Neural-network post-filter characteristics SEI message and the neural-network post-filter activation SEI message

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network post-filter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0. A conversion is performed between a visual media data and a bitstream based on the NNPFC SEI message.

Description

P24092472301WO3; G25N21009W (4824-71003)On The Neural-Network Post-Filter Characteristics SEI Message And The Neural-Network Post-Filter Activation SEI MessageCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This patent application claims the benefit of U.S. Provisional Patent Application No. 63 / 701.204 filed on September 30, 2024, which is hereby incorporated by reference in its entirety.TECHNICAL FIELD

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

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

[0004] A first aspect relates to a method for processing media data comprising: determining that rmpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network post-filter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0: and performing a conversion between a visual media data and a bitstream based on the NNPF.

[0005] Optionally, in any of the preceding aspects, another implementation of the aspect provides determining that nnpfc_absent_input_pic_zero_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the candidate input picture list to be represented by an input picture inputPicB that is the closest to the input picture inputPicA in output order and is present in the candidate input picture list.

[0006] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the candidate input picture list is designated CandlnputPicList.

[0007] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the candidate input picture list is based on a processing stage index and is designated CandInputPicList[ SeiProcStgldx ].

[0008] Optionally, in any of the preceding aspects, another implementation of the aspect provides that nnpfc_absent_input_pic_zero_flag is included in a NNPF supplemental enhancement information (SEI) message.

[0009] Optionally , in any of the preceding aspects, another implementation of the aspect provides that nnpfc_absent_input_pic_zero_flag is indicated in the bitstream using a one-bit unsigned fixed length integer (u(D).

[0010] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the conversion includes encoding the visual media data into the bitstream.P24092472301WO3; G25N21009W (4824-71003)

[0011] Optionally, in any of the preceding aspects, another implementation of the aspect provides that the conversion includes decoding the visual media data from the bitstream.

[0012] A second aspect relates to an apparatus for processing video data comprising: a processor; and a non- transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of the disclosed aspects.

[0013] A third aspect relates to a non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of the disclosed aspects.

[0014] A fourth aspect relates to a non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network postfilter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0; and generating a bitstream based on the determining.

[0015] A fifth aspect relates to a method for storing bitstream of a video, comprising: determining that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network post-filter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0; generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

[0016] A sixth aspect relates to a method, apparatus, or system described in the present disclosure.

[0017] For the purpose of clarity, any one of the foregoing embodiments may be combined with any one or more of the other foregoing embodiments to create a new embodiment within the scope of the present disclosure.

[0018] These and other features will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings and claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0019] For a more complete understanding of this disclosure, reference is now made to the following brief description, taken in connection with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0020] FIG. 1 is an example mechanism for deriving the four luma channels (right) from the luma component (left) when nnpfe inp order ide is equal to 3.

[0021] FIG. 2 is a block diagram showing an example video processing system.

[0022] FIG. 3 is a block diagram of an example video processing apparatus.

[0023] FIG. 4 is a flowchart for an example method of video processing.

[0024] FIG. 5 is a block diagram that illustrates an example video coding system.

[0025] FIG. 6 is a block diagram that illustrates an example encoder.P24092472301WO3; G25N21009W (4824-71003)

[0026] FIG. 7 is a block diagram that illustrates an example decoder.

[0027] FIG. 8 is a schematic diagram of an example encoder.DETAILED DESCRIPTION

[0028] It should be understood at the outset that although an illustrative implementation of one or more embodiments are provided below, the disclosed systems and / or methods may be implemented using any number of techniques, whether currently known or yet to be developed. The disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary designs and implementations illustrated and described herein, but may be modified within the scope of the appended claims along with their full scope of equivalents.

[0029] Section headings are used in the present disclosure for ease of understanding and do not limit the applicability of techniques and embodiments disclosed in each section only to that section. Furthermore, H.266 terminology is used in some description only for ease of understanding and not for limiting scope of the disclosed techniques. As such, the techniques described herein are applicable to other video codec protocols and designs also. In the present disclosure, editing changes are shown with respect to the Versatile Video Coding (WC) specification and / or the supplemental enhancement information (SEI) messages for coded video bitstreams (VSEI) standard.1. Initial discussion

[0030] This disclosure is related to image / video coding technologies. Specifically, this disclosure is related to specifying the neural-network post-filter characteristics (NNPFC) SEI message and the neural-network postfilter activation (NNPFA) SEI message. The ideas may be applied individually or in various combinations, for video bitstreams coded by any codec, e.g., the WC standard and / or the versatile SEI messages for coded video bitstreams (VSEI) standard.2. Further discussion2.1 Video coding standards

[0031] Video coding standards have evolved primarily through the development of International Telecommunication Union (ITU) telecommunication standardization sector (ITU-T) and International Organization for Standardization (ISO) / International Electrotechnical Commission (IEC) standards. The ITU-T produced H.261 and H.263, ISO / IEC produced motion picture experts group (MPEG)-l and MPEG-4 Visual, and the two organizations jointly produced the H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Coding (AVC) and H.265 / high efficiency video coding (HEVC) [1] standards. Since H.262, the video coding standards are based on the hybrid video coding structure wherein temporal prediction plus transform coding are utilized. The Versatile Video Coding (WC) standard (ITU-T H.266 | ISO / IEC 23090-3) [2] and the associated Versatile Supplemental Enhancement Information for coded video bitstreams (VSEI) standard (ITU-T H.274 | ISO / IEC 23002-7) [3] are designed for use in a maximally broad range of applications, including both the simple uses such as television broadcast, video conferencing, or playback from storage media, and also more advancedP24092472301WO3; G25N21009W (4824-71003) use cases such as adaptive bit rate streaming, video region extraction, composition and merging of content from multiple coded video bitstreams, multiview video, scalable layered coding, and viewport-adaptive three hundred sixty degree (360°) immersive media.2.2 SEI messages in general and in VVC

[0032] SEI messages assist in processes related to decoding, display or other purposes. However, SEI messages are not required for constructing the luma or chroma samples by the decoding process. Conforming decoders are not required to process this information for output order conformance. Some SEI messages are required for checking bitstream conformance and for output timing decoder conformance. Other SEI messages are not required for check bitstream conformance.

[0033] Annex D of WC specifies syntax and semantics for SEI message payloads for some SEI messages, and specifies the use of the SEI messages and VUI parameters for which the syntax and semantics are specified in ITU-T H.SEI | ISO / IEC 23002-7.2.3 The neural-network post-filter characteristics (NNPFC) SEI message and the neural-network postfilter activation (NNPFA) SEI message

[0034] JVET-AI2006 [4] and version 3 of the VSEI standard [3] include the specifications of the neural- network post-filter characteristics (NNPFC) SEI message and the neural-network post-filter activation (NNPFA) SEI message, as well as the general post-processing filtering process using neural-network post-processing filters (NNPFs), as follows.8.28.1 General post-processing filtering process using NNPFs8.28.1.1 General

[0035] Input to this process is a bitstream BitstreamToFilter. Output of this process is a list of NNPF output pictures ListNnpfOutputPics.

[0036] First, BitstreamToFilter is decoded, and the list CroppedDecodedPictures is set to be the list of the cropped decoded pictures in output order resulted from decoding BitstreamToFilter.

[0037] Second, the filtering process for one picture, as specified in clause 8.28.1.2, is repeatedly invoked, in output order, for each cropped decoded picture that is in CroppedDecodedPictures and for which one or more NNPFs are activated.

[0038] The order of the pictures in ListNnpfOutputPics is in output order.

[0039] Within ListNnpfOutputPics there shall be no more than one picture pertaining to any particular output time instance. When for any particular picture in CroppedDecodedPictures there are multiple NNPFs activated and only one of the NNPFs is allowed to be chosen to be applied although any of the NNPFs may be chosen, the above constraint shall apply regardless of w hich NNPF is chosen to be applied to the particular picture.

[0040] For any particular pair of pictures inputPicA and inputPicB consecutive in output order in CroppedDecodedPictures, when there are one or more pictures intermediatePicSetA in ListNnpfOutputPics betw een inputPicA and inputPicB in output order, one and only one of the following shall apply:P24092472301WO3; G25N21009W (4824-71003)The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with PictureRateUpsamplingFlag equal to 1 when a particular picture currPicA in CroppedDecodedPictures was the current picture.The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with TemporalExtrapolationFlag equal to 1 when a particular picture currPicA in CroppedDecodedPictures was the current picture.

[0041] The application of any other NNPF that was used in the fdtering process for one picture when currPicA was the current picture or the application of any NNPF (including nnpfA) that was used in the fdtering process for one picture when any other picture currPicB in CroppedDecodedPictures was the current picture shall not output any picture between the inputPicA and inputPicB in output order.

[0042] NOTE - The intent of the constraints expressed in the above paragraph is to disallow generating NNPF output pictures between any particular pair of consecutive input pictures more than once.8.28.1.2 Filtering process for one picture using an NNPF

[0043] The filtering process specified in this clause applies to each cropped decoded picture, referred to as the current picture, that is in CroppedDecodedPictures and for which one or more NNPFs are activated.

[0044] When applying an NNPF to the current picture, the following applies:The filtered and / or interpolated pictures are generated by the NNPF by applying the NNPF process specified in the semantics of the NNPFC SEI message, in a patch-wise maimer, to the current picture.The order of the pictures generated by the NNPF by applying the NNPF process being stored into the output tensor of the NNPF is in output order.

[0045] When the applied NNPF is the last NNPF that is applied to the current picture, the pictures generated by the NNPF and output by the NNPF process are included into ListNnpfOutputPics, in the same order as when the pictures are stored into the output tensor of the NNPF.8.28.2 Neural-network post-filter characteristics SEI message8.28.2.1 Neural-network post-filter characteristics SEI message syntaxP24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)8.28.2.2 Neural-network post-filter characteristics SEI message semantics

[0046] The neural-network post-filter characteristics (NNPFC) SEI message specifies a neural network that may be used as a post-processing filter. The use of specified neural-network post-processing filters (NNPFs) for specific pictures is indicated with neural-network post-filter activation (NNPFA) SEI messages.

[0047] Use of this SEI message requires the definition of the following variables:Input picture width and height in units of luma samples, denoted herein by CroppedWidth and CroppedHeight, respectively.Luma sample array CroppcdYPicf idx ] and chroma sample arrays CroppcdCbPic[ idx ] and CroppedCrPic[ idx ], when present, of the input pictures with index idx in the range of 0 to numlnputPics - 1 , inclusive, that are used as input for the NNPF.- Bit depth BitDepthY for the luma sample array of the input pictures.Bit depth BitDepthC for the chroma sample arrays, if any, of the input pictures.- A chroma format indicator, denoted herein by ChromaFormatldc, as described in clause 7.3.P24092472301WO3; G25N21009W (4824-71003)- When nnpfc auxiliary inp idc is equal to 1, a filtering strength control value array StrengthControlVal[ idx ] that shall contain real numbers in the range of 0 to 1, inclusive, of the input pictures with index idx in the range of 0 to numlnputPics - 1, inclusive.

[0048] Input picture with index 0 corresponds to the picture for which the NNPF defined by this NNPFC SEI message is activated by an NNPFA SEI message. Input picture with index i in the range of 1 to numlnputPics - 1, inclusive, precedes the input picture with index i - 1 in output order.

[0049] The variables SubWidthC and SubHeightC are derived from Chroma Format Ide .

[0050] NOTE 1 - More than one NNPFC SEI message can be present for the same picture. When more than one NNPFC SEI message with different values of nnpfe id is present or activated for the same picture, they can have the same value or different values of nnpfc_purpose and the same value or different values of nnpfc mode idc.

[0051] nnpfc_purpose indicates the purpose of the NNPF as specified in Table 1. where ( nnpfc_purpose & bitMask ) not equal to 0 indicates that the NNPF has the purpose associated with the bitMask value in Table 1. When nnpfc_purpose is greater than 0 and ( nnpfc_purpose & bitMask ) is equal to 0, the purpose associated with the bitMask value is not applicable to the NNPF. When nnpfc_pupose is equal to 0, the NNPF may be used as determined by the application and as specified by the nnpfc_application_purpose_tag_uri.

[0052] All NNPFC SEI messages with a particular value of nnpfe id within a CLVS shall have the same value of nnpfc purposc.

[0053] The value of nnpfc purposc shall be in the range of 0 to 255, inclusive, in bitstreams conforming to this version of this Specification. Values of 256 to 65,535, inclusive, for nnpfc_purpose are reserved for future use 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 NNPFC SEI messages with nnpfc_purpose in the range of 256 to 65.535, inclusive.Table 1 - Definition of nnpfc purposeP24092472301WO3; G25N21009W (4824-71003)

[0054] The variables ChromaUpsamplingFlag, ResolutionResamplingFlag, PictureRateUpsamplingFlag, BitDepthUpsamplingFlag, ColourizationFlag, and TemporalExtrapolationFlag, specifying whether nnpfc purpose indicates the purpose of the NNPF to include chroma upsampling, resolution resampling, picture rate upsampling, bit depth upsampling, colourization, and temporal extrapolation, respectively, are derived as follows:ChromaUpsamplingFlag = ( ( nnpfc _purpose & 0x02 ) > 0 ) ? 1 : 0ResolutionResamplingFlag = ( ( nnpfc_purpose & 0x04 ) > 0 ) ? 1 : 0PictureRateUpsamplingFlag = ( ( nnpfc_purpose & 0x08 ) > 0 ) ? 1 : 0 (75)BitDepthUpsamplingFlag = ( ( nnpfc_purpose & 0x10 ) > 0 ) ? 1 : 0ColourizationFlag = ( ( nnpfc_purpose & 0x20 ) > 0 ) ? 1 : 0TemporalExtrapolationFlag = ( ( nnpfc_purpose & 0x40 ) > 0 ) ? 1 : 0SpatialExtrapolationFlag = ( ( nnpfc_purpose & 0x80 ) > 0 ) ? 1 : 0

[0055] NOTE 2 -When a reserved value of nnpfc_purpose is taken into use in the future by ITU-T | ISO / IEC, the syntax of this SEI message could be extended with syntax elements whose presence is conditioned by nnpfc_purpose being equal to that value or any one of a set of values including that value.

[0056] When ChromaFormatldc is equal to 3, ChromaUpsamplingFlag shall be equal to 0.

[0057] When ChroniaUpsamplingFlag is equal to 1, ColourizationFlag shall be equal to 0.

[0058] When PictureRateUpsamplingFlag or TemporalExtrapolationFlag is equal to 1 and the input picture with index 0 is associated with a frame packing arrangement SEI message with fp arrangement type equal to 5, all input pictures are associated with a frame packing arrangement SEI message with fp_arrangcment_typc equal to 5 and the same value of fp current frame is frameO flag.

[0059] When TemporalExtrapolationFlag is equal to 1, the extrapolated pictures generated by the NNPF follow all input pictures of the NNPF in output order. When TemporalExtrapolationFlag is equal to 1 and there is a decoded output picture that follows, in output order, the current picture for which the NNPF is activated, the extrapolated pictures generated by the NNPF precede that decoded output picture in output order.

[0060] nnpfc id contains an identifying number that may be used to identify an NNPF. The value of nnpfc id shall be in the range of 0 to 212- 2, inclusive. Values of nnpfc id from 256 to 511, inclusive, and from 231to 232- 2, inclusive, are reserved for future use by ITU-T | ISO / IEC. Decoders conforming to this version of this Specification encountering an NNPFC SEI message with nnpfc id in the range of 256 to 511, inclusive, or in the range of 231to 232- 2, inclusive, shall ignore the SEI message.

[0061] When an NNPFC SEI message is the first NNPFC SEI message, in decoding order, that has a particular nnpfc id value within the current CLVS, the following applies:- This SEI message specifies a base NNPF.P24092472301WO3; G25N21009W (4824-71003)This SEI message pertains to the current decoded picture and all subsequent decoded pictures of the current layer, in output order, until the end of the current CLVS.

[0062] nnpfc base flag equal to 1 specifies that the SEI message specifies the base NNPF. nnpfc base flag equal to 0 specifies that the SEI message specifies an update relative to the base NNPF.

[0063] The following constraints apply to the value of nnpfc base flag:- When an NNPFC SEI message is the first NNPFC SEI message, in decoding order, that has a particular nnpfc id value within the current CLVS, the value of nnpfc_base_flag shall be equal to 1.- All NNPFC SEI messages in a CLVS that have a particular nnpfc id value and nnpfc base flag equal to 1 shall have identical SEI payload content.

[0064] When nnpfc base flag is equal to 0, the following applies:This SEI message defines an update relative to the preceding base NNPF in decoding order with the same nnpfc id value. Updates arc not cumulative but rather each update is applied on the base NNPF, which is the NNPF specified by the first NNPFC SEI message, in decoding order, that has a particular nnpfc id value within the current CLVS. The NNPF defined by this SEI message is obtained by applying the update defined by this SEI message relative to the base NNPF with the same nnpfc id value.This SEI message pertains to the current decoded picture and all subsequent decoded pictures of the current layer, in output order, until the end of the current CLVS or up to but excluding the decoded picture that follows the current decoded picture in output order within the current CLVS and is associated with a subsequent NNPFC SEI message, in decoding order, having nnpfc base flag equal to 0 and that particular nnpfc id value within the current CLVS, whichever is earlier.

[0065] nnpfe mode ide, when equal to 0, indicates that the neural network information is contained in the NNPFC SEI message, and the neural network information is in the format of an ISO / IEC 15938-17 bitstream, nnpfe mode ide equal to 1 indicates that the neural network information is identified by the URI indicated by nnpfe uri with the format identified by the tag URI mipfe tag uri.

[0066] The value of nnpfe mode ide shall be in the range of 0 to 255. inclusive. Values of 2 to 255. inclusive, for nnpfe mode ide are reserved for future use 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 NNPFC SEI messages with nnpfe mode ide in the range of 2 to 255, inclusive.

[0067] impfc alignment zero bit a shall be equal to 0.

[0068] nnpfe tag uri contains a tag URI with syntax and semantics as specified in IETF RFC 4151 identifying the format and associated information about the neural network used as a base NNPF or an update relative to the base NNPF with the same nnpfc id value specified by nnpfe uri.

[0069] NOTE 3 - mipfe tag uri enables uniquely identifying the format of neural network data specified by nnpfe uri without needing a central registration authority.P24092472301WO3; G25N21009W (4824-71003)

[0070] nnpfc tag uri equal to "tag:iso.org, 2023:15938-17" indicates that the neural network data identified by nnpfc uri conforms to ISO / IEC 15938-17.

[0071] nnpfc uri contains a URI with syntax and semantics as specified in IETF Internet Standard 66 identifying the neural network used as a base NNPF or an update relative to the base NNPF with the same nnpfc id value.

[0072] nnpfc propcrty prcscnt flag equal to 1 specifics that syntax elements related to the filter properties including purpose, input formatting, output formatting, and complexity are present, nnpfc _property_present_flag equal to 0 specifies that no syntax elements related to the filter properties are present.

[0073] When nnpfe base flag is equal to 1, nnpfc_property_present_flag shall be equal to 1.

[0074] When nnpfc_property_present_flag is equal to 0, the values of all syntax elements that may be present only when nnpfe property _present_flag is equal to 1 are inferred to be equal to their corresponding syntax elements, respectively, in the NNPFC SEI message that contains the base NNPF for which this SEI message provides an update.

[0075] When an NNPFC SEI message nnpfcCurr is not the first NNPFC SEI message, in decoding order, that has a particular nnpfc id value within the current CLVS, is not a repetition of the first NNPFC SEI message with that particular nnpfc id value (in this case the value of nnpfc_basc_flag is equal to 0), and the value of nnpfc _p ropcrty_p resen t_flag is equal to 1, the following constraints apply:- The values of syntax elements following nnpfc_property_present_flag and preceding nnpfc_complexity_info_present flag, in decoding order, in the NNPFC SEI message shall be the same as the values of corresponding syntax elements in the first NNPFC SEI message, in decoding order, that has that particular nnpfc id value within the current CLVS.Either mipfc_complexity_info_present_flag shall be equal to 0 or both impfc_complexity_info_present_flag shall be equal to 1 in the first NNPFC SEI message, in decoding order, that has that particular nnpfc id value within the current CLVS (denoted as nnpfcBase below) and all the following constraints apply:- nnpfc_parameter_type_idc in nnpfcCurr shall be equal to nnpfc paramctcr typc idc in nnpfcBase.- impfc_log2_parameter_bit_length_minus3 in nnpfcCurr, when present, shall be less than or equal to rmpfc_log2_parameter_bit_length_minus3 in nnpfcBase.If mrpfc_num_parameters_idc in nnpfcBase is equal to 0. nnpfc_num_parameters_idc in nnpfcCurr shall be equal to 0.- Otherwise (nnpfc num parameters ide in nnpfcBase is greater than 0). nnpfc num_parameters ide in nnpfcCurr shall be greater than 0 and less than or equal to nnpfc_num_parameters_idc in nnpfcBase.If nnpfc num kmac operations idc in nnpfcBase is equal to 0, nnpfc num kmac operations idc in nnpfcCurr shall be equal to 0.P24092472301WO3; G25N21009W (4824-71003)Otherwise (rmpfc_num_kmac_operations_idc in nnpfcBase is greater than 0), mrpfc num kmac operations idc in nnpfcCurr shall be greater than 0 and less than or equal to nnpfc num kmac operations idc in nnpfcBase.- If nnpfc total kilobyte size in nnpfcBase is equal to 0, nnpfc total kilobyte size in nnpfcCurr shall be equal to 0.Otherwise (nnpfc total kilobyte size in nnpfcBase is greater than 0), nnpfc total kilobyte size in nnpfcCurr shall be greater than 0 and less than or equal to nnpfctotal kilobyte size in nnpfcBase.

