding function may be defined as Round'(x)=Ceil(x-0.5) and all above sub-items may apply. 6. Embodiments

[0365] Below are some example embodiments for the aspects summarized above in Section 5.

[0366] Most relevant parts that have been added are shown in bold or deleted are shown in bold italics. There may be some other changes that are editorial in nature and thus not shown. 6.1 First Embodiment

[0367] This embodiment is related to most of the items 1, 1.a, 1.b, 1.b.i, 1.c, 1.c.i summarized above in Section 5. 7.3 VUI parameters semantics ...Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) vui_matrix_coeffs describes the equations used in deriving luma and chroma signals from the green, blue, and red, or Y, Z, and X primaries. Its semantics are as specified for MatrixCoefficients in Rec. ITU-T H.273 | ISO / IEC 23091-2. vui_matrix_coeffs shall not be equal to 0 unless both of the following conditions are true: — BitDepthC is equal to BitDepthY. — ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format). The specification of the use of vui_matrix_coeffs equal to 0 under all other conditions is reserved for future use by ITU-T | ISO / IEC. vui_matrix_coeffs shall not be equal to 8 unless one of the following conditions is true: — BitDepthC is equal to BitDepthY, — BitDepthC is equal to BitDepthY + 1 and ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format). The specification of the use of vui_matrix_coeffs equal to 8 under all other conditions is reserved for future use by ITU-T | ISO / IEC. When the vui_matrix_coeffs syntax element is not present, the value of vui_matrix_coeffs is inferred to be equal to 2 (unknown or unspecified or determined by other means not specified in this document). vui_matrix_coeffs shall not be equal to 16 (YCgCo-Re) unless all of the following conditions are true: — BitDepthCis equal to BitDepthY. — ( BitDepthC& 0x01 ) is equal to 0. — ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format). The specification of the use of vui_matrix_coeffs equal to 16 under all other conditions is reserved for future use by ITU-T | ISO / IEC. vui_matrix_coeffs shall not be equal to 17 (YCgCo-Ro) unless all of the following conditions are true: — BitDepthCis equal to BitDepthY. — ( BitDepthC& 0x01 ) is equal to 1. — ChromaFormatIdc is equal to 3 (the 4:4:4 chroma format). The specification of the use of vui_matrix_coeffs equal to 17 under all other conditions is reserved for future use by ITU-T | ISO / IEC. ... 6.2 Second Embodiment

[0368] This embodiment is related to most of this items 2, 2.a, 2.a.i, 2.a.ii, 2.a.iii. summarized above in Section 5. 8.3 Matrix coefficients ... When MatrixCoefficients is equal to 0, 8, 16, or 17, the variables BitDepthRGB and MaxValRGB are derived using the following ordered steps: a) The variable BitDepthRGB is derived as follows: — If MatrixCoefficients is equal to 0 or 8, the following applies:Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) BitDepthRGB = BitDepthY (23) — Otherwise, if MatrixCoefficients is equal to 8 and BitDepthC is equal to BitDepthY, the following applies: BitDepthRGB = BitDepthY — Otherwise, if MatrixCoefficients is equal to 8 and BitDepthCis not equal to BitDepthY, the following applies: BitDepthRGB= BitDepthC− 1 — Otherwise, if MatrixCoefficients is equal to 16, the following applies: BitDepthRGB = BitDepthY + 2 BitDepthC – 2 (24) — Otherwise (MatrixCoefficients is equal to 17), the following applies: BitDepthRGB = BitDepthY + 1 BitDepthC − 1 (25) b) The variable MaxValRGB is derived as follows: MaxValRGB= ( 1 << BitDepthRGB) − 1 (26) ... 6.3 Third Embodiment

[0369] This embodiment is related to most of the items 13, 3.a, 3.a.i, 3.a.ii, 3.a.iii, 3.a.iii.1, 3.a.iv, 3.a.iv.1 summarized above in Section 5. 8.5.2 Film grain characteristics SEI message semantics ... fg_matrix_coeffs has the same semantics as specified in subclause 7.3 for the vui_matrix_coeffs syntax element, except as follows: — fg_matrix_coeffs specifies the matrix coefficients of the film grain characteristics specified in the SEI message, rather than the matrix coefficients used for the CLVS. — When fg_matrix_coeffs is not present in the film grain characteristics SEI message, the value of fg_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. — The values allowed for fg_matrix_coeffs are not constrained by the chroma format of the decoded video pictures that is indicated by the value of ChromaFormatIdc for the semantics of the VUI parameters. fg_matrix_coeffs shall not be equal to 0 unless fg_bit_depth_luma_minus8 is equal to fg_bit_depth_chroma_minus8. fg_matrix_coeffs shall not be equal to 8 unless one of the following conditions is true: — fg_bit_depth_chroma_minus8 is equal to fg_bit_depth_luma_minus8, — fg_bit_depth_chroma_minus8 is equal to fg_bit_depth_luma_minus8 + 1. ... 6.4 Fourth Embodiment

