Neural network post-processing filter with downsampling capability

Abstract

A method of processing media data is disclosed. In one embodiment, the method includes determining a value of a neural network post-processing filter characteristic (NNPFC) destination (nnpfcpurse) in a supplemental enhancement information (SEI) message, where nnpfcpurse is configured to be set to include output picture size downsampling, where nnpfcpurse is configured to include output picture size downsampling, and where nnpfcpurse is configured to include output picture size downsampling. And wherein at least one of (1) the output picture width is not equal to the input picture width and (2) the output picture height is not equal to the input picture height; and performing a conversion between the visual media data and the bitstream on the basis of the nnpfcpurpose.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims the benefit of U.S. Provisional Patent Application No. 63 / 398,701, filed on August 17, 2022, which is incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the generation, storage and use of digital audio-visual media information in file format. Background Art

[0004] Digital video accounts for the largest share of bandwidth used on the Internet and other digital communications networks. As the number of connected user devices capable of receiving and displaying video increases, bandwidth requirements for digital video usage are likely to continue to grow. Summary of the invention

[0005] A first aspect relates to a method for processing video data, comprising: determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC supplemental enhancement information (SEI) message, wherein the nnpfc_purpose is configured to be set to include output picture size downsampling, and wherein at least one of the following: (1) the output picture width is not equal to the input picture width and (2) the output picture height is not equal to the input picture height; and performing conversion between visual media data and a bitstream based on the nnpfc_purpose.

[0006] Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: the output picture width is less than the input picture width, wherein the output picture height is less than the input picture height, or both. Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: the input picture width is referred to as the crop width, and the input picture height is referred to as the crop height. Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: nnpfc_purpose is configured to be set to indicate chroma format downsampling without changing the output picture size.

[0007] Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format or a 4:2:0 chroma format. Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: chroma format downsampling includes downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0008] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: nnpfc_purpose is configured to be set to indicate both output picture size downsampling and chroma format downsampling, wherein the output picture width is reduced relative to the input picture width, the output picture height is reduced relative to the input picture height, or both, and wherein the chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from a 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0009] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: nnpfc_purpose is configured to be set to indicate both output picture size downsampling and chroma format upsampling, wherein the output picture width is reduced relative to the input picture width, the output picture height is reduced relative to the input picture height, or both, and wherein the chroma format upsampling includes upsampling from a 4:2:0 chroma format to a 4:2:2 chroma format, upsampling from a 4:2:0 chroma format to a 4:4:4 chroma format, or upsampling from a 4:2:2 chroma format to a 4:4:4 chroma format.

[0010] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: nnpfc_purpose is configured to be set to indicate both output picture size upsampling and chroma format downsampling, wherein the output picture width is increased relative to the input picture width, the output picture height is increased relative to the input picture height, or both, and wherein the chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from a 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0011] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides that: the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 0, the value of nnpfc_purpose does not indicate the purpose of changing the chroma format, and wherein ChromaFormatIdc is equal to 0 indicates that the input chroma format is monochrome.

[0012] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides that: the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 1, the value of nnpfc_purpose does not indicate a purpose involving chroma format downsampling, and wherein ChromaFormatIdc is equal to 1 indicating that the input chroma format is a 4:2:0 chroma format.

[0013] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides that: the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 3, the value of nnpfc_purpose does not indicate a purpose involving chroma format upsampling, and wherein ChromaFormatIdc is equal to 3 indicating that the input chroma format is a 4:4:4 chroma format.

[0014] Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: the bitstream includes an indication to indicate that for purposes involving chroma format upsampling, the variable output chroma component block width (outSubWidthC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0015] Optionally, in any of the foregoing aspects, another implementation of the aspect provides that: the bitstream includes an indication to indicate that for purposes involving chroma format downsampling, the variable output chroma component block height (outSubHeightC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0016] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides that: the bitstream includes an indication to indicate the absolute increment of the width and the absolute increment of the height of the luminance sample array of the picture produced by applying a post-processing filter to the cropped decoded output picture for the purpose of changing the size of the output picture.

[0017] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides for using the encoded unsigned integer variable (ue(v)) syntax to specify the absolute increment of width and the absolute increment of height.

[0018] Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the value of the absolute increment of the width of the luma sample array should be in the range of 0 to the input and output picture width (CroppedWidth)*M-1 (including the endpoints), where M is an integer greater than 0. Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the value of M is equal to 15. Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the value of M is equal to 1, 3, 7, 15, 31, 63, 127 or 255.

[0019] Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of the absolute increment of the height of the luma sample array should be in the range of 0 to the input and output picture height (CroppedHeight)*N-1 (including the endpoints), where N is an integer greater than 0. Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of N is equal to 15. Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of N is 1, 3, 7, 15, 31, 63, 127 or 255.

[0020] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: for the purpose of upsampling the output picture size, the value of the width of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedWidth and the absolute increment of the width, and for the purpose of upsampling the output picture size, the value of the height of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedHeight and the absolute increment of the height.

[0021] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: for the purpose of downsampling the output picture size, the value of the width of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedWidth and the absolute increment of the width, and for the purpose of downsampling the output picture size, the value of the height of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedHeight and the absolute increment of the height.

[0022] Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that: the value of the width of the luma sample array and the value of the height of the luma sample array are both greater than zero. Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that: the value of the width of the luma sample array is greater than or equal to CroppedWidth / (M+1), where M is equal to 1, 3, 7, 15, 31, 63, 127, or 255. Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that: the value of the height of the luma sample array is greater than or equal to CroppedHeight / (N+1), where N is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

[0023] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: for purposes not involving changing the size of the output picture, the value of the width of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0024] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: the bitstream includes indications to indicate the increment of the width and the increment of the height of the luminance sample array of the picture produced by applying a post-processing filter to the cropped decoded output picture for the purpose of changing the size of the output picture.

[0025] Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the increment of width and the increment of height are specified using the unsigned integer variable (ue(v)) syntax of the codec. Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the increment of width is in the range of -CroppedWidth+width value (ValW) to CroppedWidth*M-1 (including the endpoints), where M is an integer greater than 0. Optionally, in any of the foregoing aspects, another implementation of this aspect specifies that the value of the width value (ValW) is 1.

[0026] Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that the value of the width value (ValW) is equal to CroppedWidth / (M+1). Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that the value of M is equal to 15. Optionally, in any of the foregoing aspects, another implementation of the aspect specifies that the value of M is 1, 3, 7, 15, 31, 63, 127, or 255.

[0027] Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the increment of height is in the range of -CroppedHeight+height value (ValH) to CroppedHeight*N-1 (including the endpoints), where N is an integer greater than 0. Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of the height value (ValH) is 1. Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of the height value (ValH) is equal to CroppedHeight / (N+1). Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of N is equal to 15. Optionally, in any of the aforementioned aspects, another implementation of this aspect specifies that the value of N is 1, 3, 7, 15, 31, 63, 127 or 255.

[0028] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: for purposes involving changing the size of the output picture, the value of the width of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the CroppedWidth and the increased value of the width, and for purposes involving changing the size of the output picture, the value of the height of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the CroppedHeight and the increased value of the height.

[0029] Optionally, in any of the aforementioned aspects, another implementation of the aspect provides that: for purposes not involving changing the size of the output picture, the value of the width of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the brightness sample array of the picture generated by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0030] Optionally, in any of the aforementioned aspects, another implementation of this aspect provides that: the conversion includes encoding the visual media data into a bitstream.

[0031] Optionally, in any of the preceding aspects, another implementation of this aspect provides that: the converting includes decoding the visual media data from a bitstream.

[0032] A second aspect relates to an apparatus for processing video data, comprising: a processor; and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform any of the aforementioned aspects.

[0033] A third aspect relates to a non-transitory computer-readable medium, comprising a computer program product for use by a video codec device, the computer program product comprising computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs the method of any of the aforementioned aspects.

[0034] A fourth aspect relates to a non-transitory computer-readable recording medium storing a bit stream of a video generated by a method performed by a video processing device, wherein the method includes any one of the disclosed methods.

[0035] A fifth aspect relates to a method for storing a bitstream of a video, comprising any one of the disclosed methods.

[0036] A sixth aspect relates to a method, device or system described in the present disclosure.

[0037] For clarity, any of the foregoing embodiments may be combined with one or more of the other foregoing embodiments to create new embodiments within the scope of the present disclosure.

[0038]

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

[0039] For a more complete understanding of the present disclosure, reference is now made to the following brief description taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0040] Figure 1 is an example illustration of a luma data channel with nnpfc_inp_order_idc equal to 3.

[0041] Figure 2 is a block diagram illustrating an exemplary video processing system.

[0042] Figure 3 is a block diagram of an exemplary video processing apparatus.

[0043] Figure 4 is a flow chart of an example method for video processing.

[0044] Figure 5 is a block diagram illustrating an exemplary video encoding and decoding system.

[0045] Figure 6 is a block diagram illustrating an exemplary encoder.

[0046] Figure 7 is a block diagram illustrating an exemplary decoder.

[0047] Figure 8is a schematic diagram of an exemplary encoder. DETAILED DESCRIPTION

[0048] First, it should be understood that although illustrative implementations 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 present disclosure should not be limited in any way to the exemplary implementations, drawings, and techniques shown below, including the exemplary designs and implementations shown and described herein, but may be modified within the full scope of the appended claims and their equivalents.

[0049] The section headings used in this disclosure are for ease of understanding and do not limit the applicability of the techniques and embodiments disclosed in each section to only that section. In addition, the use of H.266 terminology in some descriptions is only for ease of understanding and is not intended to limit the scope of the disclosed technology. Thus, the techniques described herein are also applicable to other video codec protocols and designs. In this disclosure, with respect to the Common Video Codec (VVC) specification and / or the Common Supplemental Enhancement Information (VSEI) standard, editorial changes to text are shown with bold italics indicating canceled text and with bold indicating added text.

[0050] 1. Preliminary Discussion

[0051] The present disclosure relates to image and / or video coding techniques. Specifically, the present disclosure relates to the definition and signaling of the purpose of downsampling capabilities of a neural network post-processing filter that is signaled in a video bitstream. The downsampling herein may be chroma format downsampling, for example, downsampling from a 4:4:4 chroma format to a 4:2:2 or 4:4:4 chroma format, or downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format. The downsampling herein may also be either or both of reducing picture width and reducing picture height. For video bitstreams encoded and decoded by any codec, such as the VVC standard and / or the general SEI message for the video bitstream for encoding and decoding (VSEI) standard, these examples may be applied individually or in various combinations.