[0076] nnpfc niim input pics niinus I plus 1 specifies the number of pictures used as input for the NNPF. The value of rmpfc_num_input_pics_minus 1 shall be in the range of 0 to 63, inclusive. When PictureRateUpsamplingFlag is equal to 1, the value of nnpfc_num_input_pics_minus 1 shall be greater than 0.

[0077] The variable numlnputPics, specifying the number of pictures used as input for the NNPF, is derived as follows: numlnputPics = impfc_num_input_pics_minus 1 + 1 (76)

[0078] nnpfc input_pic filtering flag[ i ] equal to 1 indicates that for the i-th input picture the NNPF generates a corresponding output picture. nnpfc_input_pic_filtering_flag[ i ] equal to 0 indicates that for the i-th input picture the NNPF does not generate a corresponding output picture. Each NNPF-generated picture is stored in the output tensor of the NNPF. When nnpfc_num_input_pics_minus 1 is equal to 0, impfc_input_pic_filtering_flag

[0000] is inferred to be equal to 1. When PictureRateUpsamplingFlag is equal to 0 and nnpfc num input _pics_minus 1 is greater than 0, impfc_input_pic_filtering_flag[ i ] shall be equal to 1 for at least one value of i in the range of 0 to nnpfc num input pics minus 1, inclusive.

[0079] nnpfc_absent_input_pic_zero_flag equal to 1 indicates that the NNPF expects an input picture that is not present in the bitstream to be represented by sample arrays with sample values equal to 0. rmpfc_abscnt_input_pic_zcro_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the bitstream to be represented by the input picture inputPicB that is the closest to inputPicA in output order and is present in the bitstream.

[0080] impfc out sub c flag specifies the values of the variables outSubWidthC and outSubHeightC when ChromaUpsamplingFlag is equal to 1. nnpfc_out_sub_c_flag equal to 1 specifies that outSubWidthC is equal to1 and outSubHeightC is equal to 1. impfc out sub c flag equal to 0 specifies that outSubWidthC is equal to 2 and outSubHeightC is equal to 1. When ChromaFonnatldc is equal to 2 and impfc out sub c flag is present, the value of impfc out sub c flag shall be equal to 1.

[0081] nnpfc out colour format idc, when ColourizationFlag is equal to 1, specifies the colour format of the NNPF-generated pictures and consequently the values of the variables outSubWidthC and outSubHeightC. impfc out colour format idc equal to 1 specifies that the colour format of the NNPF-generated pictures is the 4:2:0 format and outSubWidthC and outSubHeightC are both equal to 2. mrpfc out colour fonnat idc equal to2 specifies that the colour fonnat of the NNPF-generated pictures is the 4:2:2 format and outSubWidthC is equalP24092472301WO3; G25N21009W (4824-71003) to 2 and outSubHeightC is equal to 1. nnpfc out colour format idc equal to 3 specifies that the colour format of the NNPF -generated pictures is the 4:4:4 format and outSubWidthC and outSubHeightC are both equal to 1. The value of nnpfc out colour format idc shall not be equal to 0.

[0082] When ChromaUpsamplingFlag and ColourizationFlag are both equal to 0, outSubWidthC and outSubHeightC are inferred to be equal to SubWidthC and SubHeightC, respectively.

[0083] nnpfc_pic_width_num_minus 1 plus 1 and nnpfc_pic_width_denom_minus 1 plus 1 specify the numerator and denominator, respectively, for the resampling ratio of the width of the NNPF -generated pictures relative to CroppedWidth. Both nnpfc_pic_width_num_minus 1 and nnpfc_pic_width_denom_minus 1 shall be in the range of 0 to 65,535, inclusive.

[0084] The value of ( nnpfc_pic_width_num_minus 1 + 1 ) -fy nnpfc_pic_width_denom_minus 1 + 1 ) shall be in the range of 1 ^- 16 to 16, inclusive. When mrpfc_pic_width_num_minusl and impfc_pic_width_dcnom_minus 1 arc not present, the values of impfc_pic_width_num_minus 1 and nnpfc jic width denom minus 1 are both inferred to be equal to 0.

[0085] The variable nnpfcOutputPicWidth, representing the width of the luma sample arrays of the NNPF- generated pictures, is derived as follows: nnpfcOutputPicWidth = Ceil( CroppedWidth *(77)( nnpfc_pic_width_num_minusl + 1 ) -fy nnpfc_pic_width_denom_minus 1 + 1 ) )When SpatialExtrapolation is equal to 1, nnpfcOutputPicWidth is updated as follows: nnpfcOutputPicWidth += outSubWidthC * ( nnpfc spatial extrapolation left offset + (77) nnpfc spatial extrapolation right offset )

[0086] It is a requirement of bitstream conformance that nnpfcOutputPicWidth shall be greater than 0 and nnpfcOutputPicWidth % outSubWidthC shall be equal to 0.

[0087] nnpfc pic height num minus 1 plus 1 and nnpfc pic height denom minus 1 plus 1 specify the numerator and denominator, respectively, for the resampling ratio of the height of the NNPF-generated pictures relative to CroppedHeight. Both nnpfc_pic_height_num_minusl and rmpfc_pic_height_denom_minus 1 shall be in the range of 0 to 65,535, inclusive.

[0088] The value of ( nnpfc_pic_height_num_minus 1 + 1 ) ( nnpfc_pic_height_denom_minus 1 + 1 ) shall be in the range of 1 ^- 16 to 16, inclusive. When mrpfc_pic_height_num_minus 1 and nnpfc_pic_height_denom_minus 1 are not present, the values of nnpfc_pic_height_num_minus 1 and nnpfc_pic_height_denom_minus 1 are both inferred to be equal to 0.

[0089] The variable nnpfcOutputPicHeight, representing the height of the luma sample arrays of the NNPF- generated pictures, is derived as follows:P24092472301WO3; G25N21009W (4824-71003) nnpfcOutputPicHeight = Ceil( CroppedHeight *(78)( impfc_pic_height_num_minus 1 + 1 ) ( mipfc_pic_height_denom_minus 1 + 1 ) )

[0090] When SpatialExtrapolation is equal to 1. nnpfcOutputPicHeight is updated as follows: nnpfcOutputPicHeight += outSubHeightC * ( nnpfc spatial extrapolation top offset + (78) nnpfc spatial cxtrapolation bottom offsct )

[0091] It is a requirement of bitstream conformance that nnpfcOutputPicHeight shall be greater than 0 and nnpfcOutputPicHeight % outSubHeightC shall be equal to 0.

[0092] When ResolutionResamplingFlag is equal to 1, at least one the following conditions shall be true: The value of nnpfcOutputPicWidth is not equal to CroppedWidth.The value of nnpfcOutputPicHeight is not equal to CroppedHeight.SpatialExtrapolationFlag is equal to 1.

[0093] nnpfc_interpolated_pics[ i ] specifies the number of interpolated pictures generated by the NNPF between the i-th and the ( i + 1 )-th input picture for the NNPF. The value of nnpfc_interpolated_pics[ i ] shall be in the range of 0 to 63, inclusive. When the nnpfc_interpolated_pics[ i ] syntax elements are present, the value of nnpfc_interpolated_pics[ i ] shall be greater than 0 for at least one value of i in the range of 0 to impfc_num_input_pics_minus 1 - 1, inclusive.

[0094] NOTE 4 -When PictureRateUpsamplingFlag is equal to 1 for an NNPF and the NNPFA SEI message that activated this NNPF has nnpfa_persistence_flag equal to 1, only for a single value of i in the range of 0 to numlnputPics - 1, inclusive, the value of nnpfc_interpolated_pics[ i ] is greater than 0.

[0095] nnpfc_extrapolated_pics_minus 1 plus 1 specifies the number of extrapolated pictures generated by the NNPF subsequent to all input pictures for the NNPF in output order. The value of nnpfc_extrapolated_pics_minus 1 shall be in the range of 0 to 62, inclusive.

[0096] The variables NumlnpPicsInOutputTensor, specifying the number of pictures that have a corresponding input picture and are present in the output tensor of the NNPF, Inpldx[ idx ], specifying the input picture index, to the list of input pictures in reverse output order, of the idx-th picture that is present in the output tensor of the NNPF and has a corresponding input picture, and numPicsInOutputTcnsor, specifying the total number of pictures present in the output tensor of the NNPF, are derived as follows: for( i = 0. numPicsInOutputTensor = 0; i < numlnputPics; i++ ) if( nnpfc_input_pic_filtering_flag[ i ] ) { Inpldx[ numPicsInOutputTensor ] = i numPicsInOutputTensor++} (79)NumlnpPicsInOutputTensor = numPicsInOutputTensor if( PictureRateUpsamplingFlag )P24092472301WO3; G25N21009W (4824-71003) for( i = 0; i <= numlnputPics - 2; i++ ) numPicsInOutputTensor += nnpfc_interpolated_pics[ i ] if( TemporalExtrapolationFlag ) numPicsInOutputTensor += nnpfc_extrapolated_pics + 1

[0097] nnpfc spatial extrapolation left offset, nnpfc spatial extrapolation right offset, nnpfc_spatial_ extrapolation_top_offset, and nnpfc_spatial_extrapolation_bottom_offset specify the spatial extrapolation area. The luma samples with horizontal picture coordinates from outSubWidthC * mipfc spatial extrapolation left offset to nnpfcOutputPicWidth - ( outSubWidthC * nnpfc_spatial_ extrapolation right offset ) and vertical picture coordinates from outSubHeightC * nnpfc_ spatial extrapolation top offset to nnpfcOutputPicHeight - ( outSubHeightC * nnpfc spatial extrapolation bottom offset ) correspond to the spatial area of the input picture. The value of nnpfc_spatial_extrapolation_left_offset, nnpfc_spatial_extrapolation_right_offset, nnpfc_spatial_ extrapolation_top_offset and nnpfc_spatial_extrapolation_bottom_offset shall be in the range of -65 536 to 65 536, inclusive. At least one of nnpfc spatial extrapolation left offset, nnpfc_spatial_ extrapolation right offset, nnpfc spatial extrapolation top offset and nnpfc_spatial_extrapolation_bottom_ offset shall be greater than 0.

[0098] nnpfc_spatial_extrapolation_prompt_present_flag equal to 1 specifies that nnpfc_prompt syntax element is present and nnpfc_alignment_zero_bit_c syntax element may be present. mipfc_spatial_extrapolation_prompt_present_flag equal to 0 specifies that nnpfcjirompt syntax element and nnpfc alignment zero bit c syntax element are not present.

[0099] nnpfc alignment zero bit c shall be equal to 0.

[0100] nnpfc_prompt specifies the text string prompt used for generating the contents of the spatial extrapolation image area. When nnpfc_spatial_cxtrapolation_prompt_prcscnt_flag is equal to 1, nnpfc_prompt shall not be a null string.

[0101] nnpfc component last flag equal to 1 indicates that the last dimension in the input tensor inputTensor to the NNPF and the output tensor outputTensor of the NNPF is used for a current channel, nnpfc component last flag equal to 0 indicates that the third dimension in the input tensor inputTensor to the NNPF and the output tensor outputTensor of the NNPF is used for a current channel.

[0102] NOTE 5 - The first dimension in the input tensor and in tire output tensor is used for the batch index, which is a common practice in some neural network frameworks. While the equations in the semantics of this SEI message use the batch size corresponding to the batch index equal to 0, it is up to the post-processing implementation to determine the batch size used as the input to the neural network inference process.

[0103] NOTE 6 - For example, when nnpfc inp ordcr idc is equal to 3 and nnpfe auxiliary inp ide is equal to 1, there are 7 channels in the input tensor, including four luma matrices, two chroma matrices, and one auxiliary input matrix. In this case, the process DeriveInputTensors( ) would derive each of these 7 channels ofP24092472301WO3; G25N21009W (4824-71003) the input tensor one by one, and when a particular channel of these channels is processed, that channel is referred to as the current channel during the process.

[0104] nnpfc inp format idc indicates the method of converting a sample value of the input picture to an input value to the NNPF. The value of nnpfc inp format idc shall be in the range of 0 to 255, inclusive. Values of nnpfc inp format idc in the range of 2 to 255, inclusive, are reserved for future specification by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc inp format idc in the range of 2 to 255, inclusive.

[0105] When nnpfc inp format ide is equal to 0. the input values to the NNPF are real numbers and the functions InpY( ) and InpC( ) are specified as follows:InpY( x ) = x - ( ( I « BitDepthy ) - 1 )(80)InpC( x )= x <- ( ( 1 « BitDepthc ) - 1 )(81)

[0106] When nnpfc inp format idc is equal to 1, the input values to the NNPF are unsigned integer numbers and the functions InpY( ) and InpC( ) are specified as follows: shiftY = BitDepthY — inpTensorBitDepthY if( inpTensorBitDepthY >= BitDepthY)InpY( x ) = x « ( inpTensorBitDepthY - BitDepthY ) (82) elseInpY( x ) = Clip3(0, ( 1 « inpTensorBitDepthY ) - 1, ( x + ( 1 « ( shiftY - 1 ) ) ) » shiftY ) shiftC = BitDepthC - inpTensorBitDepthC if( inpTensorBitDepthC >= BitDepthC )InpC( x ) = x « ( inpTensorBitDepthC - BitDepthC ) (83) elseInpC( x ) = Clip3(0, ( 1 « inpTensorBitDepthC ) - 1, ( x + ( 1 « ( shiftC - I ) ) ) » shiftC )

[0107] The variable inpTensorBitDepthY is derived from the syntax element impfc_inp_tensor_luma_bitdepth_minus8 as specified below. The variable inpTensorBitDepthC is derived from the syntax element nnpfc_inp_tcnsor_chroma_bitdcpth_minus8 as specified below.

[0108] impfe auxiliary inp ide greater than 0 indicates that auxiliary input data is present in the input tensor of the NNPF. impfe auxiliary inp ide equal to 0 indicates that auxiliary input data is not present in the input tensor, nnpfe auxiliary inp ide equal to 1, 2 or 3 specifies that auxiliary input data is derived as specified in Equation 95.

[0109] When impfe auxiliary inp ide is equal to 2 or 3, nnpfc_spatial_extrapolation_prompt_present_flag shall be equal to 1.P24092472301WO3; G25N21009W (4824-71003)

[0110] The value of nnpfc auxiliary inp idc shall be in the range of 0 to 255, inclusive. Values of 2 to 255, inclusive, for nnpfc auxiliary inp idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc auxiliary inp idc in the range of 4 to 255. inclusive. [OHl] When nnpfc auxiliary inp idc is equal to 1 tire auxiliary input data consists of strengthControlScaledVal[ i ].

[0112] When nnpfc auxiliary inp idc is equal to 2 the auxiliary input data consists of nnpfc_prompt character values.

[0113] When nnpfc auxiliary inp idc is equal to 3, the auxiliary input data consists of strengthControlScaledVal[ i ] and nnpfc_prompt character values.

[0114] nnpfc inp order idc indicates the method of ordering the sample arrays of an input picture to form an input tensor to the NNPF.

[0115] The value of nnpfc inp order idc shall be in the range of 0 to 255, inclusive. Values of 4 to 255, inclusive, for nnpfc inp order idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc inp order idc in the range of 4 to 255, inclusive.

[0116] When ChromaFormatldc is not equal to 1, nnpfc inp order idc shall not be equal to 3.

[0117] When ChromaFormatldc is equal to 0, nnpfc inp order idc shall be equal to 0.

[0118] When ChromaUpsamplingFlag is equal to 1, nnpfc inp order idc shall not be equal to 0.

[0119] Table 2 contains an informative description of nnpfc inp order idc values.Table 2 - Description of nnpfc inp order idc valuesP24092472301WO3; G25N21009W (4824-71003)

[0120] FIG. 1 is an example mechanism for deriving the four luma charnels (right) from the luma component (left) when nnpfc inp order idc is equal to 3.

[0121] impfc_inp_tensor_luma_bitdepth_minus8 plus 8 specifies the bit depth of luma sample values in the input integer tensor. The value of inpTensorBitDepthY is derived as follows: mpTensorBitDepthy = nnpfc_inp_tensor_luma_bitdepth_minus8 + 8 (84)

[0122] It is a requirement of bitstream conformance that the value of nnpfc inp tensor _luma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive.

[0123] nnpfc_inp_tensor_chroma_bitdepth_minus8 plus 8 specifies the bit depth of chroma sample values in the input integer tensor. The value of inpTensorBitDepthC is derived as follows: inpTensorBitDepthc = nnpfc_inp_tensor_chroma_bitdepth_minus8 + 8 (85)

[0124] ft is a requirement of bitstream conformance that the value of nnpfc inp tensor _chroma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive.

[0125] nnpfc out format idc equal to 0 indicates that the sample values output by the NNPF are real numbers where the value range of 0 to 1, inclusive, maps linearly to the unsigned integer value range of 0 to ( 1 « bitDepth ) - 1, inclusive, for any desired bit depth bitDepth for subsequent post-processing or displaying.

[0126] nnpfc out format idc equal to 1 indicates that the luma sample values output by the NNPF are unsigned integer numbers in the range of 0 to ( 1 « outTensorBitDepthY ) - 1, inclusive, and the chromaP24092472301WO3; G25N21009W (4824-71003) sample values output by the NNPF are unsigned integer numbers in the range of 0 to ( 1 « outTensorBitDepthC ) - 1, inclusive.

[0127] The value of nnpfc out format idc shall be in the range of 0 to 255. inclusive. Values of 2 to 255. inclusive, for nnpfc out format idc are reserved for future specification by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc out format idc in the range of 2 to 255, inclusive.

[0128] nnpfc out order idc indicates the output order of samples resulting from the NNPF.

[0129] The value of nnpfc out order idc shall be in the range of 0 to 255, inclusive. Values of 4 to 255. inclusive, for nnpfc out order idc are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc out order idc in the range of 4 to 255, inclusive.

[0130] When ChromaUpsamplingFlag is equal to 1, mipfc out order idc shall not be equal to 0 or 3.

[0131] When ColourizationFlag is equal to 1, nnpfc out order ide shall not be equal to 0.

[0132] Table 3 contains an informative description of nnpfc out order idc values.Table 3 - Description of nnpfc out order idc values

[0133] nnpfc out tensor luma bitdepth minus 8 plus 8 specifies the bit depth of luma sample values in the output integer tensor. The value of nnpfc_out_tensor_luma_bitdepth_minus8 shall be in the range of 0 to 24, inclusive. The value of outTensorBitDepthY is derived as follows: outTensorBitDepthy = nnpfc_out_tensor_luma_bitdepth_minus8 + 8 (86)

[0134] impfc_out_tensor_chroma_bitdepth_minus8 plus 8 specifies the bit depth of chroma sample values in the output integer tensor. The value of nnpfc out tensor chroma bitdepth minus 8 shall be in the range of 0 to 24, inclusive. The value of outTensorBitDepthC is derived as follows: outTensorBitDepthc = nnpfc_out_tensor_chroma_bitdepth_minus8 + 8 (87)P24092472301WO3; G25N21009W (4824-71003)

[0135] When BitDepthUpsamplingFlag is equal to 1, the value of nnpfc out format idc shall be equal to 1 and at least one of the following conditions shall be true:- nnpfc_out_tensor_luma_bitdepth_minus8 is present and outTensorBitDepthy is greater than BitDepthy.- nnpfc_out_tensor_chroma_bitdepth_minus8 is present and outTensorBitDepthc is greater than BitDepthc.

[0136] When nnpfc_inp_tensor_luma_bitdepth_minus8, nnpfc_inp_tensor_chroma_bitdepth_minus8, nnpfc_out_tensor_luma_bitdepth_minus8, and nnpfc_out_tensor_chroma_bitdepth_minus8 are present and outTensorBitDepthY is greater than inpTensorBitDepthY, outTensorBitDepthc shall not be less than inpTensorBitDepthC. When nnpfc_inp_tensor_hima_bitdepth_minus8. nnpfc_inp_tensor_chroma_ bitdepth minus 8, nnpfc out tensor luma bitdepth minus8. and nnpfc out tensor chroma bitdepth minus 8 are present and outTensorBitDepthc is greater than inpTensorBitDepthC, outTensorBitDepthY shall not be less than inpTensorBitDepthY.