[0370] This embodiment is related to most of this items 3, 3.a, 3.a.i, 3.a.i.1, 3.a.ii, 3.a.ii.1 summarized above in Section 5.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 8.28.2.2 Neural-network post-filter characteristics SEI message semantics ... nnpfc_matrix_coeffs describes the equations used in deriving luma and chroma signals from the green, blue, and red, or Y, Z, and X primaries. Its semantics apply to the pictures resulting from applying the NNPF specified in this SEI message and are as specified for MatrixCoefficients in Rec. ITU-T H.273 | ISO / IEC 23091-2 with BitDepthYand BitDepthCbeing equal to outTensorBitDepthYand outTensorBitDepthC, respectively. When nnpfc_matrix_coeffs is not present in the NNPFC SEI message, the value of nnpfc_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. nnpfc_matrix_coeffs shall not be equal to 16 (YCgCo-Re) unless all of the following conditions are true: – Both nnpfc_out_tensor_chroma_bitdepth_minus8 and nnpfc_out_tensor_luma_bitdepth_minus8 are present. – Both nnpfc_out_tensor_chroma_bitdepth_minus8 and nnpfc_out_tensor_luma_bitdepth_minus8 are of even number. – nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8. – nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1. nnpfc_matrix_coeffs shall not be equal to 17 (YCgCo-Ro) unless all of the following conditions are true: – Both nnpfc_out_tensor_chroma_bitdepth_minus8 and nnpfc_out_tensor_luma_bitdepth_minus8 are present. – Both nnpfc_out_tensor_chroma_bitdepth_minus8 and nnpfc_out_tensor_luma_bitdepth_minus8 are of odd number. – nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8. – nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1. ... 6.5 Embodiment 5

[0371] This embodiment is related to items 1, 1.a, 1.b, 1.c, 5, 5.a, 6 summarized above in Section 5. The text changes are based on [6]. 8.3 Matrix coefficients

[0372] Type: Unsigned integer, enumeration

[0373] Range: 0 to 255, inclusive, plus associated flag

[0374] MatrixCoefficients describes the matrix coefficients used in deriving luma and chroma signals from the green, blue, and red, or X, Y, and Z primaries, as specified in Table 7, above, and the pseudocode operations specified below.

[0375] The value of MatrixCoefficients shall not be equal to 0, 16 or 17 unless both the following conditions are true: – BitDepthY is equal to BitDepthC. – The picture chroma format is 4:4:4.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0376] The specification of the use of MatrixCoefficients equal to 0, 16 or 17 under all other conditions is reserved for future use by ITU-T | ISO / IEC.

[0377] The value of MatrixCoefficients shall not be equal to 8 unless one of the following conditions are true: – BitDepthY is equal to BitDepthC. – BitDepthC is equal to BitDepthY + 1 and the picture chroma format is 4:4:4.

[0378] The specification of the use of MatrixCoefficients equal to 8 under all other conditions is reserved for future use by ITU-T | ISO / IEC.

[0379] A flag, VideoFullRangeFlag, may be supplied with this code point (see below). ... 6.6 Embodiment 6

[0380] This embodiment is related to items 4, 4.a, 4.a.ii summarized above in Section 5. The text changes are based on [6]. 8.3 Matrix coefficients ...

[0381] BitDepthY shall be greater than or equal to 3. The specification of the use of BitDepthY less than 3 is reserved for future use by ITU-T | ISO / IEC.

[0382] When MatrixCoefficients is equal to 0, 8, 16, or 17, the variables BitDepthRGB and MaxValRGB are derived using the following ordered steps: a) The variable BitDepthRGB is derived as follows: — If MatrixCoefficients is equal to 0 or 8, the following applies: BitDepthRGB = BitDepthY (23) — Otherwise, if MatrixCoefficients is equal to 16, the following applies: BitDepthRGB = BitDepthY +− 2 (24) — Otherwise (MatrixCoefficients is equal to 17), the following applies: BitDepthRGB= BitDepthY+− 1 (25) b) The variable MaxValRGBis derived as follows: MaxValRGB= ( 1 << BitDepthRGB) – 1 (26) 6.7 Embodiment 7

[0383] This embodiment is related to items 5, 5.a, 5.a.i summarized above in Section 5. The text changes are based on [6]. 8.3 Matrix coefficients ... — If VideoFullRangeFlag is equal to 0, the following applies: — If MatrixCoefficients is equal to 0, 8, 16, or 17, pseudocode operations (27) to (29) apply: R = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) ÷ ( 1 << 8 ) * ( 219 * E′R + 16 ) ) (27)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) G = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) ÷ ( 1 << 8 ) * ( 219 * E′G + 16 ) ) (28) B = Clip3( 0, MaxValRGB, ( 1 << ( BitDepthRGB − 8 ) ) ÷ ( 1 << 8 ) * ( 219 * E′B + 16 ) ) (29) — Otherwise, if MatrixCoefficients is equal to 1, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, or 15, pseudocode operations (30) to (32) apply: Y = Clip1Y( Round( ( 1 << (BitDepthY− 8 ) ) ÷ ( 1 << 8 ) * ( 219 * E′Y+ 16 ) ) ) (30) Cb = Clip1C( Round( ( 1 << (BitDepthC− 8 ) ) ÷ ( 1 << 8 ) * ( 224 * E′PB+ 128 ) ) ) (31) Cr = Clip1C( Round( ( 1 << (BitDepthC− 8 ) ) ÷ ( 1 << 8 ) * ( 224 * E′PR+ 128 ) ) ) (32) ... 6.8 Embodiment 8