[0052] 2. Abbreviations

[0053] Adaptation Parameter Set (APS), Access Unit (AU), Coded Layer Video Sequence (CLVS), Coded Layer Video Sequence Start (CLVSS), Cyclic Redundancy Check (CRC), Coded Video Sequence (CVS), Finite Impulse Response (FIR), Intra-frame Random Access Point (IRAP), Network Abstraction Layer (NAL), Picture Parameter Set (PPS), Picture Unit (PU), Random Access Skip Preamble (RASL), Supplemental Enhancement Information (SEI), Step-by-Step Temporal Sublayer Access (STSA), Video Codec Layer (VCL), Versatile Supplemental Enhancement Information (VSEI) as described in Rec. ITU-T H.274 | International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) 23002-7, Video Usability Information (VUI), Versatile Video Codec (VVC) as described in Rec. ITU-T H.266 | ISO / IEC 23090-3

[0054] 3. Further Discussion

[0055] 3.1 Video Codec Standards

[0056] Video codec standards have evolved primarily through the development of standards by the International Telecommunication Union (ITU) Telecommunication Standardization Sector (ITU-T) and ISO / International Electrotechnical Commission (IEC). ITU-T produced H.261 and H.263, ISO / IEC produced the Moving Picture Experts Group (MPEG-1) and MPEG-4 Vision, and the two organizations jointly produced the H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Codec (AVC) and H.265 / High Efficiency Video Codec (HEVC) [1] standards. Since H.262, video codec standards have been based on a hybrid video codec structure that utilizes temporal prediction plus transform coding. To explore future video codec technologies beyond HEVC, the Video Codec Experts Group (VCEG) and MPEG jointly established the Joint Video Exploration Team (JVET). JVET adopted many of the approaches and put them into a reference software called the Joint Exploration Model (JEM) [2]. When the Versatile Video Codec (VVC) project was officially launched, JVET was renamed the Joint Video Experts Team (JVET). VVC[3] is a codec standard that aims to reduce the bit rate by 50% compared to HEVC.

[0057] The Versatile Video Codec (VVC) standard (ITU-T H.266 | ISO / IEC 23090-3) [3][4] and the associated Versatile Supplementary Enhancement Information (VSEI) standard (ITU-T H.274 | ISO / IEC 23002-7) [4] are designed for the widest range of applications, including traditional uses (such as television broadcasting, video conferencing or playback from storage media), as well as newer and more advanced use cases such as adaptive bitrate streaming, video region extraction, composition and merging of content from multiple codecs’ video bitstreams, multi-view video, scalable layered codecs and viewport-adaptive 360° immersive media.

[0058] The Essential Video Codec (EVC) standard (ISO / IEC 23094-1) is another video codec standard developed by MPEG.

[0059] 3.2 General SEI Messages and SEI Messages in VVC and VSEI

[0060] SEI messages assist processes associated with decoding, display, or other purposes. However, the decoding process does not require SEI messages to construct luma or chroma samples. Conforming decoders do not need to process this information to achieve output order consistency. Some SEI messages are required to check bitstream consistency and output timing decoder consistency. Other SEI messages are not required to check bitstream consistency.

[0061] VVC Annex D specifies the syntax and semantics of the SEI message payload of some SEI messages and specifies the use of SEI messages and VUI parameters whose syntax and semantics are specified in ITU-T H.274 | ISO / IEC 23002-7.

[0062] 3.3 Signaling of Neural Network Post-Processing Filters

[0063] JVET-AA2006 [5] includes provisions for two SEI messages for signaling of neural network post-processing filters, as shown below.

[0064] 8.28 Neural Network Post-Processing Filter Characteristics SEI Message

[0065] 8.28.1 Neural Network Post-Processing Filter Characteristics SEI Message Syntax

[0066]

[0067]

[0068]

[0069] 8.28.2 Neural Network Post-Processing Filter Characteristics SEI Message Semantics

[0070] This SEI message specifies a neural network that can be used as a post-processing filter. The Activate by Neural Network Post-Processing Filter SEI message indicates the use of a specified post-processing filter for a particular picture.

[0071] The following variables need to be defined for use of this SEI message: – The width and height of the cropped decoded output picture in units of luma samples, denoted herein by CroppedWidth and CroppedHeight, respectively. – The luma sample array CroppedYPic[x][y], the chroma sample arrays CroppedCbPic[x][y], and CroppedCrPic[x][y] (if present) of the cropped decoded output picture for vertical coordinate y and horizontal coordinate x, where the coordinate y of the top left corner of the sample array is equal to 0 and x is equal to 0. – The bit depth BitDepthY of the luma sample array of the cropped decoded output picture. – The bit depth BitDepthC of the chroma sample arrays (if present) of the cropped decoded output picture. – The chroma format indicator, denoted herein by ChromaFormatIdc, as described in Section 7.3. – The quantized strength value StrengthControlVal when nnpfc_auxiliary_inp_idc is equal to 1.

[0072] When this SEI message specifies a neural network that can be used as a post-processing filter, the semantics specifies the derivation of the luma sample array FilteredYPic[x][y] and the chroma sample arrays FilteredCbPic[x][y] and FilteredCrPic[x][y] that comprise the output of the post-processing filter, as indicated by the value of nnpfc_out_order_idc. The variables SubWidthC and SubHeightC are derived from ChromaFormatIdc as specified in Table 2.

[0073] nnpfc_id contains an identification number that can be used to identify the post-processing filter. The value of nnpfc_id should be between 0 and 2. 32 -2 (inclusive). The value of nnpfc_id is from 256 to 511 (inclusive) and from 2 31 to 2 32 -2 (inclusive) is reserved for future use by ITU-T|ISO / IEC. The decoder will not respond if it encounters a value in the range of 256 to 511 (inclusive) or at 2 31 to 2 32nnpfc_mode_idc equal to 0 specifies that the post-processing filter associated with the nnpfc_id value is determined by external methods not specified in this specification. nnpfc_mode_idc equal to 1 specifies that the post-processing filter associated with the nnpfc_id value is a neural network represented by the ISO / IEC 15938-17 bitstream included in this SEI message.

[0074] nnpfc_mode_idc equal to 2 specifies that the post-processing filter associated with the nnpfc_id value is a neural network identified by the specified tag uniform resource identifier (URI) (nnpfc_uri_tag[i]) and the neural network information URI (nnpfc_uri[i]). The value of nnpfc_mode_idc shall be in the range of 0 to 255, inclusive. Values ​​of nnpfc_mode_idc greater than 2 are reserved for use by ITU-T|ISO / IEC future specifications and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages including the reserved value of nnpfc_mode_idc. nnpfc_purpose_and_formatting_flag equal to 0 specifies that there are no syntax elements related to filter purpose, input format, output format, and complexity. nnpfc_purpose_and_formatting_flag equal to 1 specifies that there are syntax elements related to filter purpose, input format, output format, and complexity. When nnpfc_mode_idc is equal to 1 and the current CLVS does not include the previous neural network post-processing filter characteristics SEI message in decoding order (whose nnpfc_id value is equal to the nnpfc_id value in this SEI message), nnpfc_purpose_and_formatting_flag shall be equal to 1.

[0075] When the current CLVS includes a previous neural network post-processing filter characteristics SEI message in decoding order (whose nnpfc_id value is equal to the nnpfc_id value in this SEI message), at least one of the following conditions shall apply: – The nnpfc_mode_idc of this SEI message is equal to 1 and the nnpfc_purpose_and_formatting_flag is equal to 0, so as to provide a neural network update. – The SEI message has the same content as the previous neural network post-processing filter characteristics SEI message. When this SEI message is the first neural network post-processing filter characteristics SEI message in decoding order (which has a specific nnpfc_id value within the current CLVS), it specifies the basic post-processing filters associated with the current decoded picture and all subsequent decoded pictures of the current layer in output order until the end of the current CLVS. When this SEI message is not the first neural network post-processing filter characteristics SEI message in decoding order (which has a specific nnpfc_id value within the current CLVS), this SEI message is relevant to the current decoded picture of the current layer in output order and all subsequent decoded pictures until the end of the current CLVS, or until the next neural network post-processing filter characteristics SEI message in output order within the current CLVS has a specific nnpfc_id value.

[0076] nnpfc_purpose indicates the purpose of the post-processing filter, as specified in Table 20. The value of nnpfc_purpose shall be between 0 and 2. 32 2 (inclusive). Values ​​of nnpfc_purpose not appearing in Table 20 are reserved for use by future ITU-T|ISO / IEC specifications and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages that include reserved values ​​for nnpfc_purpose.

[0077] Table 20 – Definition of nnpfc_purpose

[0078]

[0079] NOTE 1 – When the reserved value of nnpfc_purpose is used by ITU-T | ISO / IEC in the future, the syntax of this SEI message may be extended by syntax elements whose presence is conditional on nnpfc_purpose being equal to the reserved value.

[0080] When SubWidthC is equal to 1 and SubHeightC is equal to 1, nnpfc_purpose shall not be equal to 2 or 4. 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 nnpfc_out_sub_c_flag is not present, outSubWidthC is inferred to be equal to SubWidthC, and outSubHeightC is inferred to be equal to SubHeightC. If SubWidthC is equal to 2 and SubHeightC is equal to 1, nnpfc_out_sub_c_flag shall not be equal to 0.

[0081] nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specify the width and height, respectively, of the array of luma samples of the picture obtained by applying the post-processing filter identified by nnpfc_id to the cropped decoded output picture. When nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not present, they are inferred to be equal to CroppedWidth and CroppedHeight, respectively. nnpfc_component_last_flag equal to 0 specifies that the second dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor resulting from the post-processing filter is used for this channel. nnpfc_component_last_flag equal to 1 specifies that the last dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor resulting from the post-processing filter is used for this channel.

[0082] NOTE 2 – The first dimension in the input and output tensors is used for batch indexing, which is the practice in some neural network frameworks. Although the semantics of this SEI message uses a batch size equal to 1, it is up to the post-processing implementation to determine the batch size used as input for neural network inference. NOTE 3 – A color component is an example of a channel.

[0083] nnpfc_inp_format_flag indicates the method of converting the sample values ​​of the cropped decoded output picture into the input values ​​of the post-processing filter. When nnpfc_inp_format_flag is equal to 0, the input values ​​of the post-processing filter are real numbers, and the functions InpY and InpC are specified as follows:

[0084] InpY( x ) = x ÷ ( ( 1 << BitDepth Y ) - 1 ) (75)

[0085] InpC( x )= x ÷ ( ( 1 << BitDepth C ) - 1 ) (76)

[0086] When nnpfc_inp_format_flag is equal to 1, the input values ​​to the post-processing filter are unsigned integers, and the functions InpY and InpC are defined as follows:

[0087]

[0088] The variable inpTensorBitDepth is derived from the syntax element nnpfc_inp_tensor_bitdepth_minus8, which is defined as follows. nnpfc_inp_tensor_bitdepth_minus8 plus 8 specifies the bit depth of the luma sample values ​​in the input integer tensor. The value of inpTensorBitDepth is derived as follows:

[0089] inpTensorBitDepth=nnpfc_inp_tensor_bitdepth_minus8 + 8 (78)

[0090] Bitstream conformance requires that the value of nnpfc_inp_tensor_bitdepth_minus8 should be in the range of 0 to 24 (inclusive).

[0091] nnpfc_auxiliary_inp_idc not equal to 0 specifies that auxiliary input data is present in the input tensor of the neural network post-processing filter. nnpfc_auxiliary_inp_idc equal to 0 indicates that the auxiliary input data is not present in the input tensor. nnpfc_auxiliary_inp_idc equal to 1 specifies that the auxiliary input data is derived as specified in Table 23. The value of nnpfc_auxiliary_inp_idc shall be in the range of 0 to 255, inclusive. Values ​​of nnpfc_auxiliary_inp_idc greater than 1 are reserved for future specifications of ITU-T|ISO / IEC and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages that include reserved values ​​of nnpfc_auxiliary_inp_idc.