[0137] nnpfc_scparatc_colour_dcscription_prcscnt_flag equal to 1 indicates that a distinct combination of colour primaries, transfer characteristics, matrix coefficients, and scaling and offset values applied in association with the matrix coefficients for the picture resulting from the NNPF is specified in the SEI message syntax structure. nnpfc_separate_colour_description_present_flag equal to 0 indicates that the combination of colour primaries, transfer characteristics, matrix coefficients, and scaling and offset values applied in association with the matrix coefficients for the picture resulting from the NNPF is the same as implied by the VUI parameters vui_colour_primaries, vui tranfer characteristics, vui_matrix_coeffs, and vui full range flag that are indicated or inferred for the CLVS.

[0138] nnpfc_colour_primaries has the same semantics as specified in clause 7.3 for the vui_colour_primaries syntax element, except as follows:- nnpfc_colour_primaries specifies the colour primaries of the picture resulting from applying the NNPF specified in the SEI message, rather than the colour primaries used for the CLVS.- When iinpfc colourjirimarics is not present in the NNPFC SEI message, the value of nnpfc_colour_primaries is inferred to be equal to vui_colour_primaries.

[0139] nnpfc transfer characteristics has the same semantics as specified in clause 7.3 for the vui_transfer_characteristics syntax element, except as follows:- nnpfc transfer characteristics specifies the transfer characteristics of the picture resulting from applying the NNPF specified in the SEI message, rather than the transfer characteristics used for the CLVS.- When nnpfc transfer characteristics is not present in the NNPFC SEI message, the value of nnpfc transfer characteristics is inferred to be equal to vui transfer characteristics.

[0140] nnpfe matrix eoeffs describes the equations used in deriving luma and chroma signals from the green, blue, and red, or Y, Z, and X primaries. Its semantics apply to the pictures resulting from applying the NNPF specified in this SEI message and are as specified for MatrixCoefficients in Rec. ITU-T H.273 | ISO / IECP24092472301WO3; G25N21009W (4824-71003)23091-2 with BitDepthY and BitDepthC being equal to outTensorBitDepthY and outTensorBitDepthC, respectively.

[0141] When nnpfc matrix coeffs is not present in the NNPFC SEI message, the value of nnpfc matrix coeffs is inferred to be equal to vui matrix coeffs.

[0142] nnpfc matrix coeffs shall not be equal to 0 unless both of the following conditions are true:- impfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8.- nnpfc out order idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0143] nnpfc matrix coeffs shall not be equal to 8 unless one of the following conditions is true:- nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to mrpfc_out_tensor_luma_bitdepth_minus8.- nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8 + 1, nnpfc out order idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0144] nnpfc full range flag indicates the scaling and offset values applied in association with the matrix coefficients as specified by nnpfc matrix coeffs. Its semantics are as specified for the VideoFullRangeFlag parameter in Rec. ITU-T H.273 | ISO / IEC 23091-2. When not present, the value of nnpfc full range flag is inferred to be equal to 0.

[0145] nnpfc_chroma_loc_info_present_flag equal to 1 indicates the presence of the nnpfc chroma sample loc type frame syntax element in the NNPFC SEI message. nnpfc_cliroma_loc_info_present_flag equal to 0 indicates the absence of the nnpfc chroma samplc joc typc framc syntax element in the NNPFC SEI message. When nnpfc_chroma_loc_info_present_flag is not present, its value is inferred to be equal to 0. When ColourizationFlag is equal to 0 or nnpfc out colour format idc is not equal to 1, the value of nnpfc_chroma_loc_info_present_flag shall be equal to 0.

[0146] mrpfc chroma sample loc type frame, when not equal to 6 and mrpfc out colour format idc is equal to 1, specifies the location of chroma samples of the output pictures. nnpfc_chroma_ sample loc type frame equal to 6 and nnpfc out colour format ide equal to 1 indicates that the location of the chroma samples is unknown or unspecified or specified by other means not specified in this Specification. The value of nnpfc chroma samplc loc typc framc shall be in the range of 0 to 6, inclusive.

[0147] nnpfe overlap indicates the overlapping horizontal and vertical sample counts of adjacent input tensors of the NNPF. The value of nnpfe overlap shall be in the range of 0 to 16,383, inclusive. When SpatialExtrapolationFlag is equal to 1, nnpfe overlap is inferred to be equal to 0.

[0148] nnpfc_constant_patch_size_flag equal to 1 indicates that the NNPF accepts exactly the patch size indicated by nnpfc_patch_width_minusl and nnpfc_patch_height_minus 1 as input, nnpfc constant _patch_size_flag equal to 0 indicates that the NNPF accepts as input any patch size with width inpPatchWidth and height inpPatchHeight such that the width of an extended patch (i.e., a patch plus the overlapping area), which is equal to inpPatchWidth + 2 * nnpfe overlap, is a positive integer multiple of nnpfe extended _patch_width_cd_delta_minus 1 + 1 + 2 * nnpfe overlap, and the height of the extended patch, which is equal toP24092472301WO3; G25N21009W (4824-71003) inpPatchHeight + 2 * nnpfc_overlap, is a positive integer multiple of nnpfc_extended_patch _height_cd_delta_minus 1 + 1 + 2 * nnpfc overlap. When SpatialExtrapolationFlag is equal to 1, nnpfc_constant_patch_size_flag is inferred to be equal to 1.

[0149] nnpfc_patch_width_minus 1 plus 1, when nnpfc constant patch sizc flag equal to 1, indicates the horizontal sample counts of the patch size required for the input to the NNPF. The value of nnpfc_patch_width_minus 1 shall be in the range of 0 to Min( 32,766, CroppedWidth - 1 ), inclusive. When SpatialExtrapolationFlag is equal to 1, nnpfc_patch_width_minusl is inferred to be equal to CroppedWidth - 1.

[0150] nnpfc_patch_height_minus 1 plus 1, when nnpfc_constant_patch_size_flag equal to 1, indicates the vertical sample counts of the patch size required for the input to the NNPF. The value of nnpfc_patch_height_minus 1 shall be in the range of 0 to Min( 32,766, CroppedHeight - 1 ), inclusive. When SpatialExtrapolationFlag is equal to 1, impfc_patch_height_minus 1 is inferred to be equal to CroppedHeight - 1.

[0151] rnipfc_cxtcndcd_patch_width_cd_dclta_minusl plus 1 plus 2 * nnpfc overlap, when nnpfc_ constant _patch_size_flag equal to 0, indicates a common divisor of all allowed values of the width of an extended patch required for the input to the NNPF. The value of nnpfc_extended_patch_width_cd_delta_minus 1 shall be in the range of 0 to Min( 32,766, CroppedWidth - 1 ), inclusive.

[0152] nnpfc_extended_patch_height_cd_delta_minusl plus 1 plus 2 * nnpfc overlap, when nnpfc_constant_patch_size_flag equal to 0, indicates a common divisor of all allowed values of the height of an extended patch required for the input to the NNPF. The value of nnpfc_extended_patch_height_cd_delta_minus 1 shall be in the range of 0 to Min( 32,766, CroppedHeight - 1 ), inclusive.

[0153] Let the variables inpPatchWidth and inpPatchHeight be the patch size width and the patch size height, respectively.

[0154] If mipfc_constant_patch_size_flag is equal to 0, the following applies:- The values of inpPatchWidth and inpPatchHeight are either provided by external means not specified in this Specification or set by the post-processor itself.- The value of inpPatchWidth + 2 * nnpfc overlap shall be a positive integer multiple of nnpfc_extended_patch_width_cd_delta_minus 1 + 1 + 2 * nnpfc overlap and inpPatchWidth shall be less than or equal to CroppedWidth. The value of inpPatchHeight + 2 * nnpfc overlap shall be a positive integer multiple of nnpfc_extended_patch_height_cd_delta_minus 1 + 1 + 2 * nnpfc overlap and inpPatchHeight shall be less than or equal to CroppedHeight.

[0155] Otherwise (nnpfc_constant_patch_size_flag is equal to 1), the value of inpPatchWidth is set equal to impfc_patch_width_minus 1 + 1 and the value of inpPatchHeight is set equal to nnpfc_patch_height_minus 1 + 1.

[0156] The variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, and outPatchCHeight are derived as follows: outPatchWidth = ( nnpfcOutputPicWidth * inpPatchWidth ) / CroppedWidth (88) outPatchHeight = ( nnpfcOutputPicHeight * inpPatchHeight ) / CroppedHeight (89)P24092472301WO3; G25N21009W (4824-71003) horCScaling = SubWidthC / outSubWidthC (90) verCScaling = SubHeightC / outSubHeightC (91) outPatchCWidtli = outPatchWidth * horCScaling (92) outPatchCHeight = outPatchHeight * verCScaling (93)

[0157] It is a requirement of bitstream conformance that outPatchWidth * CroppedWidth shall be equal to nnpfcOutputPicWidth * inpPatchWidth and outPatchHeight * CroppedHeight shall be equal to nnpfcOutputPicHeight * inpPatchHeight.

[0158] nnpfc padding typc indicates the process of padding when referencing sample locations outside the boundaries of the input picture as described in Table 4. The value of nnpfc padding type shall be in the range of 0 to 15, inclusive. Values of 5 to 15, inclusive, for nnpfc_padding_type are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc_padding_typc in the range of 5 to 15, inclusive.Table 4 - Informative description of nnpfc padding type values

[0159] nnpfc himajiadding val indicates the luma value to be used for padding when nnpfc jiadding typc is equal to 4. The value of nnpfc_luma_padding_val shall be in the range of 0 to ( 1 « BitDepthY ) - I, inclusive.

[0160] nnpfc cb padding val indicates the Cb value to be used for padding when nnpfc_padding_type is equal to 4. The value of mrpfc_cb_padding_val shall be in the range of 0 to ( 1 « BitDepthC ) - 1, inclusive.

[0161] nnpfc_cr_padding_val indicates the Cr value to be used for padding when nnpfc padding typc is equal to 4. The value of nnpfc_cr_padding_val shall be in the range of 0 to ( 1 « BitDepthC ) - I, inclusive.

[0162] The function InpSampleVal( y, x, picHeight, picWidth, croppedPic, cldx ) with inputs being a vertical sample location y, a horizontal sample location x, a picture height picHeight, a picture width picWidth, sample array croppedPic. and component index cldx (equal to 0 for luma, 1 for Cb. and 2 for Cr) returns the value of sampleVal derived as follows:

[0163] NOTE 7 - For the inputs to the function InpSampleVal( ), the vertical location is listed before the horizontal location for compatibility with input tensor conventions of some inference engines.P24092472301WO3; G25N21009W (4824-71003) if( impfc padding ty c = = 0 ) if( y < 0 | | x < 0 | | y >= picHeight | | x >= picWidth ) sampleVal = 0 else sampleVal = croppedPic[ x ] [ y ] (94) else if( nnpfc_padding_type = = 1 ) sampleVal = croppedPic[ Clip3( 0, picWidth - 1, x ) ][ Clip3( 0, picHeight - 1, y ) ] else if( nnpfc_padding_typc = = 2 ) sampleVal = croppedPicf Reflect( picWidth - 1, x ) ][ Reflect( picHeight - 1, y ) ] else if( nnpfc padding type = = 3 ) if( y >= 0 && y < picHeight ) sampleVal = croppedPicf Wrap( picWidth - 1, x ) ][ y ] else if( nnpfe padding type = = 4 ) if( y < 0 | | x < 0 | | y >= picHeight | | x >= picWidth ) sampleVal = ( cldx = = 0 ? nnpfc_luma_padding_val :( cldx = = 1 ? nnpfc cb padding val : nnpfc cr padding val ) ) else sampleVal = croppedPicf x ][ y ]

[0164] When nnpfe auxiliary inp ide is equal to 1, the variable strcngthControlScalcdVal is derived as follows: for( i = 0; i < numlnputPics; i++ ) if( nnpfe inp format ide = = 1 ) (95) if( nnpfe inp order ide = = 0 | | nnpfe inp order ide = = 2 | | nnpfe inp order ide = = 3 ) strcngthControlScalcdValf i ] =Floor ( StrengthControlValf i ] * ( ( 1 « mpTensorBitDepthy ) - 1 ) ) else if( nnpfe inp order ide = = 1 ) strengthControlScaledValf i ] =Floor ( StrengthControlValf i ] * ( ( 1 « inpTensorBitDepthc ) - 1 ) ) else strengthControlScaledValf i ] = StrengthControlValf i ]

[0165] A patch is a rectangular array of samples from a component (e.g., a luma or chroma component) of a picture.P24092472301WO3; G25N21009W (4824-71003)

[0166] The process DeriveInputTensors( ), for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and a horizontal sample coordinate cLeft specifying the top-left sample location for the patch of samples included in the input tensor, is specified as follows: for( i = 0; i < numlnputPics; i++ ) 1 if( nnpfc inp order idc = = 0 ) for( yP = -nnpfc overlap; yP < inpPatchHeight + nnpfc overlap; yP++) for( xP = -nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { inpVal = InpY( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight, CroppedWidth. CroppedYPic[ i ], 0 ) ) promptCharVal = utf8ToUInt( nnpfc_prompt ) yPovlp = yP + nnpfc overlap xPovlp = xP + nnpfc overlap if( !nnpfc_component_last_flag ) inputTensor

[0000] [ i ]

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

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

[0000] = inpVal if( nnpfc auxiliary inp idc = = 1 1 1 nnpfc auxiliary inp idc = = 3) if( !impfc_component_last_flag ) inputTcnsor

[0000] [ i ]

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

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

[0001] = strengthControlScaledValf i ] if( nnpfc auxiliary inp idc = = 2 1 1 nnpfc auxiliary inp idc = = 3) if( !impfc_component_last_flag ) inputTensor

[0000] [ i ] [ nnpfc auxiliary inp idc - 1 ][ yPovlp ][ xPovlp ] = promptCharVal else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ][ nnpfc auxiliary inp idc - 1 ] = promptCharVal } else if( nnpfc inp order idc = = 1 ) (96) for( yP = -nnpfc overlap: yP < inpPatchHeight + nnpfc overlap; yP++) for( xP = -nnpfc_overlap; xP < inpPatchWidth + nnpfc_overlap; xP++ ) { inpCbVal = InpC( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCbPic[ i ], 1 ) ) inpCrVal = InpC( InpSampleVal( cTop + yP, cLeft + xP, CroppedHeight / SubHeightC, CroppedWidth / SubWidthC, CroppedCrPic[ i ], 2 ) ) promptCharVal = utf8ToUInt( nnpfc_prompt ) yPovlp = yP + nnpfc overlapP24092472301WO3; G25N21009W (4824-71003) xPovlp = xP + nnpfc overlap if( !nnpfc_component_last flag ) { inputTensorf 0 ][ i ]

[0000] [ yPovlp ][ xPovlp ] = inpCbVal inputTensorf 0 ][ i ]

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

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

[0000] = inpCbVal inputTensor

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

[0001] = inpCrVal} if( impfc auxiliary inp idc = = 1 1 1 impfc auxiliary inp idc = = 3) if( Innpfc component last flag ) inputTensor

[0000] [ i ]

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

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

[0002] = strengthControlScaledValf i ] if( impfc auxiliary inp idc = = 2 1 1 impfc auxiliary inp idc = = 3) if( Innpfc component last flag ) inputTensorf 0 ][ i ][ nnpfc auxiliary inp ide ][ yPovlp ][ xPovlp ] = promptCharVal else inputTensorf 0 ][ i ][ yPovlp ][ xPovlp ][ impfc auxiliary inp idc ] = promptCharVal } else if( nnpfe inp order ide = = 2 ) for( yP = -nnpfc overlap; yP < inpPatchHeight + nnpfc overlap; yP++) for( xP = -nnpfc overlap; xP < inpPatchWidth + nnpfc overlap; xP++ ) { yY = cTop + yP xY = cLeft + xP yC = yY / SubHeightC xC = xY / SubWidthC inpYVal = InpY( InpSampleVal( yY, xY. CroppedHeight, CroppedWidth. CroppedYPicf i ], 0 ) ) inpCbVal = InpC( InpSampleVal( yC, xC, CroppedHeight / SubHeightC,CroppedWidth / SubWidthC, CroppedCbPicf i ], 1 ) ) inpCrVal = InpC( InpSampleVal( yC, xC, CroppedHeight / SubHeightC,CroppedWidth / SubWidthC, CroppedCrPicf i ], 2 ) ) promptCharVal = utf8ToUInt( nnpfc_prompt ) yPovlp = yP + nnpfc overlap xPovlp = xP + nnpfc overlap if( !rmpfc_component_last_flag ) {P24092472301WO3; G25N21009W (4824-71003) inputTensor

[0000] [ i ]

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

[0000] [ i ]

[0001] [ yPovlp ][ xPovlp ] = inpCbVal inputTensorf 0 ][ i ]

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

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

[0000] = inpYVal inputTensor

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

[0001] = inpCbVal inputTensor

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

[0002] = inpCrVal} if( nnpfc auxiliary inp idc = = 1 1 1 nnpfc auxiliary inp idc = = 3) if( Innpfc component last flag ) inputTensor

[0000] [ i ]

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

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

[0003] = strengthControlScaledValf i ] if( nnpfc auxiliary inp idc = = 2 1 1 nnpfc auxiliary inp idc = = 3) if( Innpfc component last flag ) inputTensorf 0 ][ i ][ nnpfc auxiliary inp ide + 1 ][ yPovlp ][ xPovlp ] = promptCharVal else inputTensorf 0 ][ i ][ yPovlp ][ xPovlp ][ nnpfc auxiliary inp idc + 1 ] = promptCharVal } else if( nnpfe inp order ide = = 3 ) for( yP = -nnpfe overlap; yP < inpPatchHeight + nnpfe overlap; yP++) for( xP = -nnpfc overlap; xP < inpPatchWidth + nnpfc overlap; xP++ ) { yTL = cTop + yP * 2 xTL = cLeft + xP * 2 yBR = yTL + 1 xBR = xTL + 1 yC = cTop / 2 + yP xC = cLeft / 2 + xP inpTLVal = InpY( InpSampleVal( yTL, xTL, CroppedHeight,CroppedWidth, CroppedYPicf i ], 0 ) ) inpTRVal = InpY( InpSampleVal( yTL, xBR, CroppedHeight,CroppedWidth, CroppedYPicf i ], 0 ) ) inpBLVal = InpY( InpSampleVal( yBR, xTL. CroppedHeight,CroppedWidth. CroppedYPicf i ], 0 ) ) inpBRVal = InpY( InpSampleVal( yBR, xBR, CroppedHeight,CroppedWidth, CroppedYPicf i ], 0 ) )P24092472301WO3; G25N21009W (4824-71003) inpCbVal = InpC( InpSampleVal( yC, xC, CroppedHeight / 2, CroppedWidth / 2, CroppedCbPic[ i ], 1 ) ) inpCrVal = InpC( InpSampleVal( yC. xC. CroppedHeight / 2, CroppedWidth / 2, CroppedCrPicf i ]. 2 ) ) promptCharVal = utf8ToUInt( nnpfc_prompt ) yPovlp = yP + nnpfc overlap xPovlp = xP + nnpfc overlap if( !nnpfc_componcnt_last_flag ) { inputTensorf 0 ][ i ]

[0000] [ yPovlp ][ xPovlp ] = inpTLVal inputTensorf 0 ][ i ]

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

[0000] [ i ]

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

[0000] [ i ]

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

[0000] [ i ]

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

[0000] [ i ]

[0005] [ yPovlp ][ xPovlp ] = inpCrVal} else { inputTensorf 0 ][ i ][ yPovlp ][ xPovlp ]

[0000] = inpTLVal inputTensor

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

[0001] = inpTRVal inputTensor

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

[0002] = inpBLVal inputTensor

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

[0003] = inpBRVal inputTensor

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

[0004] = inpCbVal inputTensorf 0 ][ i ][ yPovlp ][ xPovlp ]

[0005] = inpCrVal} if( nnpfc auxiliaryinp idc = = 1 1 1 nnpfc auxiliaryinp idc = = 3) if( Innpfc component last flag ) inputTensor

[0000] [ i ]

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

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

[0006] = strengthControlScaledVal[ i ] if( nnpfc auxiliary inp idc = = 2 1 1 nnpfc auxiliary inp idc = = 3) if( Innpfc component last flag ) inputTensor

[0000] [ i ] [ nnpfc auxiliary inp idc + 4 ][ yPovlp ][ xPovlp ] = promptCharVal else inputTensor