[0384] This embodiment is related to item 6 summarized above in Section 5. The text changes are based on [6]. 8.3 Matrix coefficients ... — Otherwise, if MatrixCoefficients is equal to 8 and BitDepthCis equal to BitDepthY, pseudocode operations (51) to (53) apply: Y = Round( 0.5 * G + 0.25 * ( R + B ) ) (51) Cb = Clip1C( Round( 0.5 * G − 0.25 * ( R + B ) ) + (1 << ( BitDepthC − 1 ) ) ) (52) Cr = Clip1C( Round( 0.5 * (R − B ) ) + (1 << ( BitDepthC − 1 ) ) ) (53) ... 6.9 Embodiment 9 This embodiment is related to item 6 summarized above in Section 5. The text changes are based on [6]. 8.3 Matrix coefficients ...When MatrixCoefficients is equal to 0, 8, 16, or 17, the variables BitDepthRGBand MaxValRGBare derived using thefollowing ordered steps: a) The variable BitDepthRGB is derived as follows: — If MatrixCoefficients is equal to 0 or 8, the following applies: BitDepthRGB = BitDepthY − 2 (23) ... — Otherwise, if MatrixCoefficients is equal to 8 and BitDepthCis equal to BitDepthY, pseudocode operations (51) to (53) apply: Y = Round( 0.52 * G + 0.25 * ( R + B ) ) (51) Cb = ( BitDepthC− 1 ) ) (52) Cr =− 1 ) ) (53) 6.10 Embodiment 10

[0385] This embodiment is related to the items 9, 9.a summarized above in Section 5. The text changes are based on [6].Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 5.4 Mathematical functions The following mathematical functions are defined as follows: Abs( x ) =^ x ; x ^^ 0^x ; x ^ 0 (1)Clip1Y( x ) = Clip3( 0, ( 1 << BitDepthY) − 1, x ) (2) where BitDepthYis the representation bit depth of the corresponding luma colour component signal. Clip1C( x ) = Clip3( 0, ( 1 << BitDepthC ) − 1, x ) (3) where BitDepthC is the representation bit depth of the corresponding chroma colour component signal C. In general, BitDepthC may be distinct for different chroma colour component signal C – e.g., for C corresponding to Cb or Cr. x; z ^ xClip3( x, y, z ) = ^y ; z ^ y (4)z ; otherwiseFloor( x ) the largest integer less than or equal to x (5) Ceil( x ) the smallest integer greater than or equal to x Ln( x ) the natural logarithm of x (6) Log10( x ) the base-10 logarithm of x (7) Round( x ) = Sign( x ) * Floor( Abs( x ) + 0.5 ) (8) Round'(x) = Sign( x ) * Ceil( Abs( x ) − 0.5 ) 1; x ^ 0Sign( x ) = ^ 0 ; x ^ ^ 0 (9)0Sqrt( x (10)8.3 Matrix coefficients ... —Otherwise, if MatrixCoefficients is equal to 8 and BitDepthCis equal to BitDepthY, pseudocodeoperations (51) to (53) apply: Y = Round'( 0.5 * G + 0.25 * ( R + B ) ) (51) Cb = Round'( 0.5 * G − 0.25 * ( R + B ) ) + (1 << ( BitDepthC − 1 ) ) (52) Cr = Round'( 0.5 * (R − B ) ) + (1 << ( BitDepthC − 1 ) ) (53) ... 6.11 Embodiment 11

[0386] This embodiment is related to items 10, 10.a, 10.a.i summarized above in Section 5. The text changes are based on [6]. 5.4 Mathematical functions The following mathematical functions are defined as follows: Abs( x ) =^ x ; x ^^ 0^ (1)Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) Clip1Y( x ) = Clip3( 0, ( 1 << BitDepthY ) − 1, x ) (2) where BitDepthY is the representation bit depth of the corresponding luma colour component signal. Clip1C( x ) = Clip3( 0, ( 1 << BitDepthC ) − 1, x ) (3) where BitDepthC is the representation bit depth of the corresponding chroma colour component signal C. In general, BitDepthCmay be distinct for different chroma colour component signal C – e.g., for C corresponding to Cb or Cr. x; z ^ xClip3( x, y, z ) = ^ y ; z ^ y (4)z ; otherwiseFloor( x ) the largest integer less than or equal to x (5) Ceil( x ) the smallest integer greater than or equal to x Ln( x ) the natural logarithm of x (6) Log10( x ) the base-10 logarithm of x (7) Round( x ) = Sign( x ) * Floor( Abs( x ) + 0.5 ) (8) Round'(x) = Sign( x ) * Ceil( Abs( x ) − 0.5 ) 1; x ^ 0Sign( x ) = ^ 0 ; x ^ ^ 0 (9)0Sqrt( x (10)8.3 Matrix ... — Otherwise, if MatrixCoefficients is equal to 8 and BitDepthC is equal to BitDepthY, pseudocode operations (51) to (53) apply: Y = Round'( 0.5 * G + 0.25 * ( R + B ) ) (51) Cb = Round'( 0.5 * G − 0.25 * ( R + B ) ) + (1 << ( BitDepthC− 1 ) ) (52) Cr = Round Floor( 0.5 * (R − B ) ) + (1 << ( BitDepthC− 1 ) ) (53) ... 7. References [1] ISO / IEC 23091-2 (in force edition). [2] ITU-T and ISO / IEC, “Advanced video coding,” Rec. ITU-T H.264 | ISO / IEC 14496-10 (in force edition). [3] ITU-T and ISO / IEC, “High efficiency video coding,” Rec. ITU-T H.265 | ISO / IEC 23008-2 (in force edition). [4] ITU-T and ISO / IEC, “Versatile video coding,” Rec. ITU-T H.266 | ISO / IEC 23090-3 (in force edition). [5] ITU-T and ISO / IEC, “Versatile supplemental enhancement information messages for coded video bitstreams,” Rec. ITU-T H.274 | ISO / IEC 23002-7 (in force edition). [6] “Preliminary text of ISO / IEC FDIS 23091-2:202x Video CICP (3rd edition),” ISO / IEC SC29 / WG5 N00206