[0092] nnpfc_separate_colour_description_present_flag equal to 1 indicates that a different combination of primary colors, transfer characteristics, and matrix coefficients for the picture resulting from the post-processing filters is specified in the SEI message syntax structure. nnfpc_separate_colour_description_present_flag equal to 0 indicates that the combination of primary colors, transfer characteristics, and matrix coefficients for the picture resulting from the post-processing filters is the same as indicated in the VUI parameters of the CLVS.

[0093] nnpfc_colour_primaries has the same semantics as specified for the vui_colour_primaries syntax element in clause 7.3, with the following exceptions: – nnpfc_colour_primaries specifies the colour primaries of the picture resulting from the application of the neural network post-processing filters specified in the SEI message, rather than the colour primaries used for CLVS. – When nnpfc_colour_primaries is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_colour_primaries is inferred to be equal to vui_colour_primaries. nnpfc_transfer_characteristics has the same semantics as specified for the vui_transfer_characteristics syntax element in clause 7.3, with the following exceptions: – nnpfc_transfer_characteristics specifies the transfer characteristics of the picture resulting from the application of the neural network post-processing filters specified in the SEI message, rather than the transfer characteristics used for CLVS. – When nnpfc_transfer_characteristics is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_transfer_characteristics is inferred to be equal to vui_transfer_characteristics.

[0094] nnpfc_matrix_coeffs has the same semantics as specified for the vui_matrix_coeffs syntax element in clause 7.3, with the following exceptions: – nnpfc_matrix_coeffs specifies the matrix coefficients for the picture resulting from the application of the neural network post-processing filters specified in the SEI message, rather than the matrix coefficients for CLVS. – When nnpfc_matrix_coeffs is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. – The allowed values ​​of nnpfc_matrix_coeffs are not constrained by the chroma format of the decoded video picture, which is indicated by the ChromaFormatIdc value of the semantics of the VUI parameter. – When nnpfc_matrix_coeffs is equal to 0, nnpfc_out_order_idc shall not be equal to 1 or 3.

[0095] nnpfc_inp_order_idc indicates a method for ordering the sample array of the cropped decoded output picture as the input to the post-processing filter. Table 21 includes an information description of the nnpfc_inp_order_idc value. The semantics of nnpfc_inp_order_idc in the range of 0 to 3 (including endpoints) are specified in Table 23, which specifies the process for deriving the input tensor inputTensor for different nnpfc_inp_order_idc values ​​and for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft of the upper left corner sample position of the sample block included in the input tensor. When the chroma format of the cropped decoded output picture is not 4:2:0, nnpfc_inp_order_idc should not be equal to 3. The value of nnpfc_inp_order_idc should be in the range of 0 to 255 (including endpoints). Values ​​of nnpfc_inp_order_idc greater than 3 are reserved for future specification by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages including reserved values ​​of nnpfc_inp_order_idc.

[0096] Table 21 – Information description of nnpfc_inp_order_idc value

[0097]

[0098]

[0099] Figure 1 is an example graph for the luma data channel with nnpfc_inp_order_idc equal to 3 (informative).

[0100] A block is a rectangular array of samples from one component of a picture (e.g., luma or chroma components). nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any block size that is a positive integer multiple of the block size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. When nnpfc_constant_patch_size_flag is equal to 0, the block size width shall be less than or equal to CroppedWidth. When nnpfc_constant_patch_size_flag is equal to 0, the block size height shall be less than or equal to CroppedHeight. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the block size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1.

[0101] When nnpfc_constant_patch_size_flag is equal to 1, nnpfc_patch_width_minus1+1 specifies that the post-processing filter is the horizontal sample count of the block size required for the input. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_width_minus1+1) can be used as the horizontal sample count of the block size for the input to the post-processing filter. The value of nnpfc_patch_width_minus1 should be in the range of 0 to Min(32766, CroppedWidth-1) (including the endpoints). When nnpfc_constant_patch_size_flag is equal to 1, nnpfc_patch_height_minus1+1 specifies that the post-processing filter is the vertical sample count of the block size required for the input. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_height_minus1+1) can be used as the vertical sample count of the block size for the input to the post-processing filter. The value of nnpfc_patch_height_minus1 should be in the range of 0 to Min(32766, CroppedHeight-1), inclusive. nnpfc_overlap specifies the overlapping horizontal and vertical sample counts of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap should be in the range of 0 to 16383, inclusive.

[0102] The variables inpPatchWidth, inpPatchHeight, outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows:

[0103]

[0104]

[0105] Bitstream conformance requires that outPatchWidth*CroppedWidth shall be equal to nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight shall be equal to nnpfc_pic_height_in_luma_samples*inpPatchHeight. nnpfc_padding_type specifies the padding process when referencing sample positions outside the boundaries of a cropped decoded output picture, as shown in Table 22. The value of nnpfc_padding_type shall be in the range 0 to 15, inclusive.

[0106] Table 22 – Information description of nnpfc_padding_type values

[0107] nnpfc_padding_type describe 0 Zero padding 1 Copy Fill 2 Reflection Fill 3 Wrap-around filling 4 Fixed padding 5..15 reserve

[0108] nnpfc_luma_padding_val specifies the luma value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cb_padding_val specifies the Cb value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cr_padding_val specifies the Cr value used for padding when nnpfc_padding_type is equal to 4.

[0109] The function InpSampleVal(y,x,picHeight,picWidth,croppedPic) (whose input is the vertical sample point position y, the horizontal sample point position x, the picture height picHeight, the picture width picWidth and the sample point array croppedPic) returns the sampleVal value derived as follows:

[0110]

[0111]

[0112] Table 23 - Process for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft, which specifies the top left sample position of the block of samples included in the input tensor.

[0113]

[0114]

[0115]

[0116]

[0117] nnpfc_complexity_idc greater than 0 specifies that there may be one or more syntax elements indicating the complexity of the post-processing filters associated with nnpfc_id. nnpfc_complexity_idc equal to 0 specifies that there are no syntax elements indicating the complexity of the post-processing filters associated with nnpfc_id. The value of nnpfc_complexity_idc shall be in the range of 0 to 255, inclusive. Values ​​of nnpfc_complexity_idc greater than 1 are reserved for future specifications of ITU-T|ISO / IEC and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages that include reserved values ​​of nnpfc_complexity_idc.

[0118] nnpfc_out_format_flag equal to 0 indicates that the sample values ​​output by the post-processing filter are real numbers, and the functions OutY and OutC for converting the luma sample values ​​and chroma sample values ​​output by the post-processing filter to integer values ​​at bit depths BitDepthY and BitDepthC, respectively, are specified as follows:

[0119] OutY( x ) = Clip3( 0, ( 1 << BitDepth Y ) - 1, Round( x * ( ( 1 < <BitDepth Y ) - 1 ) ) ) (81)

[0120] OutC( x )= Clip3( 0, ( 1 << BitDepth C) - 1, Round( x * ( ( 1 < <BitDepth C ) - 1 ) ) ) (82)

[0121] nnpfc_out_format_flag equal to 1 indicates that the sample values ​​output by the post-processing filter are unsigned integers, and the functions OutY and OutC are defined as follows:

[0122]

[0123] The variable outTensorBitDepth is derived from the syntax element nnpfc_out_tensor_bitdepth_minus8 as described below. nnpfc_out_tensor_bitdepth_minus8 plus 8 specifies the bit depth of the sample values ​​in the output integer tensor. The value of outTensorBitDepth is derived as follows:

[0124] outTensorBitDepth = nnpfc_out_tensor_bitdepth_minus8 + 8 (84)

[0125] Bitstream conformance requires that the value of nnpfc_out_tensor_bitdepth_minus8 should be in the range of 0 to 24 (inclusive).

[0126] nnpfc_out_order_idc indicates the output order of samples due to the post-processing filter. Table 24 includes an information description of the nnpfc_out_order_idc value. The semantics of nnpfc_out_order_idc in the range of 0 to 3 (including the endpoints) are specified in Table 25, which specifies the process of deriving the sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for different values ​​of nnpfc_out_order_idc and a given vertical sample coordinate cTop and horizontal sample coordinate cLeft of the upper left corner sample position of the sample block included in the input tensor. When nnpfc_purpose is equal to 2 or 4, nnpfc_out_order_idc should not be equal to 3. The value of nnpfc_out_order_idc should be in the range of 0 to 255 (including the endpoints). Values ​​of nnpfc_out_order_idc greater than 3 are reserved by ITU-T|ISO / IEC for future specification and shall not be present in bitstreams conforming to versions of this specification. Decoders conforming to versions of this specification shall ignore SEI messages containing reserved values ​​of nnpfc_out_order_idc.

[0127] Table 24 – Information description of nnpfc_out_order_idc value

[0128]

[0129] Table 25 - Process for deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for different values ​​of a given vertical sample coordinate cTop and horizontal sample coordinate cLeft (which specifies the top left sample position of the sample block included in the input tensor)

[0130]

[0131]

[0132] The basic post-processing filters for the cropped decoded output picture picA are the filters identified by the first neural network post-processing filter characteristics SEI message having a particular nnpfc_id value within CLVS in decoding order.

[0133] If another neural network post-processing filter characteristics SEI message has the same nnpfc_id value, its nnpfc_mode_idc is equal to 1, its content is different from the neural network post-processing filter characteristics SEI message defining the basic post-processing filter, and belongs to the picture picA, then the basic post-processing filter is updated by decoding the ISO / IEC 15938-17 bitstream in the neural network post-processing filter characteristics SEI message to obtain the post-processing filter PostProcessingFilter(). Otherwise, the post-processing filter PostProcessingFilter() is assigned to be the same as the basic post-processing filter.

[0134] The process of filtering the cropped decoded output picture using the post-processing filter PostProcessingFilter() to generate a filtered picture is as follows. The picture includes Y, Cb, Cr sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic, respectively, as indicated by nnpfc_out_order_idc.

[0135]

[0136] nnpfc_reserved_zero_bit should be equal to 0.

[0137] nnpfc_uri_tag[i] contains a NULL-terminated UTF-8 string specifying a tag URI. The UTF-8 string contains a URI whose syntax and semantics are as specified in IETF RFC 4151, uniquely identifying the format and associated information of the neural network used as a post-processing filter specified in the nnrpf_uri[i] value. NOTE 4 – The nnrpf_uri_tag[i] element represents a 'tag' URI that allows the format of the neural network data specified by the nnrpf_uri[i] value to be uniquely identified without the need for a central registration authority. nnpfc_uri[i] contains a NULL-terminated UTF-8 string as specified in IETF Internet Standard 63. The UTF-8 string contains a URI whose syntax and semantics are as specified in IETF Internet Standard 66, identifying the neural network information (e.g., data representation) used as a post-processing filter. 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 current values ​​of i shall be a complete bit stream conforming to ISO / IEC 15938-17.