[0000] [ i ][ yPovlp ][ xPovlp ][ nnpfc auxiliary inp idc + 4 ] = promptCharVal } utf8ToUInt( x ) { result = 0P24092472301WO3; G25N21009W (4824-71003) len = 0 / * Check end of text prompt string * / if( x = = null ) return 0 / * Determine the number of bytes in the UTF-8 character * / if( (x

[0000] & 0x80 ) = = 0 ) len = 1 / * 1-byte character * / else if( (x

[0000] & OxEO ) = = OxCO ) len = 2 / * 2-byte character * / else if( (x

[0000] & OxFO ) = = OxEO ) len = 3 1* 3 -byte character * / else if( (x

[0000] & 0xF8 ) = = OxFO ) len = 4 / * 4-byte character * / else len = 0 / * Invalid UTF-8 character; this case shall not occur in bitstreams. * / for( i = 0; i < len; i++ ) / * Construct an integer from the bytes * / result = ( result « 8 ) | x[ i ] x = x + len / * Modifies the input variable, which is a syntax element * / return result}

[0167] The process StoreOutputTensors( ), for deriving sample values in the sample arrays FilteredYPic. FilteredCbPic, and FilteredCrPic, for the NNPF -generated pictures, from the output tensor outputTensor for a given vertical sample coordinate cTop and a horizontal sample coordinate cLeft specifying the top-left sample location for the patch of samples included in the input tensor, is specified as follows: for( i = 0; i < numPicsInOutputTcnsor; i++ ) { if( nnpfe out order ide = = 0 ) for( yP = 0; yP < outPatchHeight; yP++ ) for( xP = 0; xP < outPatchWidth; xP++ ) { yY = cTop * outPatchHeight / inpPatchHeight + yP xY = cLeft * outPatchWidth / inpPatchWidth + xP if( yY < impfcOutputPicHeight && xY < nnpfcOutputPicWidth ) if( !nnpfc_component_last_flag )FilteredYPic[ i ][ xY ][yY ] = outputTensorf 0 ][ i ]

[0000] [ yP ][ xP ] elseFilteredYPic[ i ] [ xY ] [ yY ] = outputTensorf 0 ] [ i ] [ yP ] [ xP ]

[0000] }P24092472301WO3; G25N21009W (4824-71003) else if( nnpfc out order idc = = 1 ) (97) for( yP = 0; yP < outPatchCHeight; yP++ ) for( xP = 0; xP < outPatchCWidth; xP++ ) { xSrc = cLeft * horCScaling + xP ySrc = cTop * verCScaling + yP if( ySrc < nnpfcOutputPicHeight / outSubHeightC && xSrc < nnpfcOutputPicWidth / outSubWidthC ) if( !nnpfc_componcnt_last flag ) {FilteredCbPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ]

[0000] [ yP ][ xP ] FilteredCrPicf i ][ xSrc ][ ySrc ] = outputTensorf 0 ][ i ]

[0001] [ yP ][ xP ] } else {FilteredCbPic[ i ][ xSrc ][ ySrc ] = outputTensorf 0 ][ i ][ yP ][ xP ]

[0000] FilteredCrPicf i ][ xSrc ][ ySrc ] = outputTensorf 0 ][ i ][ yP ][ xP ]

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

[0000] [ yP ][ xP ] FilteredCbPicf i ][ xC ][ yC ] = outputTensorf 0 ][ i ]

[0001] [ yPc ][ xPc ] FilteredCrPicf i ][ xC ][ yC ] = outputTensorf 0 ][ i ]

[0002] [ yPc ][ xPc ] } else {FilteredYPicf i ] [ xY ] [ yY ] = outputTensorf 0 ] [ i ] [ yP ] [ xP ]

[0000] FilteredCbPicf i ][ xC ][ yC ] = outputTensorf 0 ][ i ][ yPc ][ xPc ]

[0001] FilteredCrPicf i ][ xC ][ yC ] = outputTensorf 0 ][ i ][ yPc ][ xPc ]

[0002] } else if( nnpfc out order idc = = 3 )P24092472301WO3; G25N21009W (4824-71003) for( yP = 0; yP < outPatchHeight; yP++ ) for( xP = 0; xP < outPatchWidth; xP++ ) { ySrc = cTop / 2 * outPatchHeight / inpPatchHeight + yP xSrc = cLeft / 2 * outPatchWidth / inpPatchWidth + xP if( ySrc < nnpfcOutputPicHeight / 2 && xSrc < nnpfcOutputPicWidth / 2 ) if( !impfc_component_last flag ) {FiltcrcdYPic[ i ][ xSrc * 2 ][ ySrc * 2 ] = outputTcnsor

[0000] [ i ]

[0000] [ yP ][ xP ]FilteredYPic[ i ][ xSrc * 2 + 1 ][ ySrc * 2 ] = outputTensor

[0000] [ i ]

[0001] [ yP ][ xP ] FilteredYPic[ i ][ xSrc * 2 ] [ ySrc * 2 + 1 ] = outputTensor

[0000] [ i ]

[0002] [ yP ][ xP ] FilteredYPic[ i ][ xSrc * 2 + 1][ ySrc * 2 + 1 ] = outputTensor

[0000] [ i ]

[0003] [ yP ][ xP ] FilteredCbPic[ i ][ xSrc ][ ySrc ] = outputTensor

[0000] [ i ]

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

[0000] [ i ]

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

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

[0000] FilteredYPic[ i ][ xSrc * 2 + 1 ][ ySrc * 2 ] = outputTensor

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

[0001] FilteredYPic[ i ][ xSrc * 2 ] [ ySrc * 2 + 1 ] = outputTensorf 0 ][ i ][ yP ][ xP ]

[0002] FilteredYPic[ i ][ xSrc * 2 + 1][ ySrc * 2 + 1 ] = outputTensorf 0 ][ i ][ yP ][ xP ]

[0003] FilteredCbPicf i ][ xSrc ][ ySrc ] = outputTensorf 0 ][ i ][ yP ][ xP ]

[0004] FilteredCrPicf i ][ xSrc ][ ySrc ] = outputTensorf 0 ][ i ][ yP ][ xP ]

[0005] }}}

[0168] An NNPF PostProcessingFilter( ) is the target NNPF as derived in the semantics of the NNPFA SEI message. The following example process may be used, with the NNPF PostProccssingFiltcr( ), to generate, in a patch-wise maimer, the filtered and / or interpolated picture(s), which contain Y, Cb, and Cr sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic. respectively, as indicated by nnpfe out order ide: if( nnpfe inp order ide = = 0 | | nnpfe inp order ide = = 2 ) for( cTop = 0; cTop < CroppedHeight; cTop += inpPatchHeight ) for( cLeft = 0; cLeft < CroppedWidth; cLeft += inpPatchWidth ) { inputTensor = DeriveInputTensors( ) outputTensor = PostProcessingFilter( inputTensor )StoreOutputTensors( outputTensor )} else if( nnpfe inp order ide = = 1 ) for( cTop = 0; cTop < CroppedHeight / SubHeightC; cTop += inpPatchHeight )P24092472301WO3; G25N21009W (4824-71003) for( cLeft = 0; cLeft < CroppedWidth / SubWidthC; cLeft += inpPatchWidth ) { (98) inputTensor = DeriveInputTensors( ) outputTensor = PostProcessingFilter( inputTensor )StoreOutputTensors( outputTensor )} else if( nnpfc inp order idc = = 3 ) for( cTop = 0; cTop < CroppedHeight; cTop += inpPatchHeight * 2 ) for( cLeft = 0; cLeft < CroppedWidth; cLeft += inpPatchWidth * 2 ) { inputTensor = DerivehiputTensors( ) outputTensor = PostProcessingFilter( inputTensor ) StoreOutputTensors( outputTensor )}

[0169] An NNPF-generated picture with index i contains sample arrays FilteredYPic[ i ], FilteredCbPic[ i ], and FilteredCrPic[ i ], when present, that are derived by Equation 98. An NNPF-generated picture does not include the overlap regions.

[0170] The NNPF process consists of the process defined by Equation 98 followed by outputting NNPF- generated pictures in their increasing index order, where all NNPF-generated pictures that were interpolated by the NNPF are output and those NNPF-generated pictures that correspond to any input pictures to the NNPF are output as specified in the semantics of the NNPFA SEI message.

[0171] nnpfc complexity info present flag equal to 1 specifies that one or more syntax elements that indicate the complexity of the NNPF associated with the nnpfe id are present. nnpfc_complexity_info_present_flag equal to 0 specifies that no syntax elements that indicates the complexity of the NNPF associated with the nnpfe id are present.

[0172] nnpfc_parameter_type_idc equal to 0 indicates that the neural network uses only integer parameters. nnpfc_parameter_type_idc equal to 1 indicates that the neural network may use floating point or integer parameters. nnpfc_parameter_type_idc equal to 2 indicates that the neural network uses only binary parameters. nnpfc_parameter_type_idc equal to 3 is reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with rmpfc_paramctcr_typc_idc equal to 3.

[0173] nnpfc_log2_parameter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters ofbit length greater than 8, 16, 32. and 64. respectively. When nnpfc_parameter_type_idc is present and impfc_log2_parameter_bit_length_minus3 is not present, the neural network does not use parameters ofbit length greater than 1.

[0174] nnpfc_num_parameters_idc indicates the maximum number of neural network parameters for the NNPF in units of a power of 2,048. nnpfc_num_parameters_idc equal to 0 indicates that the maximum numberP24092472301WO3; G25N21009W (4824-71003) of neural network parameters is unknown. The value nnpfc_num_parameters_idc shall be in the range of 0 to 52, inclusive. Values of nnpfc_num_parameters_idc greater than 52 are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall ignore NNPFC SEI messages with nnpfc_num_parameters_idc greater than 52.

[0175] If the value of nnpfc_num_parameters_idc is greater than zero, the variable maxNumParameters is derived as follows: maxNumParameters = ( 2,048 « nnpfc_num_parameters_idc ) - 1 (99)

[0176] It is a requirement of bitstream conformance that the number of neural network parameters of the NNPF shall be less than or equal to maxNumParameters.

[0177] nnpfc num kmac operations idc greater than 0 indicates that the maximum number of multiply- accumulatc operations per sample of the NNPF is less than or equal to mrpfc num kmac opcrations idc * 1,000. nnpfc num kmac operations idc equal to 0 indicates that the maximum number of multiply -accumulate operations of the network is unknown. The value of nnpfc num kmac operations idc shall be in the range of 0 to 232- 2, inclusive.

[0178] nnpfc_total_kilobyte_size greater than 0 indicates a total size in kilobytes required to store the uncompressed parameters for the neural network. The total size in bits is a number equal to or greater than the sum of bits used to store each parameter, nnpfc total kilobyte size is the total size in bits divided by 8,000, rounded up. nnpfc total kilobyte size equal to 0 indicates that the total size required to store the parameters for the neural network is unknown. The value of nnpfc total kilobyte size shall be in the range of 0 to 2 ’2- 2. inclusive.

[0179] nnpfc num metadata extension bits equal to 0 specifies that nnpfc reserved metadata extension is not present. When nnpfc num metadata extension bits is greater than 0, let the variable numSpecifiedMetadataExtensionBits be the number of bits representing all syntax elements between nnpfc num metadata extension bits and nnpfc reserved metadata extension. nnpfc num metadata extension bits greater than 0 specifies the sum of numSpecifiedMetadataExtensionBits and the length, in bits, of nnpfc reserved metadata extension.

[0180] The value of impfc_num_metadata_extension_bits shall be in the range of numSpecifiedMetadataExtensionBits to 2,048, inclusive. Values in the range of numSpecifiedMetadataExtensionBits + 1 to 2,048, inclusive, for nnpfc num metadata extension bits are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this Specification. Decoders conforming to this version of this Specification shall allow any? value of impfc_num_metadata_extension_bits in the range of 0 to numSpecifiedMetadataExtensionBits + 1 to 2,048, inclusive.P24092472301WO3; G25N21009W (4824-71003)

[0181] nnpfc_application_purpose_tag_uri_present flag equal to 1 indicates that the nnpfc_application_purpose_tag_uri syntax element is present in this NNPFC SEI message. nnpfc_application_purpose_tag_uri_present_flag equal to 0 indicates that the nnpfc_application_purpose_tag_uri syntax element is not present in this NNPFC SEI message. When not present nnpfc_application_purpose_tag_uri_present_flag is inferred to be equal to 0.

[0182] nnpfc_metadata_alignment_zero_bit shall be equal to 0.

[0183] impfc_application_purpose_tag_uri specifies a tag URI with syntax and semantics as specified in IETF RFC 4151 identifying the application determined purpose of the NN PF. when nnpfc_purpose is equal to 0.

[0184] NOTE 4 - nnpfc_application_purpose_tag_uri enables uniquely identifying the application determined purpose of NNPF without needing a central registration authority.

[0185] nnpfc scan type idc equal to 0 indicates that the preferred display method for the pictures output by the NNPF is unknown or unspecified or specified by external means, nnpfc scan type idc equal to 1 indicates that the pictures output by the NNPF are suitable for display using overscan, nnpfc scan type ide equal to 2 indicates that the pictures output by the NNPF contain visually important information in the entire region out to the edges of the picture, such that the pictures output by the NNPF should not be displayed using overscan. Instead, they should be displayed using either an exact match between the display area and the edges, or using underscan. As used in this paragraph, the term "overscan" refers to display processes in which some parts near the borders of the pictures are not visible in the display area. The term "underscan" describes display processes in which the entire pictures are visible in the display area, but they do not cover the entire display area. For display processes that neither use overscan nor underscan, the display area exactly matches the area of the pictures. The value of nnpfc scan type idc shall not be equal to 2. When not present, the value of nnpfc_scan_type_idc is inferred to be equal to 0.

[0186] nnpfe for human viewing ide equal to 3 specifies that the intended optimal usage of the video resulting from the NNPF process includes human viewing, nnpfc for human viewing ide equal to 2 specifies that the video resulting from the NNPF process is suitable but not specifically optimized for human viewing, nnpfe for human viewing ide equal to 1 specifies that the video resulting by the NNPF process is unsuitable for human viewing, mrpfe for human viewing ide equal to 0 specifies that it is unknown if the video resulting by the NNPF process is suitable for human viewing. When not present, nnpfe for human viewing ide is inferred to be equal to 0.

[0187] nnpfc for machine analysis idc equal to 3 specifies that the intended optimal usage of the video resulting from the NNPF process includes machine analysis, rmpfc for machine analysis idc equal to 2 specifies that the video resulting from the NNPF process is suitable but not specifically optimized for machine analysis, rmpfc for machine analysis idc equal to 1 specifics that the video resulting from the NNPF process is unsuitable for machine analysis, mipfc for machine analysis idc equal to 0 specifies that it is unknown if the videoP24092472301WO3; G25N21009W (4824-71003) resulting from the NNPF process is suitable for machine analysis. When not present, impfc for machine analysis idc is inferred to be equal to 0.

[0188] It is a requirement of bitstream conformance that the value of mrpfc for human viewing idc and nnpfc for machine analysis idc shall not be both equal to 1.

[0189] NOTE 5 - When a decoding system displays the video for human viewing, any NNPF that has impfc_for_human_viewing_idc equal to 1 is suggested to be omitted. When a decoding system performs machine analysis, any NNPF that has nnpfc for machine analysis idc equal to 1 is suggested to be omitted.

[0190] nnpfc reserved metadata extension shall not be present in bitstreams conforming to this version of this Specification. However, decoders conforming to this version of this Specification shall ignore the presence and value of nnpfc reserved metadata extension. When present, the length, in bits, of nnpfc_reserved_metadata_extension is equal to nnpfc_num_mctadata_cxtcnsion_bits - numSpccificdMctadataExtcnsionBits .

[0191] impfc alignment zero bit b shall be equal to 0.

[0192] nnpfc_payload_bytc| i ] contains the i-th byte of a bitstream conforming to ISO / IEC 15938-17. The byte sequence nnpfc_payload_bytc| i ] for all present values of i shall be a complete bitstream that conforms to ISO / IEC 15938-17.8.28.3 Neural-network post-filter activation SEI message8.28.3.1 Neural-network post-filter activation SEI message syntaxP24092472301WO3; G25N21009W (4824-71003)8.28.3.2 Neural-network post-filter activation SEI message semantics

[0193] The neural-network post-filter activation (NNPFA) SEI message activates or de-activates the possible use of the target neural-network post-processing filter (NNPF), identified by nnpfa target id and nnpfa target base flag, for post-processing filtering of a set of pictures. For a particular picture for which the NNPF is activated, the target NNPF is derived as follows:If nnpfa_target_base_flag is equal to 1, the target NNPF is the base NNPF with nnpfc id equal to nnpfa_target_id.Otherwise (nnpfa target base flag is equal to 0), the target NNPF is the NNPF specified by the last NNPFC SEI message with nnpfc id equal to nnpfa target id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repetition of the NNPFC SEI message that contains the base NNPF.

[0194] NOTE 1 - There can be several NNPFA SEI messages present for the same picture, for example, when the NNPFs are meant for different purposes or for filtering of different colour components.

[0195] nnpfa target id indicates the nnpfc id of the target NNPF, which is specified by one or more NNPFCSEI messages that pertain to the current picture and have nnpfc id equal to nnpfa target id. The value of nnpfa target id shall be in the range of 0 to 232- 2, inclusive.

[0196] An NNPFA SEI message with a particular value of nnpfa_target_id shall not be present in a current PU unless one or both of the following conditions are true:Within the current CLVS there is an NNPFC SEI message with nnpfc id equal to the particular value of nnpfa target id present in a PU preceding the current PU in decoding order.There is an NNPFC SEI message with nnpfc id equal to the particular value of nnpfa target id in the current PU.

[0197] When a PU contains both an NNPFC SEI message with a particular value of nnpfc id and an NNPFA SEI message with nnpfa target id equal to the particular value of nnpfc id, the NNPFC SEI message shall precede the NNPFA SEI message in decoding order.

[0198] nnpfa cancel flag equal to 1 indicates that the persistence of the target NNPF established by any previous NNPFA SEI message with the same nnpfa target id as the current SEI message is cancelled, i.e., the target NNPF is no longer used unless it is activated by another NNPFA SEI message with the same nnpfa target id as the current SEI message and nnpfa_cancel_flag equal to 0. nnpfa cancel flag equal to 0 indicates that the nnpfa_persistence flag, nnpfa target base flag, nnpfa no prcv clvs flag. nnpfa no foil civs flag (when nnpfa persistence flag is equal to 1). and nnpfa num output entries follow.

[0199] nnpfa_persistence_flag specifies the persistence of the target NNPF for the current layer.

[0200] nnpfa_persistence_flag equal to 0 specifies that the target NNPF may be used for post-processing filtering for the current picture only.P24092472301WO3; G25N21009W (4824-71003)

[0201] nnpfa_persistence_flag equal to 1 specifies that the target NNPF may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true:A new CL VS of the current layer begins.The bitstream ends.A picture in the current layer associated with an NNPFA SEI message with the same nnpfa_target_id as the current SEI message is output that follows the current picture in output order.

[0202] NOTE 2 - The target NNPF is not applied for this subsequent picture in the current layer associated with an NNPFA SEI message with the same nnpfa target id as the current SEI message.

[0203] Let nnpfcTargetPictures be the set of pictures to which the NNPFC SEI message corresponding to the target NNPF pertains. Let impfaTargetPictures be the set of pictures for which the target NNPF is activated by the current NNPFA SEI message. It is a requirement of bitstream conformance that any picture included in impfaTargetPictures shall also be included in nnpfcTargetPictures.

[0204] impfa target base flag equal to 1 specifies that the target NNPF is the base NNPF with nnpfe id equal to nnpfa target id. impfa target base flag equal to 0 specifies that the target NNPF is the NNPF specified by the last NNPFC SEI message with nnpfc_id equal to nnpfa target id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repetition of the NNPFC SEI message that contains the base NNPF.

[0205] NOTE 3 - An NNPFA message can activate a base NNPF with a particular nnpfe id value when an update of the base NNPF is active, which switches the target NNPF from the updated NNPF to the base NNPF.

[0206] When nnpfa_target_base_flag in an NNPFA SEI message is equal to 0, there shall be at least one NNPFC SEI message with nnpfc_id equal to nnpfa target id and nnpfe base flag equal to 0 that precedes the NNPFA SEI message in decoding order.

[0207] impfa_no_prev_clvs_flag equal to 1 specifies that the input pictures for the NNPF do not originate from a previous CLVS. nnpfa_no_prev_clvs_flag equal to 0 specifies that the input pictures for the NNPF may or may not originate from a previous CLVS.

[0208] NOTE 4 - The value of nnpfa_no_prev_clvs_flag can be changed from 0 to 1, when the current CLVS is spliced from another bitstream next to the previous CLVS and this NNPFA SEI message would cause one or more input pictures to be selected from one or more previous CLVSs and therefore is likely to impact the output of the target NNPF negatively.