[0387] FIG. 7 is a block diagram showing an example video processing system 4000 in which various embodiments disclosed herein may be implemented. Various implementations may include some or all of theAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) components of the system 4000. The system 4000 may include input 4002 for receiving video content. The video content may be received in a raw or uncompressed format, e.g., 8- or 10-bit multi-component pixel values, or may be in a compressed or encoded format. The input 4002 may represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interface include wired interfaces such as Ethernet, passive optical network (PON), etc. and wireless interfaces such as Wi-Fi or cellular interfaces.

[0388] The system 4000 may include a coding component 4004 that may implement the various coding or encoding methods described in the present disclosure. The coding component 4004 may reduce the average bitrate of video from the input 4002 to the output of the coding component 4004 to produce a coded representation of the video. The coding techniques are therefore sometimes called video compression or video transcoding techniques. The output of the coding component 4004 may be either stored, or transmitted via a communication connected, as represented by the component 4006. The stored or communicated bitstream (or coded) representation of the video received at the input 4002 may be used by a component 4008 for generating pixel values or displayable video that is sent to a display interface 4010. The process of generating user-viewable video from the bitstream representation is sometimes called video decompression. Furthermore, while certain video processing operations are referred to as “coding” operations or tools, it will be appreciated that the coding tools or operations are used at an encoder and corresponding decoding tools or operations that reverse the results of the coding will be performed by a decoder.

[0389] Examples of a peripheral bus interface or a display interface may include universal serial bus (USB) or high definition multimedia interface (HDMI) or DisplayPort, and so on. Examples of storage interfaces include serial advanced technology attachment (SATA), peripheral component interconnect (PCI), integrated drive electronics (IDE) interface, and the like. The embodiments described in the present disclosure may be embodied in various electronic devices such as mobile phones, laptops, smartphones or other devices that are capable of performing digital data processing and / or video display.

[0390] FIG.8 is a block diagram of an example video processing apparatus 4100. The apparatus 4100 may be used to implement one or more of the methods described herein. The apparatus 4100 may be embodied in a smartphone, tablet, computer, Internet of Things (IoT) receiver, and so on. The apparatus 4100 may include one or more processors 4102, one or more memories 4104 and video processing circuitry 4106. The processor(s) 4102 may be configured to implement one or more methods described in the present disclosure. The memory (memories) 4104 may be used for storing data and code used for implementing the methods and embodiments described herein. The video processing circuitry 4106 may be used to implement, in hardware circuitry, some embodiments described in the present disclosure. In some embodiments, the video processing circuitry 4106 may be at least partly included in the processor 4102, e.g., a graphics co-processor.

[0391] FIG.9 is a flowchart for an example method 4200 of video processing. The method 4200 determines a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding- independent code points (CICP) at step 4202. A conversion between a visual media data and a bitstream is performedAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) based on the CICP at step 4204. The conversion may include encoding at an encoder, decoding at a decoder, or combinations thereof.

[0392] It should be noted that the method 4200 can be implemented in an apparatus for processing video data comprising a processor and a non-transitory memory with instructions thereon, such as video encoder 4400, video decoder 4500, and / or encoder 4600. In such a case, the instructions upon execution by the processor, cause the processor to perform the method 4200. Further, the method 4200 can be performed by a non-transitory computer readable medium comprising a computer program product for use by a video coding device. The computer program product comprises computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method 4200.

[0393] FIG. 10 is a block diagram that illustrates an example video coding system 4300 that may utilize the embodiments of this disclosure. The video coding system 4300 may include a source device 4310 and a destination device 4320. Source device 4310 generates encoded video data which may be referred to as a video encoding device. Destination device 4320 may decode the encoded video data generated by source device 4310 which may be referred to as a video decoding device.

[0394] Source device 4310 may include a video source 4312, a video encoder 4314, and an input / output (I / O) interface 4316. Video source 4312 may include a source such as a video capture device, an interface to receive video data from a video content provider, and / or a computer graphics system for generating video data, or a combination of such sources. The video data may comprise one or more pictures. Video encoder 4314 encodes the video data from video source 4312 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded picture is a coded representation of a picture. The associated data may include sequence parameter sets, picture parameter sets, and other syntax structures. I / O interface 4316 may include a modulator / demodulator (modem) and / or a transmitter. The encoded video data may be transmitted directly to destination device 4320 via I / O interface 4316 through network 4330. The encoded video data may also be stored onto a storage medium / server 4340 for access by destination device 4320.