[0138] nnpfc_parameter_type_idc equal to 0 indicates that the neural network uses only integer parameters. nnpfc_parameter_type_flag equal to 1 indicates that the neural network can 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 specifications of ITU-T|ISO / IEC and should not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification should ignore SEI messages including the reserved value of nnpfc_parameter_type_idc. nnpfc_log2_parameter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters with bit lengths 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 with bit lengths greater than 1. nnpfc_num_parameters_idc indicates the maximum number of neural network parameters for the post-processing filter, in powers of 2048. nnpfc_num_parameters_idc equal to 0 indicates that the maximum number of neural network parameters is unspecified. The value of 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 specifications by ITU-T|ISO / IEC and shall not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification shall ignore SEI messages that include reserved values ​​of nnpfc_num_parameters_idc. If the value of nnpfc_num_parameters_idc is greater than zero, the variable maxNumParameters is derived as follows:

[0139] maxNumParameters = (2048 << nnpfc_num_parameters_idc) - 1 (86)

[0140] Bitstream conformance requires that the number of neural network parameters of the post-processing filter shall be less than or equal to maxNumParameters. nnpfc_num_kmac_operations_idc greater than 0 specifies that the maximum number of multiplication-accumulation operations per sample of the post-processing filter is less than or equal to nnpfc_num_kmac_operations_idc*1000. nnpfc_num_kmac_operations_idc equal to 0 specifies that the maximum number of multiplication-accumulation operations of the network is unspecified. The value of nnpfc_num_kmac_operations_idc shall be between 0 and 2. 32 -1 range (including the endpoints).

[0141] 8.29 Neural Network Post-Processing Filter Activation SEI Message

[0142] 8.29.1 Neural Network Post-Processing Filter Activation SEI Message Syntax

[0143]

[0144]

[0145] 8.29.2 Neural Network Post-Processing Filter Activation SEI Message Semantics

[0146] This SEI message specifies the neural network post-processing filters that can be used for post-processing filtering for the current picture. The neural network post-processing filter activation SEI message persists only for the current picture. NOTE - There may be several neural network post-processing filter activation SEI messages for the same picture, for example, when the post-processing filters are used for different purposes or filter different color components. The neural network post-processing filters specified by the nnpfa_id specify one or more neural network post-processing filter characteristics SEI message about the current picture and nnpfc_id is equal to nnfpa_id and can be used for post-processing filtering for the current picture.

[0147] 4. Technical problems solved by the disclosed technical solution

[0148] The example design of the Neural Network Post-Processing Filter Characteristic (NNPFC) SEI message has the following problems.

[0149] First, only some neural network post-processing filter purposes with upsampling capabilities are specified. However, in video applications, downsampling is often also employed, and like upsampling, downsampling using neural network filters can also provide better performance than using other methods. Therefore, there is a need to be able to signal neural network filters with downsampling capabilities.

[0150] Second, there is no provision for a neural network post-processing filter object with a combination of upsampling capability for output picture size and downsampling capability for chroma format (or vice versa).

[0151] 5. List of solutions and implementation examples

[0152] In order to solve the above problems, the methods summarized as follows are disclosed. The examples should be regarded as examples to explain the general concept and should not be interpreted narrowly. In addition, these examples can be applied individually or combined in any way.

[0153] Example 1

[0154] A solution to the first problem is now described. In one example, one or more of the following new purposes are defined. In one example, a purpose is defined for downsampling the chroma format without changing the output picture size, wherein the chroma format is changed from a 4:4:4 chroma format to a 4:2:2 or 4:4:4 chroma format, or from a 4:2:2 chroma format to a 4:2:0 chroma format. In one example, a purpose is defined for downsampling the output picture size without changing the chroma format, wherein either or both of the width and height of the cropped decoded output picture are reduced. In one example, a purpose is defined for downsampling the output picture size and downsampling the chroma format, wherein either or both of the width and height of the cropped decoded output picture are reduced, and the chroma format is changed from a 4:4:4 chroma format to a 4:2:2 or 4:4:4 chroma format, or from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0155] Example 2

[0156] A solution to the second problem is now described. In one example, one or more of the following new purposes are defined. In one example, a purpose is defined for downsampling the output picture size and upsampling the chroma format, wherein either or both of the width and height of the cropped decoded output picture are reduced, and the chroma format is changed from a 4:2:0 chroma format to a 4:2:2 or 4:4:4 chroma format, or from a 4:2:2 chroma format to a 4:4:4 chroma format. In one example, a purpose is defined for upsampling the output picture size and downsampling the chroma format, wherein either or both of the width and height of the cropped decoded output picture are increased, and the chroma format is changed from a 4:4:4 chroma format to a 4:2:2 or 4:4:4 chroma format, or from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0157] Example 3

[0158] Solutions to the first and second problems are now described. In one example, one or more of the following constraints are specified. When ChromaFormatIdc is equal to 0 (i.e., when the input chroma format is monochrome), the value of nnpfc_purpose should not indicate a purpose involving changing the chroma format. When ChromaFormatIdc is equal to 1 (i.e., when the input chroma format is 4:2:0), the value of nnpfc_purpose should not indicate a purpose involving downsampling of the chroma format. When ChromaFormatIdc is equal to 3 (i.e., when the input chroma format is 4:4:4), the value of nnpfc_purpose should not indicate a purpose involving upsampling of the chroma format.

[0159] Example 4

[0160] Solutions to the first and second problems are further described. In one example, for purposes involving chroma format upsampling, regardless of whether the output picture size changes, a variable outSubWidthC is derived to be equal to an indication of 2 or 1. For purposes involving chroma format downsampling, regardless of whether the output picture size changes, a variable outSubHeightC is derived to be equal to an indication of 2 or 1.

[0161] Example 5

[0162] Solutions to the first and second problems are further described.In one example, for purposes involving changing the output picture size, an absolute increment of the width and height of the luma sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture is signaled.

[0163] In one example, the values ​​of these increments are signaled using ue(v) coded syntax elements.

[0164] In one example, the value of the signaled width absolute increment is required to be in the range of 0 to CroppedWidth*M-1 (including the endpoints), where M is an integer greater than 0. In one example, the value of M is equal to 15. In one example, the value of M is equal to a different integer value greater than 0, for example, 1, 3, 7, 31, 63, 127, or 255.

[0165] In one example, the value of the height absolute increment signaled is required to be in the range of 0 to CroppedHeight*N-1 (including the endpoints), where N is an integer greater than 0. In one example, the value of N is equal to 15. In one example, the value of N is equal to a different integer value greater than 0, for example, 1, 3, 7, 31, 63, 127 or 255.

[0166] In one example, for purposes involving upsampling of the output picture size, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the input-output picture width, CroppedWidth, and the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the input-output picture height, CroppedHeight, and the value of the absolute increment of the signaled height.

[0167] In one example, for purposes involving downsampling of the output picture size, the value of the width of the luma sample array of the picture produced by applying a post-processing filter to the cropped decoded output picture is derived to be equal to the difference between the input-output picture width, CroppedWidth, and the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the difference between the input-output picture height, CroppedHeight, and the value of the absolute increment of the signaled height.

[0168] In one example, the width and height values ​​derived above are both required to be greater than 0. In addition, in one example, the width value derived above is required to be greater than or equal to CroppedWidth / (M+1), where M is equal to 1, 3, 7, 15, 31, 63, 127, or 255. In addition, in one example, the height value derived above is required to be greater than or equal to CroppedHeight / (N+1), where N is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

[0169] In one example, for purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the input-output picture width CroppedWidth, and the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the input-output picture height CroppedHeight.

[0170] Example 6

[0171] Solutions to the first and second problems are further described. In one example, for purposes involving changing the size of an output picture, whether the change is to become larger or smaller, an increment in the width and height of the array of luma samples of the picture produced by applying a post-processing filter to the cropped decoded output picture is signaled. Note that in this case, the increment can be positive and can also be negative.

[0172] In one example, the values ​​of these deltas are signaled using se(v) coded syntax elements.

[0173] In one example, the value of the increment of the width to be signaled is required to be in the range of -CroppedWidth+ValW to CroppedWidth*M-1 (including the endpoints), where M is an integer greater than 0. In one example, the value of ValW is equal to 1. In one example, the value of ValW is equal to CroppedWidth / (M+1). In one example, the value of M is equal to 15. In one example, the value of M is equal to a different integer value greater than 0, for example, 1, 3, 7, 31, 63, 127, or 255.

[0174] In one example, the value of the increment of the height to be signaled is required to be in the range of -CroppedHeight+ValH to CroppedHeight*N-1 (including the endpoints), where N is an integer greater than 0. In one example, the value of ValH is equal to 1. In one example, the value of ValH is equal to CroppedHeight / (N+1). In one example, the value of N is equal to 15. In one example, the value of N is equal to a different integer value greater than 0, for example, 1, 3, 7, 31, 63, 127, or 255.

[0175] In one example, for purposes involving changing the size of an output picture, the value of the width of the luma sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture is derived to be equal to the sum of the value of the input-output picture width, CroppedWidth, and the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the input-output picture height, CroppedHeight, and the value of the increment of the signaled height.

[0176] In one example, for purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the input-output picture width CroppedWidth, and the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the input-output picture height CroppedHeight.

[0177] 6. Examples

[0178] The following are some example embodiments of some of the disclosure items summarized in Examples 1 to 4 in Section 5 above.

[0179] Most relevant parts that have been added or modified are shown in bold, while some deleted parts are shown in italic bold. There may also be some other changes that are editorial in nature and therefore not highlighted.

[0180] 6.1 First Embodiment

[0181] This embodiment is directed to Examples 1 to 6 summarized in Section 5 above.

[0182] 8.28.1 Neural Network Post-Processing Filter Characteristics SEI Message Syntax

[0183]

[0184]

[0185] 8.28.2 Neural Network Post-Processing Filter Characteristics SEI Message Semantics

[0186] This SEI message specifies a neural network that can be used as a post-processing filter. The Activate with Neural Network Post-Processing Filter SEI message indicates the use of the specified post-processing filter for a particular picture. ...

[0188] nnpfc_purpose indicates the purpose of the post-processing filter as specified in Table 20. The value of nnpfc_purpose shall be in the range of 0 to 232-2, inclusive. Values ​​of nnpfc_purpose not appearing in Table 20 are reserved by ITU-T|ISO / IEC for future specification and shall not be present in the bitstream conforming to versions of this specification. Decoders conforming to versions of this specification shall ignore SEI messages containing reserved values ​​of nnpfc_purpose.

[0189] Table 20 – Definition of nnpfc_purpose

[0190]

[0191] NOTE 1 – When the reserved value of nnpfc_purpose is used by ITU-T | ISO / IEC in the future, the syntax of this SEI message may be extended with syntax elements whose presence is constrained by nnpfc_purpose being equal to this value.

[0192]

[0193]

[0194] nnpfc_component_last_flag equal to 0 specifies that the second dimension in the input tensor inputTensor of the post-processing filter and the output tensor outputTensor produced by the post-processing filter is used for this channel. nnpfc_component_last_flag equal to 1 specifies that the last dimension in the input tensor inputTensor of the post-processing filter and the output tensor outputTensor produced by the post-processing filter is used for this channel. ...

[0196] nnpfc_overlap specifies the overlapping horizontal and vertical sample counts of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap should be in the range of 0 to 16383 (inclusive).