[0209] nnpfa no foll clvs flag equal to 1 specifies that when this NNPFA SEI message persists for the last PU of a CLVS in output order, the NNPFA SEI message is treated like it persisted for the last PU, in output order, of the current layer within the bitstream. When this NNPFA SEI message does not persist for the last PU, in output order, of a CLVS in output order or nnpfa no foil civs flag is equal to 0, the value of nnpfa no foll clvs flag causes no specific impact.P24092472301WO3; G25N21009W (4824-71003)

[0210] NOTE 5 - The value of nnpfa_no_foll_clvs flag can be changed from 0 to 1 for a picture-rate- upsampling NNPF, when the following CLVS is spliced from a different bitstream next to the current CLVS. Consequently, the NNPF process interpolates pictures up to the end of the current CLVS using input pictures originating from the current CLVS only.

[0211] nnpfa num output entries specifies the number of nnpfa_output_flag[ i ] syntax elements present in the NNPFA SEI message. The value of nnpfa_num_output_entries shall be in the range of 0 to NumlnpPicsInOutputTensor, inclusive. When PictureRateUpsamplingFlag is equal to 0 and nnpfa num output entries is equal to NumlnpPicsInOutputTensor, nnpfa_output_flag[ i ] shall be equal to 1 for at least one value of i in the range of 0 to nnpfa num output entries - 1, inclusive.

[0212] nnpfa output flagf i ] equal to 1 specifies that the NNPF -generated picture that corresponds to the input picture having index Inpldx[ i ] is output by the NNPF process activated by this NNPFA SEI message, where the NNPF process is specified in the semantics of the NNPFC SEI message. nnpfa output flagf i ] equal to 0 specifies that the NNPF-generated picture that corresponds to the input picture having index Inpldx[ i ] is not output by the NNPF process activated by this NNPFA SEI message. When nnpfa num output entries is less than NumlnpPicsInOutputTensor, nnpfa_output_flag[ i ] is inferred to be equal to 1 for each value of i in the range of nnpfa num output entries to NumlnpPicsInOutputTensor - 1, inclusive.2.4 The SEI processing order (SPO) SEI message

[0213] JVET-AI2006 [4] includes the specification of an SEI message named the SEI processing order (SPO) SEI message, for carrying information indicating the preferred processing order, as determined by the encoder (i.e.. the content producer), for a group of types of SEI messages that may be present in a CVS.

[0214] An improved version of the specification of the SPO SEI message in IVET-AI2006 is as follows.P24092472301WO3; G25N21009W (4824-71003)8.30.1 SEI processing order SEI message8.30.1.1 SEI processing order SEI message syntax8.30.1.2 SEI processing order SEI message semantics

[0215] The SEI processing order (SPO) SEI message carries information indicating the preferred processing order, as determined by the encoder (i.e., the content producer), for a group of types of SEI messages that may be present in a CVS.

[0216] Use of this SEI message requires the definition of the following:Two lists of payloadType values, SeiProcessingOrderSeiList and SpoProcessSeiList.

[0217] The semantics of the SPO SEI message uses the concept of types of SEI messages. SEI messages that have different payloadType values are considered different types of SEI messages. Additionally, differentP24092472301WO3; G25N21009W (4824-71003)SEI messages that have the same payloadType value but are differentiated by values of syntax elements in the SEI payload are considered different types of SEI messages. Such differentiation by values of syntax elements in tire SEI payload is to be performed by comparing values sent using po_sei_prefix_data_bit[ i ] [ j ] syntax elements (when present) or values sent as SEI messages within a processing order nesting SEI message (when present). For example, neural-network post-filter characteristics (NNPFC) SEI messages can be differentiated by having different nnpfc id values.

[0218] When the i-th SEI message seiA in any SPO SEI message has po_sei_wrapping_flag[ i ] and po_sei_prefix_flag[ i ] both equal to 0, there shall be no other SEI message seiB included in the same SPO SEI message or in a different SPO SEI message in the current CVS for which all of the following are true:The value of po_sei_payload_type[ i ] of seiB is the same as that for seiA.The value of po_sei_wrapping_flag[ i ] of seiB is equal to 0.The value of po_sei_prefix_flag[ i ] of seiB is equal to 1.

[0219] When an SPO SEI message with a particular value of po id is present in any access unit of a CVS, an SPO SEI message with that particular value of po id shall be present in the first access unit of the CVS in decoding order. The number of SEI messages and the payloadType codes of the SEI messages indicated within each SPO SEI message with the same value of po id persist in decoding order from the current access unit until the end of the CVS in output order.

[0220] The SPO SEI message can carry’ one or more SEI prefix indications of a particular payloadType. When present, each SEI prefix indication is a bit string that follows the SEI payload syntax of that value of payloadType and contains a number of complete syntax elements starting from the first syntax element in the SEI payload. These SEI prefix indications should provide sufficient information to determine the specific processing order for ty pes of SEI messages having the same value of payloadType but a different preferred processing order.

[0221] po id contains an identifying number to identify’ the SPO SEI message.

[0222] A processing chain consists of a list of types of SEI messages identified by an SPO SEI message in the preferred processing order indicated in the SPO SEI message.

[0223] Each type of SEI message in the processing chain indicated by an SPO SEI message is identified by’ the syntax elements po_sei_payload_type[ i ], po sei wrapping _flag[ i ], po_sei_processing_order[ i ] and, when present, po_num_bits_in_prefix_indication_minus 1 [ i ] and po_prefix_data_bit[ i ][ j ].

[0224] An SEI message type is not required to belong to any processing chain and may belong to any number of processing chains identified by SPO SEI messages with different po id values.

[0225] Each SEI message of an SEI message type identified within the SPO SEI message has the same persistence scope as if the SEI message was carried outside of the SPO SEI message and not identified within an SPO SEI message.

[0226] NOTE 1 - When an SEI message specifies a process and is not associated with a processing chain specified by any SPO SEI message, it is implicitly a processing chain by itself. Some standards, such as Rec.P24092472301WO3; G25N21009W (4824-71003)ITU-T H.266 | ISO / IEC 23090-3, have specified an implicit processing chain of a super-resolution NNPF followed by another NNPF. Implicitly specified processing chains are treated like processing chains specified by SPO SEI messages when selecting SEI messages to be applied.

[0227] NOTE 2 - Processing chains can be alternatives to each other, i.e., such that at most processing chain is chosen to be applied, or they can be complementary, i.e., such that more than one processing chain is chosen and applied separately, with each processing chain generating one output.

[0228] po_for_human_viewing_idc equal to 3 specifies that the intended optimal usage of the video resulting from the processing chain specified by this SPO SEI message includes for human viewing, po for human viewing ide equal to 2 specifies that that the video resulting from the processing chain specified by this SPO SEI message is suitable but not specifically optimized for human viewing, po for human viewing idc equal to 1 specifies that the video resulting from the processing chain specified by this SPO SEI message is unsuitable for human viewing. po_for_human_viewing_idc equal to 0 specifies that it is unknown if the video resulting from the processing chain specified by this SPO SEI message is suitable for human viewing.

[0229] po for machine analysis idc equal to 3 specifies that the intended optimal usage of the video resulting from the processing chain specified by this SPO SEI message includes machine analysis, po for machine analysisidc equal to 2 specifies that the video resulting from the processing chain specified by this SPO SEI message is suitable but not specifically optimized for machine analysis, po for machine analysis idc equal to 1 specifies that the video resulting from the processing chain specified by this SPO SEI message is unsuitable for machine analysis, po for machine analysis ide equal to 0 specifies that it is unknown if the video resulting from the processing chain specified by this SPO SEI message is suitable for machine analysis.

[0230] It is a requirement of bitstream conformance that the value of po for human viewing idc and po for machine analysis idc shall not be both equal to 1.

[0231] NOTE 3 - The values of po for human viewing idc and po for machine analysis idc are in force for the output of a processing chain instead of the respective syntax elements in an encoder optimization information (EOI) SEI message (eoi for human viewing idc and eoi_for_machine_analysis_idc) or a neural- network post-filter characteristics (NNPFC) SEI message (nnpfe for human viewing ide and mipfc for machine analysis idc), when the EOI or NNPFC SEI message is associated with the processing chain.

[0232] po reserved zero 4bits shall be equal to 0. Values greater than 0 for po reserved zero 4bits are reserved for future use 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 allow any value of po_reserved_zero_4bits in the range of 0 to 15, inclusive.P24092472301WO3; G25N21009W (4824-71003)

[0233] po_num_sei_messages_minus2 plus 2 indicates the number of types of SEI messages for which the preferred order of processing is indicated in the SPO SEI message. The variable PoNumProcStgs is set equal to po_num_sei_messages_minus2 + 2.

[0234] po breadth first flag equal to 1 specifies that the breadth-first handling of a processing chain specified in clause 8.30.3.2 shall be applied to determine the pictures that are used for interpreting the semantics of the SEI messages applied as a part of the processing chain specified by this SPO SEI message. po_breadth_first flag equal to 0 specifies that the breadth-first handling of a processing chain specified in clause 8.30.3.2 or the depth-first handling of a processing chain specified in clause 8.30.3.3 shall be applied to determine the pictures that are used for interpreting the semantics of the SEI messages applied as a part of the processing chain specified by this SPO SEI message.

[0235] NOTE 4 - When po_breadth_first_flag is equal to 0, the processing chain can be performed for a picture without processing any SEI messages applying to subsequent picture units in output order.

[0236] po sei wrapping flagt i ] equal to 1 specifies that an SEI message that applies as the i-th SEI message type in the processing chain specified in this SPO SEI message, if present, is an SEI message that is included in a PON SEI message for which both of the following conditions are true: pon_target_po_id[ j ] with any value of j is equal to po id.There is a k-th loop entry' in the processing order nesting SEI message such that the payloadTy pc of the k-th nested SEI message is equal to po_sei_payload_type[ i ] and pon_processing_order[ k ] is equal to po_sei_processing_order[ i ].

[0237] po_sei_wrapping_flag[ i ] equal to 0 specifies that an SEI message that applies as the i-th SEI message type in the processing chain specified in this SPO SEI message, if present, is an SEI message that is not included in a PON SEI message and for which both of the following conditions are true:The payloadType of the SEI message is equal po_sei_payload_type[ i ]. po_sei_prefix_flag[ i ] is equal to 0. or when po_sei_prefix_flag[ i ] is equal to 1, the payload of the SEI message starts with the values of po_sei_prefix_data_bit[ i ][ j ].

[0238] NOTE 5 - po sei wrapping _flag[ i ] equal to 1 enables SEI messages to be carried within the processing order nesting SEI message to prevent such SEI messages from being incorrectly interpreted by decoders that do not process the SPO SEI message. Thus, po_sei_wrapping_flag[ i ] equal to 1 is intended to be used when po sei wrapping _flag[ i ] equal to 0 can lead to unintended results being produced by such decoders.

[0239] po sei importance _flag[ i ] equal to 1 affects the derivation of PoSeiList, which is the list of SEI messages that a decoding system should process for a particular picture picA, as specified below.

[0240] po_sei_importance_flag[ i ] equal to 0 specifies that when the decoding system cannot interpret or does not support the functionality indicated by the i-th SEI message type, it shall ignore all data associated with the loop variable value of i and exclude the i-th SEI message type from the processing chain performed by the decoding system.P24092472301WO3; G25N21009W (4824-71003)

[0241] po_sei_processing_degree_flag[ i ] affects the derivation of PoSeiList as specified below.

[0242] po_sci_payload_typc| i ] specifies the payloadType value of the i-th type of SEI message.

[0243] po_sei_prefix_flag[ i ] equal to 1 specifies that po_num_bits_in_prefix_indication_minus 1 [ i ] and some po_sei_prefix_data_bit[ i ][ j ] syntax elements are present. po_sei_prefix_flag[ i ] equal to 0 specifies that these syntax elements are not present.

[0244] The value of po_sei_payload_type[ i ] for each i in the range of 0 to po_num_sei_messages_minus2 + 1, inclusive, shall be equal to a value in SeiProcessingOrderSeiList.

[0245] When po_sei_payload_type[ i ] is equal to any value in SpoProcessSeiList, the i-th type of SEI message indicates a process.

[0246] spoPropcrtySciList is set to consist of the payloadType values included in SeiProcessingOrderSeiList excluding the paylaodType values included in SpoProcessSeiList. When po_sei_payload_type[ i ] is equal to any value in spoPropertySeiList, the i-th type of SEI message indicates a property.

[0247] po_sei_processing_order[ i ] indicates the preferred order of processing of the i-th type of SEI message for which preferred processing order information is provided in the SPO SEI message. For any two different integer values of m and n, po_sei_processing_order[ m ] less than po_sei_processing_order[ n ] indicates that the type of SEI message associated with index m should be processed before the type of SEI message associated with index n, and po_sei_processing_order[ m ] equal to po_sei_processing_order[ n ] indicates that there is no preferred order of processing between the types of SEI messages associated with indexes m and n (e.g.. they can indicate different properties that are both applicable at that stage, or one can indicate a property and the other can indicate a process).

[0248] For i greater than 0, po_sei_processing_order[ i ] shall be greater than or equal to po_sei_processing_order[ i - 1 ].

[0249] Let seiMsgA be an SEI message that applies as the i-th SEI message type in the processing chain specified in this SPO SEI message, persists for a particular picture picA, and is associated with po_sei_processing_order[ i ] equal to poValA.

[0250] Let seiMsgSet be a set of of SEI messages that consists of each SEI message for which all of the following conditions are true:The SEI message applies as the k-th SEI message type in the processing chain specified in this SPO SEI message with any value of k less than i.The SEI message persists for picA. po_sci_proccssing_ordcr[ k ] is less than poValA.The payloadType value of the SEI message is among the values included in SpoProcessSeiList.

[0251] The pictures to which the semantics of seiMsgA apply are specified as follows:P24092472301WO3; G25N21009W (4824-71003)If seiMsgSet is non-empty, the semantics of seiMsgA apply to all the pictures generated by the process implied by the SEI message that has the greatest value of po_sei_processing_order[ k ] among the SEI messages in seiMsgSet.Otherwise, the semantics of seiMsgA apply to picA.

[0252] NOTE 6 - When an NNPF process outputs more than one NNPF -generated picture, the semantics of an SEI message that follows the NNPF in the processing order apply to all these NNPF -generated pictures.

[0253] po_num_bits_in_prefix_indication_minus 1 [ i ] and po_sei_prefix_data_bit[ i ][ j ], when present, have the same semantics as the num_bits_in_prefix_indication_minus 1 [ i ] and sei_prefix_data_bit[ i ] [ j ] syntax elements of the SEI prefix indication SEI message, with prefix sei_payload type replaced by po_sei_payload_type[ i ].

[0254] When more than one SPO SEI message with a particular value of po id is present in a CVS, the values of po_num_sci_mcssagcs_minus2 and, for each value of i, the values of po_sci_wrapping_flag[ i ], po_sei_prefix_flag[ i ]. po_sei_importance_flag[ i ], po_sei_payload_type[ i ]. po_sei_processing_order[ i ] shall be the same as in the other SPO SEI messages in the CVS with the same value of po id.

[0255] po_byte_alignment_bit_equal_to_one shall be equal to 1 .

[0256] The lists PoProcStgldx, indicating the processing stage indices of the SEI message types in the processing chain, and PoSeiTypeldx, indicating the SEI message type indices of the processing stages in the processing chain, are derived as follows:For each of the SEI message types of in the processing chain, the following applies in a non-decreasing order of the corresponding po_sei_processing_order[ i ] values, with j being set equal to 0 initially:PoProcStgIdx[ i ] = jPoSeiTypeIdx[ j ] = i(xx) j++

[0257] Where PoProcStgIdx[ i ] indicates the processing stage index of the i-th SEI message type in the processing chain, and PoSciTypcIdx| j ] indicates the SEI message type index of the j-th processing stage in the processing chain.

[0258] For a picture, the list PoSeiList, indicting the list of SEI messages, associated with SEI message types in the processing chain indicated by the SPO SEI message, that may be applied to the picture, the list PoSeiTypeList, indicating the SEI message type indices of the SEI messages that may be applied to the picture, and the variable PoNumSeiMsgs, indicating the number of SEI messages that may be applied to the picture, are derived as follows:PoSeiList is initially empty, and j and PoNumSeiMsgs arc both initially set equal to 0.P24092472301WO3; G25N21009W (4824-71003)The following applies in the same non-decreasing order of po_sei_processing_order[ i ] values as above for deriving the lists PoProcStgldx and PoSeiTypeldx for all values of i in the range of 0 to po_num_sei_messages_minus2 + 1, inclusive, unless terminated earlier as specified below:When an SEI message seiA associated with the i-th SEI message type persists for picA. the following applies:- If the decoding system can interpret and supports the functionality indicated by seiA, seiA is added at the end of PoSeiList, PoSeiTypeList[ j ] is set equal to i, PoNumSeiMsgs is set equal to PoNumSciMsgs + 1, andj is set equal to j + 1.- Otherwise, if po_sei_importance_flag[ i ] is equal to 1 and po_sei_processing_degree_flag[ i ] is equal to 0, the derivation of PoSeiList, PoSeiTypeList, and PoNumSeiMsgs are terminated.Otherwise, if po_sei_importance_flag[ i ] is equal to 1 and po_sei_processing_degree_flag[ i ] is equal to 1, the processing chain specified by this SPO SEI message should not be performed for picA, PoSeiList is set to be empty, PoNumSeiMsgs is set equal to 0, and the derivation of PoSeiList, PoSeiTypeList, and PoNumSeiMsgs are terminated.2.5 VVC SEI payloadType values

[0259] In the semantics of the SPO SEI message, two lists are used. SeiProcessingOrderSeiList and SpoProcessSeiList, which are defined in JVET-AI2005 [5] as follows: SeiProcessingOrderSeiList is set to consist of the SEI payloadType values 3, 4, 5, 19, 137, 142, 144, 147, 148, 149, 150, 153, 155, 165, 177, 210, and 211, and SpoProcessSeiList is set to consist of the payloadType values 19, 142, 155, 210, and 211.

[0260] An improved definition of SeiProcessingOrderSeiList and SpoProcessSeiList is as follows (excluding 210, the SEI payloadType value for the NNPFC SEI message, and adding 45. the SEI payloadType value for the frame packing arrangement SEI message): SeiProcessingOrderSeiList is set to consist of the SEI payloadType values 3, 4, 5, 19, 45, 137, 142, 144, 147, 148, 149, 150, 153, 155, 165, 177, and 211, and SpoProcessSeiList is set to consist of the payloadType values 19, 45, 142, 155, and 211.

[0261] These SEI payloadType values are all included in the following syntax table in JVET-AI2005, which defines SEI payloadType values for all SEI messages that may be used in a WC bitstream:P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)P24092472301WO3; G25N21009W (4824-71003)2.6 Handling of a processing chain

[0262] As can be seen from the semantics of the SPO SEI message, a processing chain consists of a list of types of SEI messages identified by an SPO SEI message in the preferred processing order indicated in the SPO SEI message.

[0263] An improved version of the specification for handling of a processing chain specified in JVET- AI2006 is as follows.

[0264] In clause 3, add the following definitions (adjust the subclausc numbering when adding):3.1 corresponding picture: For a particular picture picA, the corresponding picture in a picture list is the picture in the picture list that is either picA itself or a processed version of picA generated when the process implied by an SEI message is applied.NOTE - The particular picture picA could be a picture that is not in the picture list, in which case the corresponding picture in the picture list is a processed version of picA. When picA is in the picture list, it's corresponding picture in the picture list is itselfP24092472301WO3; G25N21009W (4824-71003)3.2 inserted picture: A picture that was interpolated or extrapolated when the process implied by an SEI message (e.g., an NNPFA SEI message activating an NNPF with PictureRateUpsamplingFlag or TemporalExtrapolationFlag equal to 1) is applied.3.3 associated inserted picture: For a particular picture picA. an associated inserted picture in a picture list is a picture picB in the picture list that is the corresponding picture of an inserted picture generated when applying the process implied by an SEI message to a corresponding picture of picA.

[0265] NOTE - The particular picture picA could be a picture that is not in the picture list.8.30.2 Handling of a processing chain8.30.2.1 General

[0266] Processing chains are alternatives to each other, i.e., at most one processing chain can be chosen to be applied by a decoding system at one time.

[0267] A special NNPF cascading case is defined as the case when such two NNPFs arc both activated for a picture: one of the two NNPFs has nnpfc_purpose equal to 4 and the other has multiple input pictures, and neither of the two NNPFs is associated with an SPO SEI message. In this case, the two NNPFs are implicitly considered as belonging to one processing chain and the processing chain only contains these two NNPFs.