[0395] Destination device 4320 may include an I / O interface 4326, a video decoder 4324, and a display device 4322. I / O interface 4326 may include a receiver and / or a modem. I / O interface 4326 may acquire encoded video data from the source device 4310 or the storage medium / server 4340. Video decoder 4324 may decode the encoded video data. Display device 4322 may display the decoded video data to a user. Display device 4322 may be integrated with the destination device 4320, or may be external to destination device 4320, which can be configured to interface with an external display device.

[0396] Video encoder 4314 and video decoder 4324 may operate according to a video compression standard, such as the High Efficiency Video Coding (HEVC) standard, Versatile Video Coding (VVC) standard and other current and / or further standards.

[0397] FIG.11 is a block diagram illustrating an example of video encoder 4400, which may be video encoder 4314 in the system 4300 illustrated in FIG.10. Video encoder 4400 may be configured to perform any or all of theAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) embodiments of this disclosure. The video encoder 4400 includes a plurality of functional components. The embodiments described in this disclosure may be shared among the various components of video encoder 4400. In some examples, a processor may be configured to perform any or all of the embodiments described in this disclosure.

[0398] The functional components of video encoder 4400 may include a partition unit 4401; a prediction unit 4402, which may include a mode select unit 4403, a motion estimation unit 4404, a motion compensation unit 4405, and an intra prediction unit 4406; a residual generation unit 4407; a transform processing unit 4408; a quantization unit 4409; an inverse quantization unit 4410; an inverse transform unit 4411; a reconstruction unit 4412; a buffer 4413; and an entropy encoding unit 4414.

[0399] In other examples, video encoder 4400 may include more, fewer, or different functional components. In an example, prediction unit 4402 may include an intra block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode in which at least one reference picture is a picture where the current video block is located.

[0400] Furthermore, some components, such as motion estimation unit 4404 and motion compensation unit 4405 may be highly integrated, but are represented in the example of video encoder 4400 separately for purposes of explanation.

[0401] Partition unit 4401 may partition a picture into one or more video blocks. Video encoder 4400 and video decoder 4500 may support various video block sizes.

[0402] Mode select unit 4403 may select one of the coding modes, intra or inter, e.g., based on error results, and provide the resulting intra or inter coded block to a residual generation unit 4407 to generate residual block data and to a reconstruction unit 4412 to reconstruct the encoded block for use as a reference picture. In some examples, mode select unit 4403 may select a combination of intra and inter prediction (CIIP) mode in which the prediction is based on an inter prediction signal and an intra prediction signal. Mode select unit 4403 may also select a resolution for a motion vector (e.g., a sub-pixel or integer pixel precision) for the block in the case of inter prediction.

[0403] To perform inter prediction on a current video block, motion estimation unit 4404 may generate motion information for the current video block by comparing one or more reference frames from buffer 4413 to the current video block. Motion compensation unit 4405 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from buffer 4413 other than the picture associated with the current video block.

[0404] Motion estimation unit 4404 and motion compensation unit 4405 may perform different operations for a current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice.

[0405] In some examples, motion estimation unit 4404 may perform uni-directional prediction for the current video block, and motion estimation unit 4404 may search reference pictures of list 0 or list 1 for a reference video block for the current video block. Motion estimation unit 4404 may then generate a reference index that indicates the reference picture in list 0 or list 1 that contains the reference video block and a motion vector that indicates a spatial displacement between the current video block and the reference video block. Motion estimation unit 4404 may output the reference index, a prediction direction indicator, and the motion vector as the motion information of the currentAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) video block. Motion compensation unit 4405 may generate the predicted video block of the current block based on the reference video block indicated by the motion information of the current video block.

[0406] In other examples, motion estimation unit 4404 may perform bi-directional prediction for the current video block, motion estimation unit 4404 may search the reference pictures in list 0 for a reference video block for the current video block and may also search the reference pictures in list 1 for another reference video block for the current video block. Motion estimation unit 4404 may then generate reference indexes that indicate the reference pictures in list 0 and list 1 containing the reference video blocks and motion vectors that indicate spatial displacements between the reference video blocks and the current video block. Motion estimation unit 4404 may output the reference indexes and the motion vectors of the current video block as the motion information of the current video block. Motion compensation unit 4405 may generate the predicted video block of the current video block based on the reference video blocks indicated by the motion information of the current video block.

[0407] In some examples, motion estimation unit 4404 may output a full set of motion information for decoding processing of a decoder. In some examples, motion estimation unit 4404 may not output a full set of motion information for the current video. Rather, motion estimation unit 4404 may signal the motion information of the current video block with reference to the motion information of another video block. For example, motion estimation unit 4404 may determine that the motion information of the current video block is sufficiently similar to the motion information of a neighboring video block.

[0408] In one example, motion estimation unit 4404 may indicate, in a syntax structure associated with the current video block, a value that indicates to the video decoder 4500 that the current video block has the same motion information as another video block.

[0409] In another example, motion estimation unit 4404 may identify, in a syntax structure associated with the current video block, another video block and a motion vector difference (MVD). The motion vector difference indicates a difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 4500 may use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.

[0410] As discussed above, video encoder 4400 may predictively signal the motion vector. Two examples of predictive signaling techniques that may be implemented by video encoder 4400 include advanced motion vector prediction (AMVP) and merge mode signaling.