[0197] The variables inpPatchWidth, inpPatchHeight, outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows:

[0198] inpPatchWidth=nnpfc_patch_width_minus1+1

[0199] inpPatchHeight=nnpfc_patch_height_minus1+1

[0200]

[0201] CroppedWidth

[0202]

[0203] horCScaling=SubWidthC / outSubWidthC

[0204] verCScaling=SubHeightC / outSubHeightC

[0205] outPatchCWidth=outPatchWidth*horCScaling

[0206] outPatchCHeight=outPatchHeight*verCScaling

[0207] overlapSize=nnpfc_overlap

[0208] Bitstream conformance requires that outPatchWidth*CroppedWidth should be equal to And outPatchHeight*CroppedHeight should be equal to ...

[0210] nnpfc_out_order_idc indicates the output order of samples due to the post-processing filter. Table 24 contains an information description of the nnpfc_out_order_idc value. The semantics of nnpfc_out_order_idc in the range of 0 to 3 (including the endpoints) are specified in Table 25, which specifies the process of deriving the sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for different values ​​of nnpfc_out_order_idc and the given vertical sample coordinates cTop and horizontal sample coordinates cLeft of the upper left corner sample position of the sample block included in the input tensor. When nnpfc_purpose is equal to 2 or 4, nnpfc_out_order_idc should not be equal to 3. The value of nnpfc_out_order_idc should be in the range of 0 to 255 (including the endpoints). Values ​​of nnpfc_out_order_idc greater than 3 are reserved by ITU-T|ISO / IEC for future specification and shall not be present in bitstreams conforming to versions of this specification. Decoders conforming to versions of this specification shall ignore SEI messages containing reserved values ​​of nnpfc_out_order_idc.

[0211] Table 24 – Information description of nnpfc_out_order_idc value

[0212]

[0213] Table 25 - Process of deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic and FilteredCrPic from the output tensor outputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft, which specify the top left sample position of the sample block included in the input tensor.

[0214]

[0215]

[0216]

[0217] The base post-processing filter for the cropped decoded output picture picA is the filter identified by the first neural network post-processing filter characteristics SEI message having a specific nnpfc_id value within CLVS in decoding order.

[0218] If another neural network post-processing filter characteristics SEI message has the same nnpfc_id value, its nnpfc_mode_idc is equal to 1, its content is different from the neural network post-processing filter characteristics SEI message defining the basic post-processing filter, and about the picture picA, the basic post-processing filter is updated by decoding the ISO / IEC15938-17 bitstream in the neural network post-processing filter characteristics SEI message to obtain the post-processing filter PostProcessingFilter(). Otherwise, the post-processing filter PostProcessingFilter() is designated as the same as the basic post-processing filter.

[0219] The following process is used to filter the cropped decoded output picture using a post-processing filter PostProcessingFilter() to generate a filtered picture, which contains Y, Cb, Cr sample arrays FilteredYPic, FilteredCbPic, FilteredCrPic, respectively, as indicated by nnpfc_out_order_idc.

[0220]

[0221]

[0222] 7. References

[0223] [1]ITU-T and ISO / IEC, "High efficiency video coding", Rec.ITU-T H.265|ISO / IEC 23008-2 (in force edition).

[0224] [2] J.Chen, E.Alshina, GJSullivan, J.-R.Ohm, J.Boyce, "Algorithmdescription of Joint Exploration Test Model 7(JEM7)," JVET-G1001, Aug.2017.

[0225] [3]Rec.ITU-T H.266|ISO / IEC 23090-3, "Versatile Video Coding", 2022.

[0226] [4]Rec.ITU-T Rec.H.274|ISO / IEC 23002-7, "Versatile SupplementalEnhancement Information Messages for Coded Video Bitstreams", 2022.

[0227] [5]S.McCarthy,T.Chujoh,M.Hannuksela,G.Sullivan,and Y.-K.Wang(editors),"Additional SEI messages for VSEI(Draft 2),"JVET output documentJVET-AA2006,publicly available online herein:https: / / www.jvet-experts.org / doc_end_user / current_document.php? id=11947.

[0228] Figure 2 4000 in which the various techniques disclosed herein may be implemented. Various embodiments may include some or all of the components of system 4000. System 4000 may include an input 4002 for receiving video content. The video content may be received in a raw or uncompressed format (e.g., 8-bit or 10-bit multi-component pixel values), or may be received in a compressed or encoded format. Input 4002 may represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interfaces include wired interfaces such as Ethernet, a passive optical network (PON), and wireless interfaces such as wireless fidelity (Wi-Fi) or a cellular interface.

[0229] System 4000 may include a codec component 4004, which may implement various encodings or encoding methods described in the present disclosure. Codec component 4004 may reduce the average bit rate of the video from input 4002 to the output of codec component 4004 to generate a codec representation of the video. Therefore, codec technology is sometimes referred to as video compression or video transcoding technology. The output of codec component 4004 may be stored or sent via a connected communication, as represented by component 4006. The stored or transmitted bitstream (or encoded) representation of the video received at input 4002 may be used by component 4008 to generate pixel values ​​or displayable video, and the generated pixel values ​​or displayable video are sent to display interface 4010. The process of generating user-visible video from bitstream representation is sometimes referred to as video decompression. In addition, although some video processing operations are referred to as "codec" operations or tools, it should be understood that the encoding tool or operation is used in the encoder, and the decoder will perform the corresponding decoding tool or operation of the inverse codec result.

[0230] Examples of peripheral bus interfaces or display interfaces may include Universal Serial Bus (USB) or High Definition Multimedia Interface (HDMI) or Display Port, etc. Examples of storage interfaces include Serial Advanced Technology Attachment (SATA), Peripheral Component Interconnect (PCI), Integrated Drive Electronics (IDE) interface, etc. The technology described in the present disclosure may be embodied in various electronic devices such as mobile phones, laptop computers, smart phones, or other devices capable of performing digital data processing and / or video display.

[0231] Figure 3 4106 is a block diagram of an example video processing device 4100. Device 4100 may be used to implement one or more methods described herein. Device 4100 may be embodied as a smart phone, a tablet computer, a computer, an Internet of Things (IoT) receiver, etc. Device 4100 may include one or more processors 4102, one or more memories 4104, and video processing circuitry 4106. Processor 4102 may be configured to implement one or more methods described in the present disclosure. Memory (memory) 4104 may be used to store data and code for implementing the methods and techniques described herein. Video processing circuitry 4106 may be used to implement some of the techniques described in the present disclosure in hardware circuitry. In some embodiments, video processing circuitry 4106 may be at least partially included in processor 4102, for example, a graphics coprocessor.

[0232] Figure 4 4200 is a flow chart of an example method 4200 for video processing. The method 4200 may be performed by, for example Figure 2 The codec component 4004, Figure 2 Codec component 4008 or Figure 3The method 4200 is implemented by the video processing device 4100. At block 4202, the method 4200 includes determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a supplemental enhancement information (SEI) message, wherein the nnpfc_purpose is configured to be set to include output picture size downsampling, and wherein at least one of the following: (1) the output picture width is not equal to the input picture width and (2) the output picture height is not equal to the input picture height. At block 4204, the method 4200 includes performing conversion between visual media data and a bitstream based on the nnpfc_purpose.

[0233] In one embodiment, the output picture width is less than the input picture width, wherein the output picture height is less than the input picture height, or both. In one embodiment, the input picture width is referred to as the crop width, and the input picture height is referred to as the crop height. In one embodiment, nnpfc_purpose is configured to be set to indicate chroma format downsampling without changing the output picture size.

[0234] In one embodiment, the chroma format downsampling comprises downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format or a 4:2:0 chroma format. In one embodiment, the chroma format downsampling comprises downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0235] In one embodiment, nnpfc_purpose is configured to be set to indicate both output picture size downsampling and chroma format downsampling, wherein the output picture width is reduced relative to the input picture width, the output picture height is reduced relative to the input picture height, or both, and wherein the chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from a 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0236] In one embodiment, nnpfc_purpose is configured to be set to indicate both output picture size downsampling and chroma format upsampling, wherein the output picture width is reduced relative to the input picture width, the output picture height is reduced relative to the input picture height, or both, and wherein the chroma format upsampling includes upsampling from a 4:2:0 chroma format to a 4:2:2 chroma format, upsampling from a 4:2:0 chroma format to a 4:4:4 chroma format, or upsampling from a 4:2:2 chroma format to a 4:4:4 chroma format.

[0237] In one embodiment, nnpfc_purpose is configured to be set to indicate both output picture size upsampling and chroma format downsampling, wherein the output picture width is increased relative to the input picture width, the output picture height is increased relative to the input picture height, or both, and wherein the chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from a 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

[0238] In one embodiment, the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 0, the value of nnpfc_purpose does not indicate a purpose related to changing the chroma format, and wherein ChromaFormatIdc equal to 0 indicates that the input chroma format is monochrome.

[0239] In one embodiment, the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 1, the value of nnpfc_purpose does not indicate a purpose related to chroma format downsampling, and wherein ChromaFormatIdc is equal to 1 indicates that the input chroma format is a 4:2:0 chroma format.

[0240] In one embodiment, the NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when ChromaFormatIdc is equal to 3, the value of nnpfc_purpose does not indicate a purpose related to chroma format upsampling, and wherein ChromaFormatIdc equal to 3 indicates that the input chroma format is a 4:4:4 chroma format.

[0241] In one embodiment, the bitstream includes an indication to indicate that for purposes involving chroma format upsampling, the variable output chroma component block width (outSubWidthC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0242] In one embodiment, the bitstream includes an indication to indicate that for purposes involving chroma format downsampling, the variable output chroma component block height (outSubHeightC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0243] In one embodiment, the bitstream includes indications to indicate absolute increments of width and height of the luma sample array of a picture resulting from applying a post-processing filter to a cropped decoded output picture for purposes involving resizing the output picture.

[0244] In one embodiment, the absolute increment of width and the absolute increment of height are specified using the unsigned integer variable (ue(v)) syntax of the codec.

[0245] In one embodiment, the value of the absolute increment of the width of the luma sample array shall be in the range of 0 to the input / output picture width (CroppedWidth)*M-1 (including the endpoints), where M is an integer greater than 0. In one embodiment, the value of M is equal to 15. In one embodiment, the value of M is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

[0246] In one embodiment, the value of the absolute increment of the height of the luma sample array should be in the range of 0 to the input and output picture height (CroppedHeight)*N-1 (including the endpoints), where N is an integer greater than 0. In one embodiment, the value of N is equal to 15. In one embodiment, the value of N is 1, 3, 7, 15, 31, 63, 127 or 255.

[0247] In one embodiment, for purposes involving upsampling of the output picture size, the value of the width of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedWidth and the absolute increment of the width, and for purposes involving upsampling of the output picture size, the value of the height of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedHeight and the absolute increment of the height.

[0248] In one embodiment, for purposes involving downsampling of the output picture size, the value of the width of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedWidth and the absolute increment of the width, and for purposes involving downsampling of the output picture size, the value of the height of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedHeight and the absolute increment of the height.