[0268] Except for the special NNPF cascading case, each processing chain containing multiple SEI message types is indicated by an SPO SEI message with a particular value of po id. Except for the special NNPF cascading case, any SEI message for which the payloadType is present in SpoProcessSeiList but is not indicated by an SPO SEI message is in its own processing chain.

[0269] In the special NNPF cascading case, PoNumProcStgs is set equal to 2, PoNumSeiMsgs is set equal to 2, and the following applies:1) If both of the NNPFs have nnpfc_purpose equal to 4 and multiple input pictures, either of the two is chosen to be applied first, and for the one chosen to be applied first. PoProcStgIdx[ i ] is set equal to 0, and PoSeiList

[0000] is set to be the NNPFA SEI message activating the NNPF, and for the other. PoProcStgIdx[ i ] is set equal to 1, and PoSeiList

[0001] is set to be the NNPFA SEI message activating the NNPF.2) Otherwise, PoProcStgldxf i ] corresponding to the NNPF with nnpfc_purpose equal to 4 is set equal to 0, PoProcStgIdx[ i ] corresponding to the NNPF with multiple input pictures is set equal to 1, PoSeiList

[0000] is set to be the NNPFA SEI message activating the NNPF with nnpfc_purpose equal to 4, and PoSeiListf 1 ] is set to be the NNPFA SEI message activing the NNPF with multiple input pictures.3) The values of po_sei_importance_flag

[0000] and po_sei_importance_flag

[0001] are both inferred to be equal to 0.

[0270] In case of a single SEI message in its own processing chain, PoNumProcStgs is set equal to 1, PoNumSeiMsgs is set equal to 1, PoProcStgldxf 0 ] is set equal to 0, po_sei_importance_flag

[0000] is inferred to be equal to 0, and PoSeiList

[0000] is set to be the single SEI message.P24092472301WO3; G25N21009W (4824-71003)

[0271] The PoSeiList for a corresponding picture of picA or for an associated inserted picture of picA is derived to be the same as the PoSeiList derived for picA.

[0272] A decoding system may choose and apply a processing chain according to the following ordered steps:1) The bitstream is decoded and a processing chain is chosen, and the following applies:The list PoCdoPicList is set to be the list of the cropped decoded output pictures in output order resulted from decoding the bitstream.When the SEI message type indicated by PoSeiTypeIdx

[0000] of the chosen processing chain corresponds to a fdm grain characteristics SEI message, the list PoDecPicList is set to be the list of the decoded pictures in output order resulted from decoding the bitstream.2) If the SEI message type indicated by PoSeiTypeIdx

[0000] of the chosen processing chain does not correspond to a fdm grain characteristics SEI message, the list CandInputPicList

[0000] is set to be identical to PoCdoPicList. Otherwise, the list CandInputPicList

[0000] is set to be identical to PoDecPicList.3) For each i in the range of 1 to PoNumProcStgs, inclusive, the list CandlnputPicListf i ] is set to be identical to PoCdoPicList.

[0273] NOTE 1 - The lists CandInputPicList[ i ] for i in the range of 1 to PoNumProcStgs, inclusive, may be updated during the next step. The list CandInputPicList[ PoNumProcStgs ] is for temporally storing the final output of the chosen processing chain.4) If the chosen processing chain is indicated by an SPO SEI message and po breadth first flag in the SPO SEI message is equal to 1, the breadth-first handling of a processing chain is invoked. Otherwise, either the depth- first handling of a processing chain or the breadth-first handling of a processing chain is invoked.When applying an NNPF to a picture during the invocation of a process for handling of a processing chain, the following applies:- The filtered and / or interpolated pictures are generated by the NNPF by applying the NNPF process specified in the semantics of the NNPFC SEI message, in a patch-wise manner, to the current picture.The order of the pictures generated by the NNPF by applying the NNPF process being stored into the output tensor of the NNPF is in output order.5) The list PoOutputPicList is set to be identical to CandlnputPicListf PoNumProcStgs ].

[0274] Regardless of which processing chain was chosen to be processed, the following constraints apply: Within PoOutputPicList there shall not be two pictures having the same output order.The pictures in PoOutputPicList shall be in increasing output order.

[0275] For each processing stage with processing stage index i in the range of 0 to PoNumProcStgs - 1, inclusive, the following applies:P24092472301WO3; G25N21009W (4824-71003)For any particular pair of pictures inputPicA and inputPicB consecutive in output order in CandInputPicList[ i ], which is the list of candidate input pictures for the processing stage, when there are one or more pictures intemiediatePicSetA between inputPicA and inputPicB in output order added to CandInputPicList[ i + 1 ] when applying the process implied by a particular SEI message of the processing stage, one and only one of the following shall apply:The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with PictureRateUpsamplingFlag equal to 1 of the processing stage when a particular picture currPicA in CandInputPicList[ i ] was the current picture.The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with TemporalExtrapolationFlag equal to 1 of the processing stage when a particular picture currPicA in CandInputPicList[ i ] was the current picture.The application of the process implied by the particular SEI message when another picture other than currPicA was the current picture or the application of the process implied by of another SEI message of the same processing stage when any picture (including currPicA) was the current picture shall not output any picture between the inputPicA and inputPicB in output order.

[0276] NOTE 2 - The intent of the constraints expressed above is to disallow generating output pictures between any particular pair of consecutive input pictures more than once within a processing stage.8.30.2.2 Breadth-first handling of a processing chain

[0277] For each SEI message types, with SEI message type index i, of the chosen processing chain, the following applies in increasing order of the corresponding processing stage index PoProcStgIdx[ i ] values:The following applies for each picture picA in CandInputPicList[ PoProcStgIdx[ i ] ] in output order, when an SEI message associated with the i-th SEI message type is present in PoSeiList of picA:- When PoProcStgIdx[ i ] is greater than 0, the following applies for the interpretation of the SEI message:The interface variables for purposes of interpretation of the SEI message are derived from picA. The semantics of the SEI message, or the semantics of the SEI message and, when the SEI message is an NNPFA SEI message, the associated NNPFC SEI message, apply to pictures in CandInputPicList[ PoProcStgldxf i ] ].When the SEI payloadType value of the i-th SEI message type is present in SpoProcessSeiList, the process implied by the SEI message is performed and each list CandInputPicList[ PoProcStgldxf i ] + j ] with j in the range of 1 to PoNumProcStgs - PoProcStgIdx[ i ], inclusive, is updated by replacing pictures with the corresponding processed pictures, if any, resulting from the process and inserting the other pictures, if any?, resulting from the process into CandInputPicList[ PoProcStgIdx[ i ] + j ] so that the output order is obeyed. When the SEI message is a film grain characteristics SEI message, PoProcStgldxf i ]P24092472301WO3; G25N21009W (4824-71003) is equal to 0, and j is equal to 1, during the replacement of a picture in CandInputPicList

[0001] with the corresponding processed picture or inserting a picture into CandInputPicList

[0001] , the corresponding processed picture or the picture to be inserted is first cropped, in the same manner as generating a cropped decoded output picture from the corresponding decoded picture, and the cropped picture is used for the replacement or insertion.8.30.2.3 Depth-first handling of a processing chain

[0278] The following is repeatedly applied, in output order, for each picture picA in CandInputPicList

[0000] : The following applies for each SEI message with SEI message index seildx in PoSeiList of picA in increasing order of list indexes for PoSeiList:When PoProcStgIdx[ PoSeiTypeList[ seildx ] ] is greater than 0, the following applies for the interpretation of the SEI message:The interface variables for purposes of interpretation of tire SEI message are derived from the pictures in CandlnputPicListf PoProcStgIdx[ PoSciTypcList| seildx ] ] ].The semantics of the SEI message, or of the SEI message and, when the SEI message is an NNPFA SEI message, the associated NNPFC SEI message, apply to pictures in CandInputPicList[ PoProcStgldxf PoSeiTypeListf seildx ] ] ].When the SEI payloadType value of the SEI message is present in SpoProcessSeiList, the process implied by the SEI message is invoked repeatedly, in output order, for picA and each of the pictures in CandlnputPicListf PoProcStgIdx[ PoSeiTypeListf seildx ] ] ] that is picA or an associated inserted picture of picA. After each invocation of the process, each list CandlnputPicListf PoProcStgldxf PoSeiTypeListf seildx ] ] + j ] with j in the range of 1 to PoNumProcStgs - PoProcStgldxf PoSeiTypeListf seildx ] ], inclusive, is updated by replacing pictures with the corresponding processed pictures, if any, resulting from the process and inserting the other pictures, if any, resulting from the process into CandlnputPicListf PoProcStgldxf PoSeiTypeListf seildx ] ] + j ] so that the output order is obeyed. When the SEI message is a film grain characteristics SEI message, PoProcStgldxf PoSeiTypeListf seildx ] ] is equal to 0, and j is equal to 1. during the replacement of a picture in CandlnputPicListf 1 ] with the corresponding processed picture or inserting a picture into CandlnputPicListf 1 ], the corresponding processed picture or the picture to be inserted is first cropped, in the same manner as generating a cropped decoded output picture from the corresponding decoded picture, and the cropped picture is used for the replacement or insertion.3. Technical problems solved by disclosed technical solutions

[0279] An example design for the neural-network post-filter characteristics (NNPFC) SEI message and the neural -network post-filter activation (NNPFA) SEI message do not work in the context of a processing chain on many aspects, including:P24092472301WO3; G25N21009W (4824-71003)

[0280] First, the input pictures of an NNPF are specified as cropped decoded output pictures. However, in the context of a processing chain, an input picture to an NNPF in the context of a processing chain can also be the corresponding picture or an associated inserted picture of a cropped decoded output picture.

[0281] Second, it is specified that the post-filtering process associated with an NNPF, which is specified by an NNFPC SEI message and activated by an NNPFA SEI message, may be applied to cropped decoded output pictures. However, the process can also be applied to the corresponding picture or an associated inserted picture of a to cropped decoded output picture.

[0282] Third, use of the NNPFC and NNPA SEI message requires the definition of the variable SeiProcStgldx, which indicates the processing stage index associated with the NNPF within a chosen processing chain; but that is missing.

[0283] Fourth, use of the NNPFC and NNPA SEI message requires the definition of the list CandInputPicList[ SeiProcStgldx ], which contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded: but that is missing.

[0284] Fifth, the variables CroppedWidth and CroppedHeight are defined as the picture width and height in units of luma samples, respectively, of cropped decoded output pictures. However, since in the context of a processing chain, an input picture to an NNPF in the context of a processing chain can also be the corresponding picture or an associated inserted picture of a cropped decoded output picture, the variables need to be specified as the picture width and height of the input pictures instead.

[0285] Sixth, the variable ChromaFormatldc is defined as the chroma format indicator of cropped decoded output pictures. Similarly as above, the variable needs to be specified as the chroma format indicator of the input pictures instead.

[0286] Seventh, it is specified that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that the NNPF expects an input picture that is not present in the bitstream to be represented by sample arrays with sample values equal to 0, and nnpfc_absent_input_pic_zero flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the bitstream to be represented by the input picture inputPicB that is the closest to inputPicA in output order and is present in the bitstream. However, the context in which an input picture is present or not should be in the candidate input picture list, i.c., CandInputPicList[ SeiProcStgldx ], not in the bitstream.4. A listing of solutions and embodiments

[0287] To solve the above-described problems, methods as summarized below are disclosed. The aspects should be considered as examples to explain the general concepts and should not be interpreted in a narrow way. Furthermore, these examples can be applied individually or combined in any manner.1) In one example, it is specified that use of the NNPFC SEI message requires the definition of the variable SeiProcStgldx, which indicates the processing stage index associated with the NNPF within a chosen processing chain.P24092472301WO3; G25N21009W (4824-71003)2) In one example, it is specified that use of the NNPFC SEI message requires the definition of the list CandInputPicList[ SeiProcStgldx ], which contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded. a. In one example, it is specified that, when SeiProcStgldx is equal to 0, pictures in CandInputPicList[ SeiProcStgldx ] are cropped decoded output pictures. b. In one example, it is specified that, when SeiProcStgldx is greater than 0, the list CandInputPicList[ SeiProcStgldx ] contains pictures after the application of the process(es) implied by the SEI mcssagc(s) associated with processing stage index values less than SeiProcStgldx.3) In one example, it is specified that use of the NNPFC SEI message requires the definition of the variables CroppedWidth and CroppedHeight, which inidcated the input picture width and height in units of luma samples, respectively, of the input pictures.4) In one example, it is specified that use of the NNPFC SEI message requires the definition of the variable ChromaFormatldc, which indicates the chroma format indicator, of the input pictures.5) In one example, it is specified that use of the NNPFA SEI message requires the definition of the variable SeiProcStgldx, which indicates the processing stage index associated with the NNPF within a chosen processing chain.6) In one example, it is specified that use of the NNPFA SEI message requires the definition of the list CandInputPicList[ SeiProcStgldx ], which contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded. a. In one example, it is specified that, when SeiProcStgldx is equal to 0, pictures in CandInputPicList[ SeiProcStgldx ] are cropped decoded output pictures. b. In one example, it is specified that, when SeiProcStgldx is greater than 0, the list CandInputPicList[ SeiProcStgldx ] contains pictures after the application of the process(es) implied by the SEI message(s) associated with processing stage index values less than SeiProcStgldx.7) In one example, it is specified that nnpfa pcrsistencc flag equal to 0 specifies that the NNPFA SEI message persists for the current picture only. a. Alternatively, in one example, it is specified that nnpfa_persistence_flag equal to 0 specifies that the NNPFA SEI message persists for the current picture and its associated inserted pictures only8) In one example, it is specified nnpfa_persistence_flag equal to 1 specifies that the NNPFA SEI message persists for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: a. A new coded layer video sequence (CLVS) of the current layer begins. b. The bitstream ends.P24092472301WO3; G25N21009W (4824-71003) c. A picture in the current layer associated with an NNPFA SEI message with the same nnpfa_target_id as the current SEI message is output that follows the current picture in output order.9) Alternatively, in one example, it is specified nnpfa_persistence_flag equal to 1 specifies that the NNPFA SEI message persists for the current picture and its associated inserted pictures, and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: a. A new CLVS of the current layer begins. b. The bitstream ends. c. A picture in the current layer associated with an NNPFA SEI message with the same nnpfa target id as the current SEI message is output that follows the current picture in output order.10) In one example, it is specified that, let nnpfcTargetPictures be the set of pictures to which the NNPFC SEI message corresponding to the target NNPF pertains, let nnpfaTargetPictures be the set of pictures for which the NNPFA SEI message persists, it is a requirement of bitstream conformance that any picture included in nnpfaTargetPictures shall also be included in nnpfcTargetPictures.11) In one example, it is specified that, the value of nnpfa no prev civs flag can be changed from 0 to 1. when the current CLVS is spliced from another bitstream next to the previous CLVS and this NNPFA SEI message would cause one or more input pictures originating from one or more previous CLVSs to be selected and therefore is likely to impact the output of the target NNPF negatively.12) In one example, it is specified that the post-filtering process associated with an NNPF, which is specified by an NNFPC SEI message and activated by an NNPFA SEI message, may be applied to a picture that is the corresponding picture or an associated inserted picture of a picture for which the NNPFA SEI message activating the NNPF persists.13) In one example, it is specified that the input picture with index 0 for an NNPF is a picture in CandInputPicList[ SeiProcStgldx ] that is a corresponding picture of currCdoPic or is an associated inserted picture of currCdoPic, where currCdoPic is a cropped decoded output picture for which the NNPF defined by this NNPFC SEI message is activated by an NNPFA SEI message. a. Additionally, in one example, it is specified that the input picture with index i in the range of 1 to numlnputPics - 1, inclusive, is the picture in CandInputPicList[ SeiProcStgldx ] that immediately precedes the input picture with index i - 1 in output order.14) In one example, it is specified that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that the NNPF expects an input picture that is not present in CandInputPicList[ SeiProcStgldx ] to be represented by sample arrays with sample values equal to 0, and nnpfc_absent_input_pic_zero_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in CandInputPicList[ SeiProcStgldx ] to be represented by the input picture inputPicB that is the closest to inputPicA in output order and is present in CandInputPicList[ SeiProcStgldx ].P24092472301WO3; G25N21009W (4824-71003)5. Embodiments

[0288] Below are some example embodiments for some of the aspects summarized above in Section 4. Some of the added or modified texts are indicated with double braces { { } }, and some of the deleted parts are indicated with triple brackets [[[ ]]].5.1 First embodimentIn clause 3. add the following definitions (adjust the subclause numbering when adding):3.1 corresponding picture: For a particular picture picA, the corresponding picture in a picture list is the picture in the picture list that is either picA itself or a processed version of picA generated when the process implied by an SEI message is applied.NOTE - The particular picture picA could be a picture that is not in the picture list, in which case the corresponding picture in the picture list is a processed version of picA. When picA is in the picture list, it's corresponding picture in the picture list is itself.3.2 inserted picture: A picture that was interpolated or extrapolated when the process implied by an SEI message (e.g., an NNPFA SEI message activating an NNPF with PictureRateUpsamplingFlag or TemporalExtrapolationFlag equal to 1) is applied.3.3 associated inserted picture: For a particular picture picA, an associated inserted picture in a picture list is a picture picB in the picture list that is the corresponding picture of an inserted picture generated when applying the process implied by an SEI message to a corresponding picture of picA.NOTE - The particular picture picA could be a picture that is not in the picture list.8.28.1 [[[General post-processing filtering process using NNPFs]]]8.28.1.1 [[[General]]]

[0289] [[[Input to this process is a bitstream BitstreamToFilter. Output of this process is a list of NNPF output pictures ListNnpfOutputPics.]]]

[0290] [[[First, BitstreamToFilter is decoded, and the list CroppedDecodedPictures is set to be the list of the cropped decoded pictures in output order resulted from decoding BitstreamToFilter.]]]

[0291] [[[Second, the filtering process for one picture, as specified in clause 8.28.1.2, is repeatedly invoked, in output order, for each cropped decoded picture that is in CroppcdDccodcdPicturcs and for which one or more NNPFs are activated.]]]

[0292] [[[The order of the pictures in ListNnpfOutputPics is in output order.]]]

[0293] [[[Within ListNnpfOutputPics there shall be no more than one picture pertaining to any particular output time instance. When for any particular picture in CroppedDecodedPictures there are multiple NNPFs activated and only one of the NNPFs is allowed to be chosen to be applied although any of the NNPFs may beP24092472301WO3; G25N21009W (4824-71003) chosen, the above constraint shall apply regardless of which NNPF is chosen to be applied to the particular picture.]]]

[0294] [[[For any particular pair of pictures inputPicA and inputPicB consecutive in output order in CroppedDecodedPictures, when there are one or more pictures intermediatePicSetA in ListNnpfOutputPics between inputPicA and inputPicB in output order, one and only one of the following shall apply:]]]

[0295] -[[[The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with PictureRateUpsamplingFlag equal to 1 when a particular picture currPicA in CroppedDecodedPictures was the current picture. ]]]

[0296] -[[[The pictures in intermediatePicSetA shall be among the pictures that were output by applying a particular NNPF nnpfA with TemporalExtrapolationFlag equal to 1 when a particular picture currPicA in CroppedDecodedPictures was the current picture.]]]

[0297] [[[The application of any other NNPF that was used in the filtering process for one picture when currPicA was the current picture or the application of any NNPF (including nnpfA) that was used in the filtering process for one picture when any other picture currPicB in CroppedDecodedPictures was the current picture shall not output any picture between the inputPicA and inputPicB in output order.]]]

[0298] [[[NOTE - The intent of the constraints expressed in the above paragraph is to disallow generating NNPF output pictures between any particular pair of consecutive input pictures more than once.]]]8.28.1.2 [[[Filtering process for one picture using an NNPF]]]

[0299] [[[The filtering process specified in this clause applies to each cropped decoded picture, referred to as the current picture, that is in CroppedDecodedPictures and for which one or more NNPFs are activated.

[0300] [[[When applying an NNPF to the current picture, the following applies:]]][[[The filtered and / or interpolated pictures are generated by the NNPF by applying the NNPF process specified in the semantics of the NNPFC SEI message, in a patch-wise manner, to the current picture.]]] [[[The order of the pictures generated by the NNPF by applying the NNPF process being stored into the output tensor of the NNPF is in output order.]]]