[0411] Intra prediction unit 4406 may perform intra prediction on the current video block. When intra prediction unit 4406 performs intra prediction on the current video block, intra prediction unit 4406 may generate prediction data for the current video block based on decoded samples of other video blocks in the same picture. The prediction data for the current video block may include a predicted video block and various syntax elements.

[0412] Residual generation unit 4407 may generate residual data for the current video block by subtracting the predicted video block(s) of the current video block from the current video block. The residual data of the current video block may include residual video blocks that correspond to different sample components of the samples in the current video block.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0413] In other examples, there may be no residual data for the current video block for the current video block, for example in a skip mode, and residual generation unit 4407 may not perform the subtracting operation.

[0414] Transform processing unit 4408 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to a residual video block associated with the current video block.

[0415] After transform processing unit 4408 generates a transform coefficient video block associated with the current video block, quantization unit 4409 may quantize the transform coefficient video block associated with the current video block based on one or more quantization parameter (QP) values associated with the current video block.

[0416] Inverse quantization unit 4410 and inverse transform unit 4411 may apply inverse quantization and inverse transforms to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. Reconstruction unit 4412 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the prediction unit 4402 to produce a reconstructed video block associated with the current block for storage in the buffer 4413.

[0417] After reconstruction unit 4412 reconstructs the video block, the loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0418] Entropy encoding unit 4414 may receive data from other functional components of the video encoder 4400. When entropy encoding unit 4414 receives the data, entropy encoding unit 4414 may perform one or more entropy encoding operations to generate entropy encoded data and output a bitstream that includes the entropy encoded data.

[0419] FIG.12 is a block diagram illustrating an example of video decoder 4500 which may be video decoder 4324 in the system 4300 illustrated in FIG.10. The video decoder 4500 may be configured to perform any or all of the embodiments of this disclosure. In the example shown, the video decoder 4500 includes a plurality of functional components. The embodiments described in this disclosure may be shared among the various components of the video decoder 4500. In some examples, a processor may be configured to perform any or all of the embodiments described in this disclosure.

[0420] In the example shown, video decoder 4500 includes an entropy decoding unit 4501, a motion compensation unit 4502, an intra prediction unit 4503, an inverse quantization unit 4504, an inverse transformation unit 4505, a reconstruction unit 4506, and a buffer 4507. Video decoder 4500 may, in some examples, perform a decoding pass generally reciprocal to the encoding pass described with respect to video encoder 4400.

[0421] Entropy decoding unit 4501 may retrieve an encoded bitstream. The encoded bitstream may include entropy coded video data (e.g., encoded blocks of video data). Entropy decoding unit 4501 may decode the entropy coded video data, and from the entropy decoded video data, motion compensation unit 4502 may determine motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. Motion compensation unit 4502 may, for example, determine such information by performing the AMVP and merge mode.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0422] Motion compensation unit 4502 may produce motion compensated blocks, possibly performing interpolation based on interpolation filters. Identifiers for interpolation filters to be used with sub-pixel precision may be included in the syntax elements.

[0423] Motion compensation unit 4502 may use interpolation filters as used by video encoder 4400 during encoding of the video block to calculate interpolated values for sub-integer pixels of a reference block. Motion compensation unit 4502 may determine the interpolation filters used by video encoder 4400 according to received syntax information and use the interpolation filters to produce predictive blocks.

[0424] Motion compensation unit 4502 may use some of the syntax information to determine sizes of blocks used to encode frame(s) and / or slice(s) of the encoded video sequence, partition information that describes how each macroblock of a picture of the encoded video sequence is partitioned, modes indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter coded block, and other information to decode the encoded video sequence.

[0425] Intra prediction unit 4503 may use intra prediction modes for example received in the bitstream to form a prediction block from spatially adjacent blocks. Inverse quantization unit 4504 inverse quantizes, i.e., de-quantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies an inverse transform.

[0426] Reconstruction unit 4506 may sum the residual blocks with the corresponding prediction blocks generated by motion compensation unit 4502 or intra prediction unit 4503 to form decoded blocks. If desired, a deblocking filter may also be applied to filter the decoded blocks in order to remove blockiness artifacts. The decoded video blocks are then stored in buffer 4507, which provides reference blocks for subsequent motion compensation / intra prediction and also produces decoded video for presentation on a display device.

[0427] FIG. 13 is a schematic diagram of an example encoder 4600. The encoder 4600 is suitable for implementing the techniques of VVC. The encoder 4600 includes three in-loop filters, namely a deblocking filter (DF) 4602, a sample adaptive offset (SAO) 4604, and an adaptive loop filter (ALF) 4606. Unlike the DF 4602, which uses predefined filters, the SAO 4604 and the ALF 4606 utilize the original samples of the current picture to reduce the mean square errors between the original samples and the reconstructed samples by adding an offset and by applying a finite impulse response (FIR) filter, respectively, with coded side information signaling the offsets and filter coefficients. The ALF 4606 is located at the last processing stage of each picture and can be regarded as a tool trying to catch and fix artifacts created by the previous stages.