[0249] In one embodiment, the value of the width of the luma sample array and the value of the height of the luma sample array are both greater than zero. In one embodiment, the value of the width of the luma sample array is greater than or equal to CroppedWidth / (M+1), where M is equal to 1, 3, 7, 15, 31, 63, 127, or 255. In one embodiment, the value of the height of the luma sample array is greater than or equal to CroppedHeight / (N+1), where N is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

[0250] In one embodiment, for purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0251] In one embodiment, the bitstream includes indications to indicate increments to be made to the width and height of the luma sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture for purposes involving resizing the output picture.

[0252] In one embodiment, the increment of width and the increment of height are specified using the unsigned integer variable (ue(v)) syntax of the codec. In one embodiment, the increment of width is in the range of -CroppedWidth+width value (ValW) to CroppedWidth*M-1 (including the endpoints), where M is an integer greater than 0. In one embodiment, the value of width value (ValW) is 1.

[0253] In one embodiment, the value of the width value (ValW) is equal to CroppedWidth / (M+1). In one embodiment, the value of M is equal to 15. In one embodiment, the value of M is 1, 3, 7, 15, 31, 63, 127, or 255.

[0254] In one embodiment, the increment of height is in the range of -CroppedHeight+height value (ValH) to CroppedHeight*N-1 (including the endpoints), where N is an integer greater than 0. In one embodiment, the value of height value (ValH) is 1. In one embodiment, the value of height value (ValH) is equal to CroppedHeight / (N+1). In one embodiment, the value of N is equal to 15. In one embodiment, the value of N is 1, 3, 7, 15, 31, 63, 127, or 255.

[0255] In one embodiment, for purposes involving resizing the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedWidth and the value of the increment for the width, and for purposes involving resizing the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedHeight and the value of the increment for the height.

[0256] In one embodiment, for purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0257] In another embodiment, a method includes determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC SEI message. The nnpfc_purpose may be set to indicate chroma format downsampling without changing the output picture size by changing the chroma format. Conversion between visual media data and a bitstream is performed based on the nnpfc_purpose.

[0258] It should be noted that method 4200 may be implemented in an apparatus for processing video data, the apparatus including a processor and a non-transitory memory having instructions thereon, such as video encoder 4400, video decoder 4500, and / or encoder 4600. In this case, the instructions, when executed by the processor, cause the processor to perform method 4200. In addition, method 4200 may be performed by a non-transitory computer-readable medium including a computer program product for use by a video codec device. The computer program product includes computer executable instructions stored on a non-transitory computer-readable medium, such that when executed by a processor, the video codec device performs method 4200.

[0259] Figure 5 43 is a block diagram illustrating an example video codec system 4300 that can utilize the techniques of the present disclosure. The video codec system 4300 may include a source device 4310 and a target device 4320. The source device 4310 generates encoded video data, which may be referred to as a video codec device. The target device 4320 may decode the encoded video data generated by the source device 4310, which may be referred to as a video decoding device.

[0260] Source device 4310 may include video source 4312, video encoder 4314 and input / output (I / O) interface 4316. Video source 4312 may include, for example, a video capture device, an interface for receiving video data from a video content provider, and / or a source of a computer graphics system for generating video data, or a combination of such sources. Video data may include one or more pictures. Video encoder 4314 encodes video data from video source 4312 to generate a bitstream. The bitstream may include a series of bits that form a codec representation of video data. The bitstream may include codec pictures and associated data. Codec pictures are coded representations of pictures. 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 directly sent to target device 4320 via network 4330 via I / O interface 4316. The encoded video data may also be stored on storage medium / server 4340 for access by target device 4320.

[0261] Target device 4320 may include an I / O interface 4326, a video decoder 4324, and a display device 4322. The I / O interface 4326 may include a receiver and / or a modem. The I / O interface 4326 may obtain encoded video data from source device 4310 or storage medium / server 4340. The video decoder 4324 may decode the encoded video data. The display device 4322 may display the decoded video data to a user. The display device 4322 may be integrated with the target device 4320, or may be external to the target device 4320, which may be configured to interface with an external display device.

[0262] The video encoder 4314 and the video decoder 4324 may operate according to a video compression standard, such as the High Efficiency Video Codec (HEVC) standard, the Versatile Video Codec (VVM) standard, and other current and / or additional standards.

[0263] Figure 6 is a block diagram showing an example of a video encoder 4400, which may be Figure 5 Video encoder 4314 in system 4300 shown. Video encoder 4400 can be configured to perform any or all of the techniques of the present disclosure. Video encoder 4400 includes multiple functional components. The techniques described in the present disclosure can be shared between the various components of video encoder 4400. In some examples, the processor can be configured to perform any or all of the techniques described in the present disclosure.

[0264] The functional components of the video encoder 4400 may include a segmentation unit 4401, a prediction unit 4402 (which may include a mode selection unit 4403, a motion estimation unit 4404, a motion compensation unit 4405, an intra-frame 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 coding unit 4414.

[0265] In other examples, the video encoder 4400 may include more, fewer, or different functional components. In one example, the prediction unit 4402 may include an intra-block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode, where at least one reference picture is a picture in which the current video block is located.

[0266] Furthermore, some components, such as the motion estimation unit 4404 and the motion compensation unit 4405 , may be highly integrated but are represented separately in the example of the video encoder 4400 for explanation purposes.

[0267] The segmentation unit 4401 may segment the picture into one or more video blocks. The video encoder 4400 and the video decoder 4500 may support various video block sizes.

[0268] The mode selection unit 4403 may select one of the coding modes, for example, based on the error result, and provide the resulting intra-frame or inter-frame coded block to the residual generation unit 4407 to generate residual block data and provide it to the reconstruction unit 4412 to reconstruct the coded block for use as a reference picture. In some examples, the mode selection unit 4403 may select an intra-frame and inter-frame prediction (CIIP) mode combination, where the prediction is based on an inter-frame prediction signal and an intra-frame prediction signal. The mode selection unit 4403 may also select a resolution of motion vectors (e.g., sub-pixel or integer pixel precision) for the block in the case of inter-frame prediction.

[0269] To perform inter-frame prediction on the current video block, the motion estimation unit 4404 may generate motion information for the current video block by comparing one or more reference frames from the buffer 4413 with the current video block. The motion compensation unit 4405 may determine a predicted video block for the current video block based on the motion information and decoded samples of a picture from the buffer 4413 (not the picture associated with the current video block).

[0270] The motion estimation unit 4404 and the motion compensation unit 4405 may perform different operations on the current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice.

[0271] In some examples, the motion estimation unit 4404 may perform unidirectional prediction on the current video block, and the motion estimation unit 4404 may search for a reference video block for the current video block in the reference pictures of list 0 or list 1. The motion estimation unit 4404 may then generate a reference index indicating a reference picture in list 0 or list 1, the reference picture including the reference video block and a motion vector indicating a spatial displacement between the current video block and the reference video block. The motion estimation unit 4404 may output the reference index, the prediction direction indicator, and the motion vector as motion information of the current video block. The motion compensation unit 4405 may generate a predicted video block of the current block based on the reference video block indicated by the motion information of the current video block.

[0272] In other examples, the motion estimation unit 4404 may perform bidirectional prediction on the current video block, and the motion estimation unit 4404 may search for a reference video block of the current video block in the reference pictures in list 0, and may also search for another reference video block of the current video block in the reference pictures in list 1. Then, the motion estimation unit 4404 may generate a reference index indicating the reference pictures in list 0 and list 1, the reference pictures including the reference video block and the motion vector indicating the spatial displacement between the reference video block and the current video block. The motion estimation unit 4404 may output the reference index and the motion vector of the current video block as the motion information of the current video block. The motion compensation unit 4405 may generate a predicted video block of the current video block based on the reference video block indicated by the motion information of the current video block.

[0273] In some examples, motion estimation unit 4404 may output a complete set of motion information for use in a decoding process of a decoder. In some examples, motion estimation unit 4404 may not output a complete set of motion information for the current video. Rather, motion estimation unit 4404 may reference motion information of another video block to signal motion information of the current video block. For example, motion estimation unit 4404 may determine that motion information of the current video block is sufficiently similar to motion information of an adjacent video block.

[0274] In one example, the motion estimation unit 4404 may indicate a value in a syntax structure associated with the current video block that indicates to the video decoder 4500 that the current video block has the same motion information as another video block.

[0275] In another example, the motion estimation unit 4404 can identify another video block and a motion vector difference (MVD) in a syntax structure associated with the current video block. The motion vector difference indicates the difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 4500 can use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.

[0276] As described above, the video encoder 4400 may predictively signal motion vectors. Two examples of predictive signaling techniques that may be implemented by the video encoder 4400 include Advanced Motion Vector Prediction (AMVP) and merge mode signaling.

[0277] The intra prediction unit 4406 may perform intra prediction on the current video block. When the intra prediction unit 4406 performs intra prediction on the current video block, the 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 the predicted video block and various syntax elements.

[0278] The residual generating unit 4407 may generate residual data for the current video block by subtracting the predicted video block of the current video block from the current video block. The residual data of the current video block may include residual video blocks corresponding to different sample components of the samples in the current video block.

[0279] In other examples, such as in skip mode, there may be no residual data for the current video block of the current video block, and the residual generation unit 4407 may not perform a subtraction operation.

[0280] The 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 the residual video block associated with the current video block.

[0281] After the transform processing unit 4408 generates a transform coefficient video block associated with the current video block, the 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.

[0282] The inverse quantization unit 4410 and the inverse transform unit 4411 may apply inverse quantization and inverse transform to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 4412 may add the reconstructed residual video block to the corresponding samples of one or more prediction video blocks generated by the prediction unit 4402 to generate a reconstructed video block associated with the current block for storage in the buffer 4413.

[0283] After the reconstruction unit 4412 reconstructs the video block, a loop filtering operation may be performed to reduce video blocking effects in the video block.

[0284] The entropy coding unit 4414 may receive data from other functional components of the video encoder 4400. When the entropy coding unit 4414 receives data, the entropy coding unit 4414 may perform one or more entropy coding operations to generate entropy coded data and output a bitstream including the entropy coded data.

[0285] Figure 7 is a block diagram showing an example of a video decoder 4500, which may be Figure 5 Video decoder 4324 in the system 4300 shown. Video decoder 4500 can be configured to perform any or all of the techniques of the present disclosure. In the example shown, video decoder 4500 includes multiple functional components. The techniques described in the present disclosure can be shared between the components of video decoder 4500. In some examples, the processor can be configured to perform any or all of the techniques described in the present disclosure.

[0286] In the example shown, the 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 transform unit 4505, and a reconstruction unit 4506, a buffer 4507. In some examples, the video decoder 4500 can perform a decoding pass that generally corresponds to the encoding pass described with respect to the video encoder 4400.

[0287] The entropy decoding unit 4501 may retrieve an encoded bitstream. The encoded bitstream may include entropy-encoded video data (e.g., encoded video data blocks). The entropy decoding unit 4501 may decode the entropy-encoded video data, and the motion compensation unit 4502 may determine motion information based on the entropy-decoded video data, including motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 4502 may determine such information, for example, by performing AMVP and merge mode.

[0288] The motion compensation unit 4502 may generate a motion compensated block, possibly performing interpolation based on an interpolation filter. The identification of the interpolation filter used with sub-pixel precision may be included in a syntax element.