[0301] [[[When the applied NNPF is the last NNPF that is applied to the current picture, the pictures generated by the NNPF and output by the NNPF process are included into ListNnpfOutputPics, in the same order as when the pictures are stored into the output tensor of the NNPF.]]]8.28.1 Neural-network post-filter characteristics SEI message8.28.1.1 Neural-network post-filter characteristics SEI message syntax(unchanged)8.28.1.2 Neural-network post-filter characteristics SEI message semantics

[0302] The neural-network post-filter characteristics (NNPFC) SEI message specifies a neural network that may be used as a post-processing filter. The use of specified neural-network post-processing filters (NNPFs) for specific pictures is indicated with neural-network post-filter activation (NNPFA) SEI messages.P24092472301WO3; G25N21009W (4824-71003)

[0303] Use of this SEI message requires the definition of the following variables:- { {The processing stage index SeiProcStgldx that indicates the processing stage index associated with the NNPF within a chosen processing chain. } }{ {The list CandInputPicList[ SeiProcStgldx ] that contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded. When SeiProcStgldx is equal to 0, pictures in CandInputPicList[ SeiProcStgldx ] are cropped decoded output pictures.}}

[0304] {{NOTE 1 - When SeiProcStgldx is greater than 0, the list CandInputPicList[ SeiProcStgldx ] contains pictures after the application of the process(es) implied by the SEI message(s) associated with processing stage index values less than SeiProcStgldx. } }- Input picture width and height in units of luma samples, denoted herein by CroppedWidth and CroppedHeight, respectively { {. of the input pictures.}}Luma sample array CroppedYPicf idx ] and chroma sample arrays CroppedCbPic[ idx ] and CroppedCrPic[ idx ], when present, of the input pictures with index idx in the range of 0 to numlnputPics - 1 , inclusive, that are used as input for the NNPF.- Bit depth BitDepthY for the luma sample array of the input pictures.- Bit depth BitDepthC for the chroma sample arrays, if any, of the input pictures.Chroma format indicator ChromaFormatldc, as described in clause 7.3 { {, of the input pictures.} }- When nnpfe auxiliary inp ide is equal to 1, a filtering strength control value array StrengthControlVal[ idx ] that shall contain real numbers in the range of 0 to 1, inclusive, of the input pictures with index idx in the range of 0 to numlnputPics - 1, inclusive.

[0305] { {Let currCdoPic be a cropped decoded output picture for which the NNPF defined by this NNPFCSEI message is activated by an NNPFA SEI message. Let currPic be a picture in CandInputPicList[ SeiProcStgldx ] that is a corresponding picture of currCdoPic or is an associated inserted picture of currCdoPic. } }

[0306] Input picture with index 0 [[[corresponds to the picture for which the NNPF defined by this NNPFC SEI message is activated by an NNPFA SEI message]]] {{is the picture currPic}}. Input picture with index i in the range of 1 to numlnputPics - 1, inclusive{{, is the picture in CandInputPicList[ SeiProcStgldx ] that immediately} } precedes the input picture with index i - 1 in output order.

[0307] The variables SubWidthC and SubHeightC are derived from ChromaFormatldc as specified by Table 2.

[0308] NOTE 1 - More than one NNPFC SEI message can be present forthe same picture. When more than one NNPFC SEI message with different values of nnpfe id is present or activated for the same picture, they can have the same value or different values of nnpfc_purpose and the same value or different values of impfc mode idc.P24092472301WO3; G25N21009W (4824-71003)

[0309] nnpfc_absent_input_pic_zero flag equal to 1 indicates that the NNPF expects an input picture that is not present in [[[the bitstream]]] { {CandlnputPicListf SeiProcStgldx ]} } to be represented by sample arrays with sample values equal to 0. nnpfc absent input _pic_zero_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in [[[the bitstream]]] ] {CandInputPicList[ SeiProcStgldx ]}} to be represented by the input picture inputPicB that is the closest to inputPicA in output order and is present in [[[the bitstream]]] {{CandInputPicList[ SeiProcStgldx ]}}.8.28.2 Neural-network post-filter activation SEI message8.28.2.1 Neural-network post-filter activation SEI message syntax(unchanged)8.28.2.2 Neural-network post-filter activation SEI message semantics

[0310] The neural-network post-filter activation (NNPF A) SEI message activates or de-activates the possible use of the target neural-network post-processing filter (NNPF), identified by nnpfa targct id and nnpfa target base flag, for post-processing filtering of a set of pictures. [[[For a particular picture for which the NNPF is activated, the]]] ] {The} } target NNPF is derived as follows:If nnpfa target base flag is equal to 1, the target NNPF is the base NNPF with nnpfc id equal to nnpfa_target_id .Otherwise (nnpfa target base flag is equal to 0), the target NNPF is the NNPF specified by the last NNPFC SEI message with nnpfc id equal to mipfa target id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repetition of the NNPFC SEI message that contains the base NNPF.

[0311] NOTE 1 - There can be several NNPFA SEI messages present for the same picture, for example, when the NNPFs are meant for different purposes or for filtering of different colour components.

[0312] { {Use of this SEI message requires the definition of the following variables: } }{ {The processing stage index SeiProcStgldx that indicates the processing stage index associated with the target NNPF within a chosen processing chain.} }{ {The list CandlnputPicListf SeiProcStgldx ] that contains a list of pictures in output order from which the input pictures for the target NNPF are selected or padded. When SeiProcStgldx is equal to 0, pictures in CandInputPicList[ SeiProcStgldx ] are cropped decoded output pictures.}}{ {NOTE 2 - When SeiProcStgldx is greater than 0, the list CandlnputPicListf SeiProcStgldx ] contains pictures after the application of the process(es) implied by the SEI message(s) associated w ith processing stage index values less than SeiProcStgldx. } }

[0313] {{The target NNPF may be used for post-processing filtering for each picture in CandlnputPicListf SeiProcStgldx ] that is the corresponding picture or an associated inserted picture of a picture for which the NNPFA SEI message persists.}}P24092472301WO3; G25N21009W (4824-71003)

[0314] nnpfa_target_id indicates the nnpfc id of the target NNPF, which is specified by one or more NNPF CSEI messages that pertain to the current picture and have nnpfc id equal to nnpfa target id. The value of nnpfa target id shall be in the range of 0 to 232- 2. inclusive.

[0315] An NNPFA SEI message with a particular value of nnpfa target id shall not be present in a current PU unless one or both of the following conditions are true:Within the current CLVS there is an NNPFC SEI message with nnpfc id equal to the particular value of nnpfa_target_id present in a PU preceding the current PU in decoding order.There is an NNPFC SEI message with nnpfc id equal to tire particular value of nnpfa target id in the current PU.

[0316] When a PU contains both an NNPFC SEI message with a particular value of nnpfc id and an NNPFA SEI message with nnpfa_target_id equal to the particular value of nnpfc id, the NNPFC SEI message shall precede the NNPFA SEI message in decoding order.

[0317] impfa cancel flag equal to 1 indicates that the persistence of the target NNPF established by any previous NNPFA SEI message with the same nnpfa target id as the current SEI message is cancelled, i.e.. the target NNPF is no longer used unless it is activated by another NNPFA SEI message with the same nnpfa target id as the current SEI message and nnpfa_cancel_flag equal to 0. impfa cancel flag equal to 0 indicates that the nnpfa_persistence_flag, nnpfa_target_base_flag, nnpfa_no_prev_clvs_flag, nnpfa no foll clvs flag (when nnpfa_persistence_flag is equal to 1), and nnpfa num output entries follow.

[0318] nnpfa_persistence_flag specifies the persistence of the target NNPF for the current layer.

[0319] nnpfa_persistence_flag equal to 0 specifies that [[[the target NNPF may be used for post-processing filtering]]] { {the NNPFA SEI message persists} } for the current picture only.

[0320] nnpfa_persistence_flag equal to 1 specifies that [ [ [the target NNPF may be used for post-processing filtering]]] { {the NNPFA SEI message persists} } for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true:A new CLVS of the current layer begins.The bitstream ends.A picture in the current layer associated with an NNPFA SEI message with the same nnpfa_targct_id as the current SEI message is output that follows the current picture in output order.

[0321] NOTE 2 - The target NNPF is not applied for this subsequent picture in the current layer associated with an NNPFA SEI message with the same nnpfa target id as the current SEI message.

[0322] Let nnpfcTargetPictures be the set of pictures to which the NNPFC SEI message corresponding to the target NNPF pertains. Let impfaTargetPictures be the set of pictures for which [[[the target NNPF is activated by the current NNPFA SEI message]]] the NNPFA SEI message persists. It is a requirement of bitstream conformance that any picture included in impfaTargetPictures shall also be included in nnpfcTargetPictures.P24092472301WO3; G25N21009W (4824-71003)

[0323] nnpfa_target_base flag equal to 1 specifies that the target NNPF is the base NNPF with nnpfc id equal to nnpfa target id. nnpfa target base flag equal to 0 specifies that the target NNPF is the NNPF specified by the last NNPFC SEI message with nnpfc id equal to nnpfa target id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repetition of the NNPFC SEI message that contains the base NNPF.

[0324] NOTE 3 - An NNPFA message can activate a base NNPF with a particular nnpfc id value when an update of the base NNPF is active, which switches the target NNPF from the updated NNPF to the base NNPF.

[0325] When nnpfa target base flag in an NNPFA SEI message is equal to 0, there shall be at least one NNPFC SEI message with nnpfc id equal to nnpfa target id and nnpfc base flag equal to 0 that precedes the NNPFA SEI message in decoding order.

[0326] nnpfa_no_prev_clvs_flag equal to 1 specifies that the input pictures for the NNPF do not originate from a previous CLVS. nnpfa_no_prev_clvs_flag equal to 0 specifies that the input pictures for the NNPF may or may not originate from a previous CLVS.

[0327] NOTE 4 - The value of nnpfa_no_prev_clvs_flag can be changed from 0 to 1, when the current CLVS is spliced from another bitstream next to the previous CLVS and this NNPFA SEI message would cause one or more input pictures [[[to be selected]]] { {originating} } from one or more previous CLVSs to be selected and therefore is likely to impact the output of the target NNPF negatively.

[0328] impfa no foll clvs flag equal to 1 specifies that when the NNPFA SEI message persists for the last PU of a CLVS in output order, the NNPFA SEI message is treated like it persisted for the last PU, in output order, of the current layer within the bitstream. When the NNPFA SEI message does not persist for the last PU, in output order, of a CLVS in output order or nnpfa_no_foll_clvs_flag is equal to 0, the value of impfa no foll clvs flag causes no specific impact.

[0329] NOTE 5 - The value of nnpfa no foll clvs flag can be changed from 0 to 1 for a picture-rate- upsampling NNPF, when the following CLVS is spliced from a different bitstream next to the current CLVS. Consequently, the NNPF process interpolates pictures up to the end of the current CLVS using input pictures originating from the current CLVS only.

[0330] nnpfa num output entries specifies the number of nnpfa_output_flag[ i ] syntax elements present in the NNPFA SEI message. The value of nnpfa num output entries shall be in the range of 0 to NumlnpPicsInOutputTensor. inclusive. When PictureRateUpsamplingFlag is equal to 0 and nnpfa num output entries is equal to NumlnpPicsInOutputTensor, nnpfa_output_flag[ i ] shall be equal to 1 for at least one value of i in the range of 0 to nnpfa num output entries - 1, inclusive.

[0331] nnpfa_output_flag[ i ] equal to 1 specifies that the NNPF -generated picture that corresponds to the input picture having index Inpldx[ i ] is output by the NNPF process activated by this NNPFA SEI message, where the NNPF process is specified in the semantics of the NNPFC SEI message, nnpfa output flag [ i ] equal to 0 specifies that the NNPF -generated picture that corresponds to the input picture having index Inpldxf i ] is notP24092472301WO3; G25N21009W (4824-71003) output by the NNPF process activated by this NNPFA SEI message. When nnpfa num output entries is less than NumlnpPicsInOutputTensor, nnpfa_output_flag[ i ] is inferred to be equal to 1 for each value of i in the range of nnpfa num output entries to NumlnpPicsInOutputTensor - 1, inclusive.6. References[1] ITU-T and ISO / IEC. '‘High efficiency video coding”. Rec. ITU-T H.265 | ISO / IEC 23008-2 (in force edition).[2] ITU-T and ISO / IEC, “Versatile Video Coding”, Rec. ITU-T H.266 | ISO / IEC 23090-3.[3] ITU-T and ISO / IEC, “Versatile Supplemental Enhancement Information Messages for Coded Video Bitstreams”, Rec. ITU-T Rec. H.274 | ISO / IEC 23002-7.[4] J. Boyce, J. Chen, S. Deshpande. M. M. Hannuksela. S. McCarthy, G. J. Sullivan, H. Tan, and Y.-K. Wang (editors), JVET-AI2006, “Additional SEI messages for VSEI version 4 (Draft 3)”.[5] G. J. Sullivan, B. Bross, M. M. Hannuksela, and Y.-K. Wang (editors), JVET-AI2005, “Additions and corrections for WC version 4 (Draft 9)”.

[0332] FIG. 2 is a block diagram showing an example video processing system 4000 in which various techniques disclosed herein may be implemented. Various implementations may include some or all of the components of the system 4000. The system 4000 may include input 4002 for receiving video content. The video content may be received in a raw or uncompressed format, e.g., 8 or 10 bit multi-component pixel values, or may be in a compressed or encoded format. The input 4002 may represent a network interface, a peripheral bus interface, or a storage interface. Examples of network interface include wired interfaces such as Ethernet, passive optical network (PON), etc. and wireless interfaces such as wireless fidelity (Wi-Fi) or cellular interfaces.

[0333] The system 4000 may include a coding component 4004 that may implement the various coding or encoding methods described in the present disclosure. The coding component 4004 may reduce the average bitrate of video from the input 4002 to the output of the coding component 4004 to produce a coded representation of the video. The coding techniques are therefore sometimes called video compression or video transcoding techniques. The output of the coding component 4004 may be either stored, or transmitted via a communication connected, as represented by the component 4006. The stored or communicated bitstream (or coded) representation of the video received at the input 4002 may be used by a component 4008 for generating pixel values or displayable video that is sent to a display interface 4010. The process of generating user-viewable video from the bitstream representation is sometimes called video decompression. Furthermore, while certain video processing operations are referred to as “coding” operations or tools, it will be appreciated that the coding tools or operations are used at an encoder and corresponding decoding tools or operations that reverse the results of the coding will be performed by a decoder.

[0334] Examples of a peripheral bus interface or a display interface may include universal serial bus (USB) or high definition multimedia interface (HDMI) or Displayport, and so on. Examples of storage interfaces include serial advanced technology attachment (SATA), peripheral component interconnect (PCI), integrated drive electronics (IDE) interface, and the like. The techniques described in the present disclosure may be embodied inP24092472301WO3; G25N21009W (4824-71003) various electronic devices such as mobile phones, laptops, smartphones or other devices that are capable of performing digital data processing and / or video display.

[0335] FIG. 3 is a block diagram of an example video processing apparatus 4100. The apparatus 4100 may be used to implement one or more of the methods described herein. The apparatus 4100 may be embodied in a smartphone, tablet, computer, Internet of Things (loT) receiver, and so on. The apparatus 4100 may include one or more processors 4102, one or more memories 4104 and video processing circuitry 4106. The processor(s) 4102 may be configured to implement one or more methods described in the present disclosure. The memory (memories) 4104 may be used for storing data and code used for implementing the methods and techniques described herein. The video processing circuitry 4106 may be used to implement, in hardware circuitry, some techniques described in the present disclosure. In some embodiments, the video processing circuitry 4106 may be at least partly included in the processor 4102, e g., a graphics co-processor.

[0336] FIG. 4 is a flowchart for an example method 4200 of video processing. The method 4200 determines that that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network post-filter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0 at step 4202. In an embodiment, nnpfc_absent_input_pic_zero_flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the candidate input picture list to be represented by an input picture inputPicB that is the closest to the input picture inputPicA in output order and is present in the candidate input picture list. A conversion between a visual media data and a bitstream is perfomed based on the NNPFA SEI message at step 4204. The conversion may include encoding at an encoder, decoding at a decoder, or combinations thereof.

[0337] It should be noted that the method 4200 can be implemented in an apparatus for processing video data comprising a processor and a non-transitory memory with instructions thereon, such as video encoder 4400, video decoder 4500, and / or encoder 4600. In such a case, the instructions upon execution by the processor, cause the processor to perform the method 4200. Further, the method 4200 can be performed by a non-transitory computer readable medium comprising a computer program product for use by a video coding device. The computer program product comprises computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method 4200.

[0338] FIG. 5 is a block diagram that illustrates an example video coding system 4300 that may utilize the techniques of this disclosure. The video coding system 4300 may include a source device 4310 and a destination device 4320. Source device 4310 generates encoded video data which may be referred to as a video encoding device. Destination device 4320 may decode the encoded video data generated by source device 4310 which may be referred to as a video decoding device.

[0339] Source device 4310 may include a video source 4312, a video encoder 4314, and an input / output (I / O) interface 4316. Video source 4312 may include a source such as a video capture device, an interface toP24092472301WO3; G25N21009W (4824-71003) receive video data from a video content provider, and / or a computer graphics system for generating video data, or a combination of such sources. The video data may comprise one or more pictures. Video encoder 4314 encodes the video data from video source 4312 to generate a bitstream. The bitstream may include a sequence of bits that form a coded representation of the video data. The bitstream may include coded pictures and associated data. The coded picture is a coded representation of a picture. The associated data may include sequence parameter sets, picture parameter sets, and other syntax structures. I / O interface 4316 may include a modulator / demodulator (modem) and / or a transmitter. The encoded video data may be transmitted directly to destination device 4320 via I / O interface 4316 through network 4330. The encoded video data may also be stored onto a storage medium / server 4340 for access by destination device 4320.

[0340] Destination device 4320 may include an I / O interface 4326, a video decoder 4324. and a display device 4322. I / O interface 4326 may include a receiver and / or a modem. I / O interface 4326 may acquire encoded video data from the source device 4310 or the storage medium / server 4340. Video decoder 4324 may decode the encoded video data. Display device 4322 may display the decoded video data to a user. Display device 4322 may be integrated with the destination device 4320, or may be external to destination device 4320, which can be configured to interface with an external display device.

[0341] Video encoder 4314 and video decoder 4324 may operate according to a video compression standard, such as the High Efficiency Video Coding (HEVC) standard, Versatile Video Coding (VVC) standard and other current and / or further standards.

[0342] FIG. 6 is a block diagram illustrating an example of video encoder 4400, which may be video encoder 4314 in the system 4300 illustrated in FIG. 5. Video encoder 4400 may be configured to perform any or all of the techniques of this disclosure. The video encoder 4400 includes a plurality of functional components. Tire techniques described in this disclosure may be shared among the various components of video encoder 4400. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

[0343] The functional components of video encoder 4400 may include a partition unit 4401, a prediction unit 4402 which may include a mode select unit 4403. a motion estimation unit 4404, a motion compensation unit 4405, an intra prediction unit 4406, a residual generation unit 4407, a transform processing unit 4408, a quantization unit 4409, an inverse quantization unit 4410, an inverse transform unit 4411, a reconstruction unit 4412, a buffer 4413, and an entropy encoding unit 4414.

[0344] In other examples, video encoder 4400 may include more, fewer, or different functional components. In an example, prediction unit 4402 may include an intra block copy (IBC) unit. The IBC unit may perfonn prediction in an IBC mode in which at least one reference picture is a picture where the current video block is located.

[0345] Furthermore, some components, such as motion estimation unit 4404 and motion compensation unit 4405 may be highly integrated, but are represented in the example of video encoder 4400 separately for purposes of explanation.P24092472301WO3; G25N21009W (4824-71003)

[0346] Partition unit 4401 may partition a picture into one or more video blocks. Video encoder 4400 and video decoder 4500 may support various video block sizes.

[0347] Mode select unit 4403 may select one of the coding modes, intra or inter, e.g.. based on error results, and provide the resulting intra or inter coded block to a residual generation unit 4407 to generate residual block data and to a reconstraction unit 4412 to reconstruct the encoded block for use as a reference picture. In some examples, mode select unit 4403 may select a combination of intra and inter prediction (CIIP) mode in which the prediction is based on an inter prediction signal and an intra prediction signal. Mode select unit 4403 may also select a resolution for a motion vector (e.g., a sub-pixel or integer pixel precision) for the block in the case of inter prediction.

[0348] To perform inter prediction on a current video block, motion estimation unit 4404 may generate motion information for the current video block by comparing one or more reference frames from buffer 4413 to the current video block. Motion compensation unit 4405 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from buffer 4413 other than the picture associated with the current video block.

[0349] Motion estimation unit 4404 and motion compensation unit 4405 may perform different operations for a current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice.

[0350] In some examples, motion estimation unit 4404 may perform uni-directional prediction for the current video block, and motion estimation unit 4404 may search reference pictures of list 0 or list 1 for a reference video block for the current video block. Motion estimation unit 4404 may then generate a reference index that indicates the reference picture in list 0 or list 1 that contains the reference video block and a motion vector that indicates a spatial displacement between the current video block and the reference video block. Motion estimation unit 4404 may output the reference index, a prediction direction indicator, and the motion vector as the motion information of the current video block. Motion compensation unit 4405 may generate the predicted video block of the current block based on the reference video block indicated by the motion information of the current video block.