[0428] The encoder 4600 further includes an intra prediction component 4608 and a motion estimation / compensation (ME / MC) component 4610 configured to receive input video. The intra prediction component 4608 is configured to perform intra prediction, while the ME / MC component 4610 is configured to utilize reference pictures obtained from a reference picture buffer 4612 to perform inter prediction. Residual blocks from inter prediction or intra prediction are fed into a transform (T) component 4614 and a quantization (Q) component 4616 to generate quantized residual transform coefficients, which are fed into an entropy coding component 4618. The entropy coding component 4618 entropy codes the prediction results and the quantized transform coefficients andAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) transmits the same toward a video decoder (not shown). Quantization components output from the quantization component 4616 may be fed into an inverse quantization (IQ) components 4620, an inverse transform component 4622, and a reconstruction (REC) component 4624. The REC component 4624 is able to output images to the DF 4602, the SAO 4604, and the ALF 4606 for filtering prior to those images being stored in the reference picture buffer 4612.

[0429] A listing of solutions preferred by some examples is provided next.

[0430] The following solutions show examples of embodiments discussed herein.

[0431] 1. A method for processing media data comprising: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); and performing a conversion between a visual media data and a bitstream based CICP.

[0432] 2. The method of solution 1, wherein a chroma bit depth shall be equal to a luma bit depth when YCgCo- Re or YCgCo-Ro is used in CICP.

[0433] 3. The method of any of solutions 1-2, wherein bit depth is an even number when YCgCo-Re is used in CICP, or wherein bit depth is an odd number when YCgCo-Ro is used in CICP.

[0434] 4. The method of any of solutions 1-3, wherein a bit depth and a maximum sample value in a red green blue (RGB) domain are based on a chroma bit depth for the YCgCo format.

[0435] 5. The method of any of solutions 1-4, wherein the bit depth in RGB domain is equal to the chroma bit depth minus one when YCgCo-R is used, or wherein the bit depth in RGB domain is equal to the chroma bit depth minus two when YCgCo-Re is used, or wherein the bit depth in RGB domain is equal to the chroma bit depth minus one when YCgCo-Ro is used.

[0436] 6. The method of any of solutions 1-5, wherein constraints on using MatrixCoefficients are specified for supplemental enhancement information (SEI) messages for RGB or YCgCo related values.

[0437] 7. The method of any of solutions 1-6, wherein constraints on using MatrixCoefficients in a film grain characteristics SEI message are specified for RGB or YCgCo related values.

[0438] 8. The method of any of solutions 1-7, wherein matrix coefficients of film grain characteristics shall not be equal to 0 unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics, or wherein the matrix coefficients of the film grain characteristics shall not be equal to 8 unless the luma bit depth of the film grain characteristics plus one is equal to the chroma bit depth of the film grain characteristics.

[0439] 9. The method of any of solutions 1-8, wherein the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Re unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics, or wherein the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Re unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics and both are of even numbers.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0440] 10. The method of any of solutions 1-9, wherein the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Ro unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics and both are of odd numbers, or wherein the matrix coefficients of the film grain characteristics shall not be equal to the value indicating YCgCo-Ro unless the luma bit depth of the film grain characteristics is equal to the chroma bit depth of the film grain characteristics and both are of odd numbers.

[0441] 11. The method of any of solutions 1-10, wherein constraints on using MatrixCoefficients in the neural- network post-filter characteristics SEI message are specified for YCgCo-Ro and YCgCo-Re related values.

[0442] 12. The method of any of solutions 1-11, wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re when the output tensor is not in the 4:4:4 chroma format, or wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re when either the chroma bit depth or the luma bit depth are not present.

[0443] 13. The method of any of solutions 1-12, wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re when the chroma bit depth and the luma bit depth are not equal, or wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Re when either the chroma bit depth or the luma bit depth are not of even number.

[0444] 14. The method of any of solutions 1-13, wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro when the output tensor is not in the 4:4:4 chroma format, or wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo-Ro when either the chroma bit depth or the luma bit depth are not present, or wherein the matrix coefficients of the neural-network post-filter characteristics shall not be equal to the value indicating YCgCo- Ro when the chroma bit depth and the luma bit depth are not equal.

[0445] 15. The method of any of solutions 1-14, wherein the conversion includes encoding the visual media data into the bitstream.

[0446] 16. The method of any of solutions 1-14, wherein the conversion includes decoding the visual media data from the bitstream.

[0447] 17. An apparatus for processing video data comprising: a processor; and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of solutions 1-16.

[0448] 18. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non- transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of solutions 1-16.

[0449] 19. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representationAtty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); and generating the bitstream based on the determining.

[0450] 20. A method for storing bitstream of a video comprising: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); generating the bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

[0451] 21. A method, apparatus, or system described in the present disclosure.

[0452] In the solutions described herein, an encoder may conform to the format rule by producing a coded representation according to the format rule. In the solutions described herein, a decoder may use the format rule to parse syntax elements in the coded representation with the knowledge of presence and absence of syntax elements according to the format rule to produce decoded video.

[0453] In the present disclosure, the term “video processing” may refer to video encoding, video decoding, video compression or video decompression. For example, video compression algorithms may be applied during conversion from pixel representation of a video to a corresponding bitstream representation or vice versa. The bitstream representation of a current video block may, for example, correspond to bits that are either co-located or spread in different places within the bitstream, as is defined by the syntax. For example, a macroblock may be encoded in terms of transformed and coded error residual values and also using bits in headers and other fields in the bitstream. Furthermore, during conversion, a decoder may parse a bitstream with the knowledge that some fields may be present, or absent, based on the determination, as is described in the above solutions. Similarly, an encoder may determine that certain syntax fields are or are not to be included and generate the coded representation accordingly by including or excluding the syntax fields from the coded representation.