[0289] The motion compensation unit 4502 may calculate interpolation of sub-integer pixels of a reference block using an interpolation filter used by the video encoder 4400 during encoding of the video block. The motion compensation unit 4502 may determine the interpolation filter used by the video encoder 4400 according to received syntax information and use the interpolation filter to generate a prediction block.

[0290] The motion compensation unit 4502 can use some syntax information to determine the size of blocks used to encode frames and / or slices of the encoded video sequence, partitioning information describing how each macroblock of the pictures of the encoded video sequence is partitioned, a mode indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-frame codec block, and other information used to decode the encoded video sequence.

[0291] The intra prediction unit 4503 may form a prediction block from spatially adjacent blocks using, for example, an intra prediction mode received in a bitstream. The inverse quantization unit 4504 inversely quantizes, i.e., dequantizes, the video block coefficients provided in the bitstream and decoded and quantized by the entropy decoding unit 4501. The inverse transform unit 4505 applies an inverse transform.

[0292] The reconstruction unit 4506 may add the residual block to the corresponding prediction block generated by the motion compensation unit 4502 or the intra prediction unit 4503 to form a decoded block. If necessary, a deblocking filter may also be applied to filter the decoded block to remove block artifacts. The decoded video block is then stored in a buffer 4507, which provides reference blocks for subsequent motion compensation / intra prediction and also generates a decoded video for presentation on a display device.

[0293] Figure 8 4600 is a schematic diagram of an example encoder 4600. The encoder 4600 is suitable for implementing VVC technology. The encoder 4600 includes three 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 that uses a predefined filter, the SAO 4604 and the ALF 4606 utilize the original samples of the current picture to reduce the mean square error between the original samples and the reconstructed samples by adding an offset and applying a finite impulse response (FIR) filter, respectively, and using codec side information signaling to notify the offset and filter coefficients. The ALF 4606 is located at the last processing stage of each picture and can be regarded as a tool that attempts to capture and repair artifacts created by previous stages.

[0294] The encoder 4600 also includes an intra prediction component 4608 and a motion estimation / compensation (ME / MC) component 4610 configured to receive an input video. The intra prediction component 4608 is configured to perform intra prediction, while the ME / MC component 4610 is configured to perform inter prediction using a reference picture obtained from a reference picture buffer 4612. The residual block from the inter prediction or intra prediction is fed to the transform (T) component 4614 and the quantization (Q) component 4616 to generate quantized residual transform coefficients, which are fed to the entropy coding component 4618. The entropy coding component 4618 entropy encodes the prediction result and the quantized transform coefficients and sends them to a video decoder (not shown). The quantized component output from the quantization component 4616 can be fed to the inverse quantization (IQ) component 4620, the inverse transform component 4622, and the reconstruction (REC) component 4624. The REC component 4624 is capable of outputting images to the DF 4602 , SAO 4604 , and ALF 4606 for filtering before these pictures are stored in the reference picture buffer 4612 .

[0295] A list of solutions preferred by some examples is provided next.

[0296] The following solutions illustrate examples of the techniques discussed herein.

[0297] 1. A method for processing media data, comprising: determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC SEI message, wherein the nnpfc_purpose may be set to indicate chroma format downsampling without changing the output picture size by changing the chroma format. And performing conversion between visual media data and a bitstream based on the nnpfc_purpose.

[0298] 2. The method of solution 1, wherein the nnpfc_purpose can be set to indicate output picture size downsampling without changing the chroma format by reducing the width of the cropped decoded output picture, the height of the cropped decoded output picture, or both.

[0299] 3. A method as described in any of solutions 1 to 2, wherein the nnpfc_purpose can be set to indicate both output picture size downsampling and chroma format downsampling by reducing the width of the cropped decoded output picture, the height of the cropped decoded output picture, or both and changing the chroma format.

[0300] 4. A method as described in any of solutions 1 to 3, wherein the nnpfc_purpose can be set to indicate both output picture size downsampling and chroma format upsampling by reducing the width of the cropped decoded output picture, the height of the cropped decoded output picture, or both and changing the chroma format.

[0301] 5. A method as described in any of solutions 1 to 4, wherein the nnpfc_purpose can be set to indicate both output picture size upsampling and chroma format downsampling by increasing the width of the cropped decoded output picture, the height of the cropped decoded output picture, or both, and changing the chroma format.

[0302] 6. A method as described in any one of Solutions 1 to 5, wherein the NNPFC SEI message is constrained as follows: when ChromaFormatIdc is equal to 0, the value of nnpfc_purpose should not indicate a purpose involving changing the chroma format; when ChromaFormatIdc is equal to 1, the value of nnpfc_purpose should not indicate a purpose involving downsampling of the chroma format; and when ChromaFormatIdc is equal to 3, the value of nnpfc_purpose should not indicate a purpose involving upsampling of the chroma format.

[0303] 7. A method as described in any of solutions 1 to 5, wherein an indication is signaled in the bitstream to indicate that for purposes involving chroma format upsampling, a variable output chroma component block width (outSubWidthC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0304] 8. A method as described in any of Solutions 1 to 7, wherein an indication is signaled in the bitstream to indicate that for purposes involving chroma format downsampling, a variable output chroma component block height (outSubHeightC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

[0305] 9. A method as described in any of solutions 1 to 8, wherein an indication is signaled in the bitstream to indicate an absolute increment in width and an absolute increment in height of a luminance sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture for purposes involving changing the size of the output picture.

[0306] 10. A method as described in any one of Solutions 1 to 8, wherein the value of the absolute increment of the width should be in the range of 0 to the input-output picture width (CroppedWidth)*M-1 (including the endpoints), where M is an integer greater than 0.

[0307] 11. A method as described in any of solutions 1 to 10, wherein M is an integer value of 1, 3, 7, 15, 31, 63, 127 or 255.

[0308] 12. A method as described in any one of solutions 1 to 11, wherein the value of the absolute increment of the height should be in the range of 0 to the input-output picture height (CroppedHeight)*N-1 (including the endpoints), where N is an integer greater than 0.

[0309] 13. A method as described in any of solutions 1 to 12, wherein N is an integer value of 1, 3, 7, 15, 31, 63, 127 or 255.

[0310] 14. A method as described in any one of solutions 1 to 13, wherein, for the purpose of upsampling the output picture size, the value of the width of the luminance sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedWidth and the absolute increment of the width, and for the purpose of upsampling the output picture size, the value of the height of the luminance sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedHeight and the absolute increment of the height.

[0311] 15. A method as described in any one of solutions 1 to 13, wherein, for the purpose of downsampling the output picture size, the value of the width of the luminance sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedWidth and the absolute increment of the width, and, for the purpose of downsampling the output picture size, the value of the height of the luminance sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedHeight and the absolute increment of the height.

[0312] 16. A method as described in any one of solutions 1 to 15, wherein, for purposes not involving changing the size of the output picture, the value of the width of the brightness sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the brightness sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0313] 17. A method as described in any of solutions 1 to 16, wherein an indication is signaled in the bitstream to indicate an increment in the width and height of the luma sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture for purposes involving changing the size of the output picture.

[0314] 18. A method as described in any of Solutions 1 to 17, wherein the increment of the width is in the range of -CroppedWidth+width value (ValW) to CroppedWidth*M-1 (including endpoints), where M is an integer greater than 0.

[0315] 19. A method as described in any one of Solutions 1 to 17, wherein the increment of the height is in the range of -CroppedHeight+height value (ValH) to CroppedHeight*N-1 (including endpoints), where N is an integer greater than 0.

[0316] 20. A method as described in any one of solutions 1 to 19, wherein for the purpose of changing the size of the output picture, the value of the width of the brightness sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedWidth and the value of the increment of the width, and for the purpose of changing the size of the output picture, the value of the height of the brightness sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedHeight and the value of the increment of the height.

[0317] 21. A method as described in any one of solutions 1 to 20, wherein, for purposes not involving changing the size of the output picture, the value of the width of the brightness sample array of the picture produced by applying a post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the brightness sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

[0318] 22. A device for processing video data, comprising: a processor; and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform a method as described in any one of solutions 1 to 21.

[0319] 23. A non-transitory computer-readable medium, comprising a computer program product for use by a video codec device, the computer program product comprising computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs a method as described in any one of Solutions 1 to 21.

[0320] 24. A non-transitory computer-readable recording medium storing a bitstream of a video generated by a method performed by a video processing device, wherein the method comprises: determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC SEI message, wherein the nnpfc_purpose can be set to indicate chroma format downsampling without changing an output picture size by changing the chroma format; and generating a bitstream based on the determination.

[0321] 25. A method for storing a bitstream of a video, comprising: determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC SEI message, wherein the nnpfc_purpose can be set to indicate chroma format downsampling without changing an output picture size by changing the chroma format; generating a bitstream based on the determination; and storing the bitstream in a non-transitory computer-readable recording medium.

[0322] 26. A method, apparatus or system as described in the present disclosure.

[0323] In the solution described herein, an encoder can comply with the format rules by generating a codec representation according to the format rules. In the solution described herein, a decoder can parse syntax elements in the codec representation using the format rules and generate decoded video based on the presence and absence of syntax elements known according to the format rules.

[0324] In the present disclosure, the term "video processing" may refer to video encoding, video decoding, video compression, or video decompression. For example, a video compression algorithm may be applied during conversion from a pixel representation of a video to a corresponding bitstream representation (or vice versa). For example, the bitstream representation of a current video block may correspond to bits that are co-located or distributed at different locations in the bitstream, as defined by the syntax. For example, a macroblock may be encoded based on error residual values ​​from a transform and codec, and also encoded and decoded using bits in a header and other fields in the bitstream. In addition, during conversion, the decoder may parse the bitstream based on a determination, and it is known that some fields may or may not be present, as described in the above solution. Similarly, the encoder may determine whether to include certain syntax fields, and generate the codec representation accordingly by including or excluding the syntax fields in the codec representation.

[0325] The disclosed and other solutions, examples, embodiments, modules and functional operations described in the present disclosure may be implemented in digital electronic circuits or computer software, firmware or hardware or a combination of one or more thereof, which includes the structures disclosed in the present disclosure and their equivalents. The disclosed and other embodiments may 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 a data processing device or for controlling the operation of the data processing device. The computer-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a material composition that affects a machine-readable propagation signal, or a combination of one or more thereof. The term "data processing device" encompasses all devices, equipment and machines for processing data, including, for example, a programmable processor, a computer or multiple processors or computers. In addition to hardware, the device may also include code that creates an execution environment for the computer program in question, for example, code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more thereof. A propagation signal is an artificially generated signal, for example, a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information for transmission to a suitable receiver device.

[0326] A computer program (also referred to 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 any 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 may 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 portions of one or more modules, subroutines, or code). A computer program may be deployed to execute on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0327] The processes or logic flows described in the present disclosure may 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 may also be performed by, and the devices may also be implemented as, special purpose logic circuits (e.g., field programmable gate arrays (FPGAs) or application specific integrated circuits (ASICs)).

[0328] Processors suitable for executing computer programs include, for example, both general and special purpose microprocessors and any one or more processors of any kind of digital computer. Typically, the processor will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data, or be operatively coupled to receive data from one or more mass storage devices or transfer data to one or more mass storage devices or both. 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, for example, semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and compact disk read-only memory (CD ROM) and digital versatile disk read-only memory (DVD-ROM) disks. The processor and memory may be supplemented by or incorporated in dedicated logic circuits.