[0351] In other examples, motion estimation unit 4404 may perform bi-directional prediction for the current video block, motion estimation unit 4404 may search the reference pictures in list 0 for a reference video block for the current video block and may also search the reference pictures in list 1 for another reference video block for the current video block. Motion estimation unit 4404 may then generate reference indexes that indicate the reference pictures in list 0 and list 1 containing the reference video blocks and motion vectors that indicate spatial displacements between the reference video blocks and the current video block. Motion estimation unit 4404 may output the reference indexes and the motion vectors of the current video block as the motion information of the current video block. Motion compensation unit 4405 may generate the predicted video block of the current video block based on the reference video blocks indicated by the motion information of the current video block.P24092472301WO3; G25N21009W (4824-71003)

[0352] In some examples, motion estimation unit 4404 may output a full set of motion information for decoding processing of a decoder. In some examples, motion estimation unit 4404 may not output a full set of motion information for the current video. Rather, motion estimation unit 4404 may signal the motion information of the current video block with reference to the motion information of another video block. For example, motion estimation unit 4404 may determine that the motion information of the current video block is sufficiently similar to the motion information of a neighboring video block.

[0353] In one example, motion estimation unit 4404 may indicate, in a syntax structure associated with the current video block, a value that indicates to the video decoder 4500 that the current video block has the same motion information as another video block.

[0354] In another example, motion estimation unit 4404 may identify, in a syntax structure associated with the current video block, another video block and a motion vector difference (MVD). The motion vector difference indicates a difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 4500 may use the motion vector of the indicated video block and the motion vector difference to determine the motion vector of the current video block.

[0355] As discussed above, video encoder 4400 may predictively signal the motion vector. Two examples of predictive signaling techniques that may be implemented by video encoder 4400 include advanced motion vector prediction (AMVP) and merge mode signaling.

[0356] Intra prediction unit 4406 may perform intra prediction on the current video block. When intra prediction unit 4406 performs intra prediction on the current video block, intra prediction unit 4406 may generate prediction data for the current video block based on decoded samples of other video blocks in the same picture. The prediction data for the current video block may include a predicted video block and various syntax elements.

[0357] Residual generation unit 4407 may generate residual data for the current video block by subtracting the predicted video block(s) of the current video block from the current video block. The residual data of the current video block may include residual video blocks that correspond to different sample components of the samples in the current video block.

[0358] In other examples, there may be no residual data for the current video block for the current video block, for example in a skip mode, and residual generation unit 4407 may not perform the subtracting operation.

[0359] Transform processing unit 4408 may generate one or more transform coefficient video blocks for the current video block by applying one or more transforms to a residual video block associated with the current video block.

[0360] After transform processing unit 4408 generates a transform coefficient video block associated with the current video block, quantization unit 4409 may quantize the transform coefficient video block associated with the current video block based on one or more quantization parameter (QP) values associated with the current video block.P24092472301WO3; G25N21009W (4824-71003)

[0361] Inverse quantization unit 4410 and inverse transform unit 4411 may apply inverse quantization and inverse transforms to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. Reconstruction unit 4412 may add the reconstructed residual video block to corresponding samples from one or more predicted video blocks generated by the prediction unit 4402 to produce a reconstructed video block associated with the current block for storage in the buffer 4413.

[0362] After reconstruction unit 4412 reconstructs the video block, the loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0363] Entropy encoding unit 4414 may receive data from other functional components of the video encoder 4400. When entropy encoding unit 4414 receives the data, entropy encoding unit 4414 may perform one or more entropy encoding operations to generate entropy encoded data and output a bitstream that includes the entropy encoded data.

[0364] FIG. 7 is a block diagram illustrating an example of video decoder 4500 which may be video decoder 4324 in the system 4300 illustrated in FIG. 5. The video decoder 4500 may be configured to perfonn any or all of the techniques of this disclosure. In the example shown, the video decoder 4500 includes a plurality of functional components. The techniques described in this disclosure may be shared among the various components of the video decoder 4500. In some examples, a processor may be configured to perform any or all of the techniques described in this disclosure.

[0365] In the example shown, video decoder 4500 includes an entropy decoding unit 4501, a motion compensation unit 4502, an intra prediction unit 4503, an inverse quantization unit 4504, an inverse transformation unit 4505, a reconstruction unit 4506, and a buffer 4507. Video decoder 4500 may, in some examples, perform a decoding pass generally reciprocal to the encoding pass described with respect to video encoder 4400.

[0366] Entropy decoding unit 4501 may retrieve an encoded bitstream. The encoded bitstream may include entropy coded video data (e.g., encoded blocks of video data). Entropy decoding unit 4501 may decode the entropy coded video data, and from the entropy decoded video data, motion compensation unit 4502 may determine motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. Motion compensation unit 4502 may, for example, determine such information by performing the AMVP and merge mode.

[0367] Motion compensation unit 4502 may produce motion compensated blocks, possibly performing interpolation based on interpolation filters. Identifiers for interpolation filters to be used with sub-pixel precision may be included in the syntax elements.

[0368] Motion compensation unit 4502 may use interpolation filters as used by video encoder 4400 during encoding of the video block to calculate interpolated values for sub-integer pixels of a reference block. Motion compensation unit 4502 may determine the interpolation filters used by video encoder 4400 according to received syntax information and use the interpolation filters to produce predictive blocks.P24092472301WO3; G25N21009W (4824-71003)

[0369] Motion compensation unit 4502 may use some of the syntax information to determine sizes of blocks used to encode frame(s) and / or slice(s) of the encoded video sequence, partition information that describes how each macroblock of a picture of the encoded video sequence is partitioned, modes indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter coded block, and other information to decode the encoded video sequence.

[0370] Intra prediction unit 4503 may use intra prediction modes for example received in the bitstream to form a prediction block from spatially adjacent blocks. Inverse quantization unit 4504 inverse quantizes, i.e.. dequantizes, the quantized video block coefficients provided in the bitstream and decoded by entropy decoding unit 4501. Inverse transform unit 4505 applies an inverse transform.

[0371] Reconstruction unit 4506 may sum the residual blocks with the corresponding prediction blocks generated by motion compensation unit 4502 or intra prediction unit 4503 to form decoded blocks. If desired, a deblocking filter may also be applied to filter the decoded blocks in order to remove blockincss artifacts. The decoded video blocks are then stored in buffer 4507, which provides reference blocks for subsequent motion compensation / intra prediction and also produces decoded video for presentation on a display device.

[0372] FIG. 8 is a schematic diagram of an example encoder 4600. The encoder 4600 is suitable for implementing the techniques of WC. The encoder 4600 includes three in-loop filters, namely a deblocking filter (DF) 4602, a sample adaptive offset (SAO) 4604, and an adaptive loop filter (ALF) 4606. Unlike the DF 4602, which uses predefined filters, the SAO 4604 and the ALF 4606 utilize the original samples of the current picture to reduce the mean square errors between the original samples and the reconstructed samples by adding an offset and by applying a finite impulse response (FIR) filter, respectively, with coded side information signaling the offsets and filter coefficients. The ALF 4606 is located at the last processing stage of each picture and can be regarded as a tool trying to catch and fix artifacts created by the previous stages.

[0373] The encoder 4600 further includes an intra prediction component 4608 and a motion estimation / compensation (ME / MC) component 4610 configured to receive input video. The intra prediction component 4608 is configured to perform intra prediction, while the ME / MC component 4610 is configured to utilize reference pictures obtained from a reference picture buffer 4612 to perform inter prediction. Residual blocks from inter prediction or intra prediction are fed into a transform (T) component 4614 and a quantization (Q) component 4616 to generate quantized residual transform coefficients, which are fed into an entropy coding component 4618. The entropy coding component 4618 entropy codes the prediction results and the quantized transform coefficients and transmits the same toward a video decoder (not shown). Quantization components output from the quantization component 4616 may be fed into an inverse quantization (IQ) components 4620, an inverse transform component 4622, and a reconstruction (REC) component 4624. The REC component 4624 is able to output images to the DF 4602, the SAO 4604, and the ALF 4606 for filtering prior to those images being stored in the reference picture buffer 4612.

[0374] A listing of solutions preferred by some examples is provided next.P24092472301WO3; G25N21009W (4824-71003)

[0375] The following solutions show examples of techniques discussed herein.

[0376] 1. A method for processing media data comprising: determining that use of a neural-network postfilter characteristics (NNPFC) supplemental enhancement information (SEI) message requires a definition of a variable SEI processing stage index (SeiProcStgldx), which indicates a processing stage index associated with a neural network post-filter (NNPF) within a chosen processing chain; and performing a conversion between a visual media data and a bitstream based on the NNPFC SEI message.

[0377] 2. The method of solution 1, wherein use of the NNPFC SEI message requires the definition of the list CandlnputPicListf SeiProcStgldx ]. where CandlnputPicList is a candidate input picture list which contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded.

[0378] 3. The method of any of solutions 1-2, wherein when SeiProcStgldx is equal to 0, pictures inCandlnputPicListf SeiProcStgldx ] are cropped decoded output pictures, or wherein when SeiProcStgldx is greater than 0, the list CandlnputPicListf SeiProcStgldx ] contains pictures after the application of the processes implied by the SEI messages associated with processing stage index values less than SeiProcStgldx.

[0379] 4. The method of any of solutions 1-3, wherein use of the NNPFC SEI message requires the definition of the variables cropped width (CroppedWidth) and cropped height (CroppedHeight), which inidcated the input picture width and height in units of luma samples, respectively, of the input pictures.

[0380] 5. The method of any of solutions 1-4, wherein use of the NNPFC SEI message requires the definition of the variable chroma format identification code (ChromaFormatldc), which indicates the chroma format indicator, of the input pictures.

[0381] 6. The method of any of solutions 1-5, wherein use of the neural -network post-filter activation(NNPF A) SEI message requires the definition of the variable SeiProcStgldx, which indicates the processing stage index associated with the NNPF within a chosen processing chain.

[0382] 7. The method of any of solutions 1-6, wherein use of the NNPFA SEI message requires the definition of the list CandlnputPicListf SeiProcStgldx ], which contains a list of pictures in output order from which the input pictures for the NNPF are selected or padded.

[0383] 8. The method of any of solutions 1-7, wherein when SeiProcStgldx is equal to 0, pictures inCandlnputPicListf SeiProcStgldx ] are cropped decoded output pictures, or wherein when SeiProcStgldx is greater than 0, the list CandlnputPicListf SeiProcStgldx ] contains pictures after the application of the processes implied by the SEI messages associated with processing stage index values less than SeiProcStgldx.

[0384] 9. The method of any of solutions 1-8, wherein that NNPFA persistence flag(nnpfajicrsistcncc flag) equal to 0 specifics that the NNPFA SEI message persists for the current picture only.

[0385] 10. The method of any of solutions 1-9, wherein nnpfajrersistence flag equal to 0 specifies that theNNPFA SEI message persists for the current picture and its associated inserted pictures only.

[0386] 11. The method of any of solutions 1-10, wherein nnpfa_persistence_flag equal to 1 specifies that the NNPFA SEI message persists for the current picture and all subsequent pictures of the current layer in outputP24092472301WO3; G25N21009W (4824-71003) order until one or more of the following conditions are true: a new coded layer video sequence (CLVS) of the current layer begins; the bitstream ends; or a picture in the current layer associated with an NNPFA SEI message with the same NNPFA target identifier (nnpfa target id) as the current SEI message is output that follows the current picture in output order.

[0387] 12. The method of any of solutions 1-11, wherein nnpfa_persistence_flag equal to 1 specifies that the NNPFA SEI message persists for the current picture and its associated inserted pictures, and all subsequent pictures of the current layer in output order until one or more of the following conditions are true: a new CLVS of the current layer begins; the bitstream ends; or a picture in the current layer associated with an NNPFA SEI message with the same nnpfa target id as the current SEI message is output that follows the current picture in output order.

[0388] 13. The method of any of solutions 1-12, wherein when NNPFC target pictures(nnpfcTargetPictures) is the set of pictures to which the NNPFC SEI message corresponding to the target NNPF pertains, and when NNPFA target pictures (nnpfaTargetPictures) is the set of pictures for which the NNPFA SEI message persists, bitstream conformance requires that any picture included in nnpfaTargetPictures shall also be included in nnpfcTargetPictures.

[0389] 14. The method of any of solutions 1-13, wherein the value of NNPFA no previous CLVS flag(nnpfa_no_prev_clvs_flag) can be changed from 0 to 1 when the current CLVS is spliced from another bitstream next to the previous CLVS and this NNPFA SEI message would cause one or more input pictures originating from one or more previous CLVSs to be selected and therefore is likely to impact the output of the target NNPF negatively.

[0390] 15. The method of any of solutions 1-14, wherein a post-fdtering process associated with an NNPF, which is specified by an NNFPC SEI message and activated by an NNPFA SEI message, is allwed to be applied to a picture that is the corresponding picture or an associated inserted picture of a picture for which the NNPFA SEI message activating the NNPF persists.

[0391] 16. The method of any of solutions I -15, wherein an input picture with index 0 for an NNPF is a picture in CandInputPicList[ SeiProcStgldx ] that is a corresponding picture of current cropped decoded output (CDO) picture (currCdoPic) or is an associated inserted picture of currCdoPic, where currCdoPic is a cropped decoded output picture for which the NNPF defined by this NNPFC SEI message is activated by an NNPFA SEI message.

[0392] 17. The method of any of solutions 1-16, wherein the input picture with index i in the range of 1 to number of input pictures (numlnputPics) - 1, inclusive, is the picture in CandInputPicList[ SeiProcStgldx ] that immediately precedes the input picture with index i - 1 in output order.

[0393] 18. The method of any of solutions 1-17, wherein NNPFC absent input picture zero flag(nnpfc_absent_input_pic_zero_flag) equal to 1 indicates that the NNPF expects an input picture that is not present in CandInputPicList[ SeiProcStgldx ] to be represented by sample arrays with sample values equal to 0, andP24092472301WO3; G25N21009W (4824-71003) impfc_absent_input_pic_zero_flag equal to 0 indicates that the NNPF expects an input picture (inputPicA) that is not present in CandInputPicList[ SeiProcStgldx ] to be represented by the input picture (inputPicB) that is the closest to inputPicA in output order and is present in CandInputPicList[ SeiProcStgldx ].

[0394] 19. The method of any of solutions 1-18. wherein the conversion includes encoding the visual media data into the bitstream.

[0395] 20. The method of any of solutions 1-18, wherein the conversion includes decoding the visual media data from the bitstream.

[0396] 21. An apparatus for processing video data comprising: a processor: and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of solutions 1-20.

[0397] 22. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of solutions 1-20.

[0398] 23. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining that use of a neural-network post-filter characteristics (NNPFC) supplemental enhancement information (SEI) message requires a definition of a variable SEI processing stage index (SeiProcStgldx), which indicates a processing stage index associated with a neural network post-filter (NNPF) within a chosen processing chain: and generating a bitstream based on the determining.

[0399] 24. A method for storing bitstream of a video comprising: determining that use of a neural-network post-filter characteristics (NNPFC) supplemental enhancement information (SEI) message requires a definition of a variable SEI processing stage index (SeiProcStgldx), which indicates a processing stage index associated with a neural network post-filter (NNPF) within a chosen processing chain: generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

[0400] 25. A method, apparatus, or system described in the present disclosure.

[0401] In the solutions described herein, an encoder may conform to the format rule by producing a coded representation according to the format rule. In the solutions described herein, a decoder may use the format rule to parse syntax elements in the coded representation with the knowledge of presence and absence of syntax elements according to the format rule to produce decoded video.

[0402] In the present disclosure, the term “video processing” may refer to video encoding, video decoding, video compression or video decompression. For example, video compression algorithms may be applied during conversion from pixel representation of a video to a corresponding bitstream representation or vice versa. The bitstream representation of a current video block may, for example, correspond to bits that are either co-located or spread in different places within the bitstream, as is defined by the syntax. For example, a macroblock may beP24092472301WO3; G25N21009W (4824-71003) encoded in terms of transformed and coded error residual values and also using bits in headers and other fields in the bitstream. Furthermore, during conversion, a decoder may parse a bitstream with the knowledge that some fields may be present, or absent, based on the determination, as is described in the above solutions. Similarly, an encoder may determine that certain syntax fields are or are not to be included and generate the coded representation accordingly by including or excluding the syntax fields from the coded representation.

[0403] The disclosed and other solutions, examples, embodiments, modules and the functional operations described in this disclosure can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this disclosure and their structural equivalents, or in combinations of one or more of them. The disclosed and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more them. The term “data processing apparatus" encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.

[0404] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g.. files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0405] The processes and logic flows described in this disclosure can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by. and apparatus can also be implemented as, special purpose logic circuitry, e.g., an field programmable gate array (FPGA) or an application specific integrated circuit (ASIC).P24092472301WO3; G25N21009W (4824-71003)

[0406] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random-access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e g., erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and compact disc read-only memory (CD ROM) and digital versatile disc-read only memory (DVD-ROM) disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0407] While the present disclosure contains many specifics, these should not be construed as limitations on the scope of any subject matter or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular techniques. Certain features that are described in the present disclosure in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0408] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Moreover, the separation of various system components in the embodiments described in the present disclosure should not be understood as requiring such separation in all embodiments.

[0409] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in the present disclosure.

[0410] A first component is directly coupled to a second component when there are no intervening components, except for a line, a trace, or another medium between the first component and the second component. The first component is indirectly coupled to the second component when there are intervening components other than a line, a trace, or another medium between the first component and the second component. The term “coupled” and its variants include both directly coupled and indirectly coupled. The use of the term “about” means a range including ±10% of the subsequent number unless otherwise stated.P24092472301WO3; G25N21009W (4824-71003)

[0411] While several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods might be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples are to be considered as illustrative and not restrictive, and the intention is not to be limited to the details given herein. For example, the various elements or components may be combined or integrated in another system or certain features may be omitted, or not implemented.

[0412] In addition, techniques, systems, subsystems, and methods described and illustrated in the various embodiments as discrete or separate may be combined or integrated with other systems, modules, techniques, or methods without departing from the scope of the present disclosure. Other items shown or discussed as coupled may be directly connected or may be indirectly coupled or communicating through some interface, device, or intermediate component whether electrically, mechanically, or otherwise. Other examples of changes, substitutions, and alterations are ascertainable by one skilled in the art and could be made without departing from the spirit and scope disclosed herein.

Claims

P24092472301WO3; G25N21009W (4824-71003)CLAIMSWhat is claimed is:

1. A method for processing media data, comprising: determining that nnpfc_absent_input_pic_zero flag equal to 1 indicates that a neural-network postfilter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0; and performing a conversion between a visual media data and a bitstream based on the NNPF.

2. The method of claim 1, further comprising determining that nnpfc absent input pic zero flag equal to 0 indicates that the NNPF expects an input picture inputPicA that is not present in the candidate input picture list to be represented by an input picture inputPicB that is the closest to the input picture inputPicA in output order and is present in the candidate input picture list.

3. The method of any of claims 1-2, wherein the candidate input picture list is designated CandlnputPicList.

4. The method of any of claims 1 -3, wherein the candidate input picture list is based on a processing stage index and is designated CandlnputPicListf SeiProcStgldx ] .

5. The method of claims 1-4, wherein nnpfc_absent_input_pic_zero_flag is included in a NNPF supplemental enhancement information (SEI) message.

6. The method of any of claims 1-5, wherein nnpfc_absent_input_pic_zero_flag is indicated in the bitstream using a one-bit unsigned fixed length integer (u(l)).

7. The method of any of claims 1-6, wherein the conversion includes encoding the visual media data into the bitstream.

8. The method of any of claims 1 -6, wherein the conversion includes decoding the visual media data from the bitstream.

9. An apparatus for processing video data comprising: a processor; and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor, cause the processor to perform the method of any of claims 1-9.P24092472301WO3; G25N21009W (4824-71003)10. A non-transitory computer readable medium comprising a computer program product for use by a video coding device, the computer program product comprising computer executable instructions stored on the non-transitory computer readable medium such that when executed by a processor cause the video coding device to perform the method of any of claims 1-9.

11. A non-transitory computer-readable recording medium storing a bitstream of a video which is generated by a method performed by a video processing apparatus, wherein the method comprises: determining that nnpfc_abscnt_input_pic_zcro_flag equal to 1 indicates that a neural-network postfilter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0; and generating a bitstream based on the determining.

12. A method for storing bitstream of a video, comprising: determining that nnpfc_absent_input_pic_zero_flag equal to 1 indicates that a neural-network postfilter (NNPF) expects an input picture that is not present in a candidate input picture list to be represented by sample arrays with sample values equal to 0; generating a bitstream based on the determining; and storing the bitstream in a non-transitory computer-readable recording medium.

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

Images