[0454] The disclosed and other solutions, examples, embodiments, modules and the functional operations described in this disclosure can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this disclosure and their structural equivalents, or in combinations of one or more of them. The disclosed and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more them. The term “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0455] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0456] The processes and logic flows described in this disclosure can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC).

[0457] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random-access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and compact disc read-only memory (CD ROM) and Digital versatile disc-read only memory (DVD-ROM) disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0458] While the present disclosure contains many specifics, these should not be construed as limitations on the scope of any subject matter or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of the present disclosure. Certain features that are described in the present disclosure in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W)

[0459] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Moreover, the separation of various system components in the embodiments described in the present disclosure should not be understood as requiring such separation in all embodiments.

[0460] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in the present disclosure.

[0461] A first component is directly coupled to a second component when there are no intervening components, except for a line, a trace, or another medium between the first component and the second component. The first component is indirectly coupled to the second component when there are intervening components other than a line, a trace, or another medium between the first component and the second component. The term “coupled” and its variants include both directly coupled and indirectly coupled. The use of the term “about” means a range including ±10% of the subsequent number unless otherwise stated.

[0462] While several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods might be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples are to be considered as illustrative and not restrictive, and the intention is not to be limited to the details given herein. For example, the various elements or components may be combined or integrated in another system or certain features may be omitted, or not implemented.

[0463] In addition, techniques, systems, subsystems, and methods described and illustrated in the various embodiments as discrete or separate may be combined or integrated with other systems, modules, techniques, or methods without departing from the scope of the present disclosure. Other items shown or discussed as coupled may be directly connected or may be indirectly coupled or communicating through some interface, device, or intermediate component whether electrically, mechanically, or otherwise. Other examples of changes, substitutions, and alterations are ascertainable by one skilled in the art and could be made without departing from the spirit and scope disclosed herein.

Claims

Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) CLAIMS What is claimed is:

1. A method for processing media data, comprising: performing a conversion between a visual media data and a bitstream of the visual media data based on coding- independent code points (CICP) according to a rule, wherein the rule specifies that a video or an image of the visual media data shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo- R odd bit depth (YCgCo-Ro) is used in CICP.

2. The method of claim 1, wherein the rule further specifies that when YCgCo is used in CICP, either a) at least one of Cb and Cr components, or b) at least two of Y, Cb, and Cr components are calculated according to: Round’( x ) = Sign( x ) * Ceil( x ), wherein x is the component being calculated, wherein Sign( x ) is a sign of x, and wherein Ceil( x ) is a smallest integer greater than or equal to x.

3. The method of claim 1, wherein the rule further specifies that when YCgCo is used in CICP, either a) at least one of Cb and Cr components, or b) at least two of Y, Cb, and Cr components are calculated according to: Round’( x ) = Ceil( x – 0.5 ), wherein x is the component being calculated, and wherein Ceil( x – 0.5 ) is a smallest integer greater than or equal to x – 0.

5.

4. The method of any of claims 1-3, wherein the rule further specifies that Round( x ) is replaced by Round’( x ) for two color channel calculations, and is replaced by Floor( x ) for a third color channel calculation.

5. The method of claim 4, wherein the first two color channels calculations comprise Y and Cb calculations, and the third color channel calculation comprises a Cr calculation.

6. The method of any of claims 1-3, wherein the rule further specifies that Round( x ) is replaced by Round’( x ) for a first color channel calculation, and is replaced by Floor( x ) for second two color channel calculations.

7. The method of claim 6, wherein the first color channel calculation comprises a Y calculation, and the second two color channel calculations comprise Cb and Cr calculations.

8. The method of any of claims 1-3, wherein the rule further specifies that Round( x ) is replaced by Round’( x ) for a first color channel calculation, and is replaced by Floor( x ) for a second color channel calculations.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 9. The method of claim 8, wherein the first color channel calculation comprises a Cb calculation, and the second color channel calculation comprises a Cr calculation.

10. The method of any of claims 1-9, wherein Round’( x ) = Sign( x ) * Ceil( x ), or wherein Round’( x ) = Ceil( x – 0.5 ).

11. The method of any of claims 1-10, wherein Round’( x ) is applied to an integer transform, an inverse transform, an integer system, and / or a digital random number generation system to avoid range overflow and / or to balance an error distribution.

12. The method of claim 11, wherein Round’( x ) is applied in combination with Floor( x ) and / or Ceiling( x ).

13. The method of any of claims 1-12, wherein the conversion includes encoding the visual media data into the bitstream.

14. The method of any of claims 1-12, wherein the conversion includes decoding the visual media data from the bitstream.

15. An apparatus for processing video data comprising: a processor; and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of claims 1-14.

16. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of claims 1-14.

17. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); and generating the bitstream based on the determining.Atty. Dkt. No.: 4824-54308 (P24032360799WO2; G25N11256W) 18. A method for storing bitstream of a video, comprising: determining a video or an image shall be in the 4:4:4 chroma format when luma chrominance green chrominance orange representation (YCgCo-R) even bit depth (YCgCo-Re) or YCgCo-R odd bit depth (YCgCo-Ro) is used in coding-independent code points (CICP); generating the bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

Images