[0329] Although the present disclosure contains many details, these details should not be interpreted as limitations on the scope of any subject matter or content that may be claimed, but should be interpreted as descriptions of features of specific embodiments that may be specific to a particular technology. Certain features described in the context of separate embodiments in the present disclosure may also be implemented in combination in a single embodiment. Conversely, the individual features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any appropriate sub-combination. In addition, although the above may describe features as acting in certain combinations and even initially claiming protection, in some cases, one or more features from the claimed combination may be removed from the combination, and the claimed combination may involve a sub-combination or a deformation of a sub-combination.

[0330] Similarly, although operations are shown in a particular order in the figures, this should not be understood as requiring such operations to be performed in the particular order shown or in a sequential order or to perform all of the operations shown to achieve the desired results. In addition, the separation of various system components described in this disclosure should not be understood as requiring such separation in all embodiments.

[0331] Only a few implementations and examples are described, and other implementations, enhancements, and modifications may be made based on what is described and illustrated in this disclosure.

[0332] A first component is directly coupled to a second component when there are no intermediate components other than a line, trace, or another medium between the first and second components. A first component is indirectly coupled to a second component when there are intermediate components other than a line, trace, or another medium between the first and second components. The term "coupled" and variations thereof include direct coupling and indirect coupling. Unless otherwise specified, the use of the term "about" is meant to include a range of ±10% of the subsequent value.

[0333] Although several embodiments are provided in the present disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples are considered to be illustrative rather than restrictive, and are not intended to be limited to the details given herein. For example, various elements or components may be combined or integrated in another system, or certain features may be omitted or not implemented.

[0334] In addition, without departing from the scope of the present disclosure, the techniques, systems, subsystems and methods described and shown as discrete or separate in various embodiments may be combined or integrated with other systems, modules, techniques or methods. Other items shown or discussed as coupled may be directly connected, or may be indirectly coupled or communicated through some interface, device or intermediate component, whether electrically, mechanically or otherwise coupled or communicated. Other examples of changes, substitutions and alterations may be identified by those skilled in the art, and these changes, substitutions and alterations may be made without departing from the spirit and scope disclosed herein.

Claims

1. A method for processing media data, comprising: determining a value of a neural network post-processing filter characteristic (NNPFC) purpose (nnpfc_purpose) in a NNPFC supplemental enhancement information (SEI) message, wherein the nnpfc_purpose is configured to be set to include output picture size downsampling, and wherein at least one of: (1) the output picture width is not equal to the input picture width and (2) the output picture height is not equal to the input picture height; and Conversion between visual media data and bitstream is performed based on the nnpfc_purpose.

2. The method of claim 1, wherein: The output picture width is smaller than the input picture width, wherein the output picture height is smaller than the input picture height, or both.

3. The method according to any one of claims 1 to 2, wherein: The input picture width is referred to as the crop width, and the input picture height is referred to as the crop height.

4. The method according to any one of claims 1 to 3, wherein: The nnpfc_purpose is configured to be set to indicate chroma format downsampling without changing the output picture size.

5. The method of claim 4, wherein: The chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format or a 4:2:0 chroma format.

6. The method of claim 4, wherein: The chroma format downsampling includes downsampling from a 4:2:2 chroma format to a 4:2:0 chroma format.

7. The method according to any one of claims 1 to 6, wherein: The npfc_purpose is configured to be set to indicate both the output picture size downsampling and the chroma format downsampling, wherein the output image width is reduced relative to the input image width, the output image height is reduced relative to the input image height, or both, and The chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from the 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from the 4:2:2 chroma format to the 4:2:0 chroma format.

8. The method according to any one of claims 1 to 7, wherein: The npfc_purpose is configured to be set to indicate both the output picture size downsampling and the chroma format upsampling, wherein the output image width is reduced relative to the input image width, the output image height is reduced relative to the input image height, or both, and The chroma format upsampling includes upsampling from a 4:2:0 chroma format to a 4:2:2 chroma format, upsampling from the 4:2:0 chroma format to a 4:4:4 chroma format, or upsampling from the 4:2:2 chroma format to the 4:4:4 chroma format.

9. The method according to any one of claims 1 to 8, wherein: The nnpfc_purpose is configured to be set to indicate both output picture size upsampling and chroma format downsampling, wherein the output image width is increased relative to the input image width, the output image height is increased relative to the input image height, or both, and The chroma format downsampling includes downsampling from a 4:4:4 chroma format to a 4:2:2 chroma format, downsampling from the 4:4:4 chroma format to a 4:2:0 chroma format, or downsampling from the 4:2:2 chroma format to the 4:2:0 chroma format.

10. The method according to any one of claims 1 to 9, wherein: The NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when the ChromaFormatIdc is equal to 0, the value of the nnpfc_purpose does not indicate a purpose related to changing the chroma format, and wherein the ChromaFormatIdc is equal to 0 indicates that the input chroma format is monochrome.

11. The method according to any one of claims 1 to 9, wherein: The NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when the ChromaFormatIdc is equal to 1, the value of the nnpfc_purpose does not indicate a purpose related to chroma format downsampling, and wherein the ChromaFormatIdc is equal to 1 indicating that the input chroma format is a 4:2:0 chroma format.

12. The method according to any one of claims 1 to 9, wherein: The NNPFC SEI message includes a chroma format indicator (ChromaFormatIdc), wherein when the ChromaFormatIdc is equal to 3, the value of the nnpfc_purpose does not indicate a purpose related to chroma format upsampling, and wherein the ChromaFormatIdc is equal to 3 indicating that the input chroma format is a 4:4:4 chroma format.

13. The method according to any one of claims 1 to 12, wherein: The bitstream includes an indication that for purposes involving chroma format upsampling, a variable output chroma component block width (outSubWidthC) is derived to be equal to 2 or 1, regardless of whether the output picture size is changed.

14. The method according to any one of claims 1 to 12, wherein: The bitstream includes an indication that a variable output chroma component block height (outSubHeightC) is derived to be equal to 2 or 1 for purposes involving chroma format downsampling, regardless of whether the output picture size is changed.

15. The method according to any one of claims 1 to 14, wherein: The bitstream includes indications of an absolute increment of width and an absolute increment of height of a luma sample array of a picture resulting from applying a post-processing filter to a cropped decoded output picture for purposes involving resizing the output picture.

16. The method of claim 15, wherein: The absolute increment of the width and the absolute increment of the height are specified using the unsigned integer variable (ue(v)) syntax of the codec.

17. The method of claim 15, wherein: The value of the absolute increment of the width of the luma sample array should be in the range of 0 to the input and output picture width (CroppedWidth)*M-1, including the endpoints, where M is an integer greater than 0.

18. The method of claim 17, wherein: The value of M is equal to 15.

19. The method of claim 17, wherein: The value of M is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

20. The method of claim 15, wherein: The value of the absolute increment of the height of the luma sample array should be in the range of 0 to input / output picture height (CroppedHeight)*N-1, including endpoints, where N is an integer greater than 0.

21. The method of claim 20, wherein: The value of N is equal to 15.

22. The method of claim 20, wherein: The value of N is 1, 3, 7, 15, 31, 63, 127, or 255.

23. The method of any one of claims 1 to 22, wherein: For purposes involving upsampling of the output picture size, the value of the width of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedWidth and the absolute increment of the width, and for purposes involving upsampling of the output picture size, the value of the height of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the CroppedHeight and the absolute increment of the height.

24. The method of any one of claims 1 to 22, wherein: For purposes involving downsampling of the output picture size, the value of the width of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the absolute increment of the width, and for purposes involving downsampling of the output picture size, the value of the height of the luma sample array of the picture resulting from applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of the absolute increment of the height.

25. The method of any one of claims 23 to 24, wherein: The value of the width of the luma sample array and the value of the height of the luma sample array are both greater than zero.

26. The method of any one of claims 23 to 24, wherein: The value of the width of the luma sample array is greater than or equal to the CroppedWidth / (M+1), where M is equal to 1, 3, 7, 15, 31, 63, 127, or 255.

27. The method of any one of claims 23 to 24, wherein: The value of the width of the luma sample array is greater than or equal to the CroppedHeight / (N+1), where N is equal to 1, 3, 7, 15, 31, 63, 127 or 255.

28. The method of any one of claims 1 to 22, wherein: For purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

29. The method of any one of claims 1 to 28, wherein: The bitstream includes indications to indicate an increment in width and an increment in height of a luma sample array of a picture produced by applying a post-processing filter to a cropped decoded output picture for purposes related to resizing the output picture.

30. The method of claim 29, wherein: The increment of the width and the increment of the height are specified using the unsigned integer variable (ue(v)) syntax of the codec.

31. The method of claim 29, wherein: The width increment is in the range of -CroppedWidth+width value (ValW) to CroppedWidth*M-1, including the endpoints, where M is an integer greater than 0.

32. The method of claim 31, wherein: The value of the width value (ValW) is 1.

33. The method of claim 31, wherein: The value of the width value (ValW) is equal to CroppedWidth / (M+1).

34. The method of claim 31, wherein: The value of M is equal to 15.

35. The method of claim 31, wherein: The value of M is 1, 3, 7, 15, 31, 63, 127, or 255.

36. The method of claim 29, wherein: The increment of the height is in the range of -CroppedHeight+height value (ValH) to CroppedHeight*N-1, including the endpoints, where N is an integer greater than 0.

37. The method of claim 36, wherein the width value (ValW) has a value of 1.

38. The method of claim 36, wherein the value of the width value (ValW) is equal to CroppedWidth / (M+1).

39. The method of claim 36, wherein the value of M is equal to 15.

40. The method of claim 36, wherein the value of M is 1, 3, 7, 15, 31, 63, 127 or 255.

41. The method of any one of claims 1 to 22, wherein: For purposes involving resizing the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedWidth and the value of the increment to the width, and for purposes involving resizing the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to the sum of the value of CroppedHeight and the value of the increment to the height.

42. The method of any one of claims 1 to 22, wherein: For purposes not involving changing the size of the output picture, the value of the width of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedWidth, and for purposes not involving changing the size of the output picture, the value of the height of the luma sample array of the picture produced by applying the post-processing filter to the cropped decoded output picture is derived to be equal to CroppedHeight.

43. The method of any one of claims 1 to 42, wherein the converting comprises encoding the visual media data into the bitstream.

44. The method of any one of claims 1 to 42, wherein the converting comprises decoding the visual media data from the bitstream.

45. An apparatus for processing media data, comprising: processor; and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method of any one of claims 1 to 44.

46. ​​A non-transitory computer-readable medium, comprising a computer program product for use by a video codec device, the computer program product comprising computer executable instructions stored on the non-transitory computer-readable medium, so that when executed by a processor, the video codec device performs the method as described in any one of claims 1 to 44.

47. A non-transitory computer-readable recording medium storing a bit stream of a video generated by a method performed by a video processing device, wherein the method comprises the method according to any one of claims 1 to 44.

48. A method of storing a bitstream of a video, comprising the method of any one of claims 1 to 44.

49. A method, apparatus or system as described in the present disclosure.

Images