Method and device for video processing and medium

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is presented. The method comprises applying a neural network filter to a current video unit for a conversion between the current video unit of the video and a bitstream of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprises at least one of the following items: prediction information of the current video unit, segmentation information of the current video unit, or coding and decoding information of a previously coded and decoded video unit; and performing the transition based on the application.

Description

Technical Field

[0001] Embodiments of the present disclosure relate generally to video processing techniques, and more particularly, to neural network filters for video processing. Background Art

[0002] Nowadays, digital video capabilities are being applied to all aspects of people's lives. For video encoding / decoding, various types of video compression technologies have been proposed, such as MPEG-2, MPEG-4, ITU-TH.263, ITU-TH.264 / MPEG-4 Part 10 Advanced Video Codec (AVC), ITU-TH.265 High Efficiency Video Codec (HEVC) standard, and Versatile Video Codec (VVC) standard. However, it is generally expected to further improve the encoding and decoding efficiency of video encoding and decoding technologies. Summary of the invention

[0003] Embodiments of the present disclosure provide a solution for video processing.

[0004] In a first aspect, a method for video processing is proposed. The method includes: for conversion between a current video unit of a video and a bitstream of the video, applying a neural network filter to the current video unit based at least on auxiliary information associated with the current video unit, the auxiliary information including at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, and encoding and decoding information of a previously encoded and decoded video unit; and based on the application, performing the conversion. The method according to the first aspect of the present disclosure uses auxiliary information to improve the performance of a neural network filter (e.g., a neural network post-processing filter), thereby improving the encoding and decoding efficiency and encoding and decoding effectiveness of video encoding and decoding.

[0005] In a second aspect, a device for video processing is provided. The device includes a processor and a non-volatile memory having instructions thereon. These instructions, when executed by the processor, cause the processor to perform the method according to the first aspect of the present disclosure.

[0006] In a third aspect, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores instructions for causing a processor to execute the method according to the first aspect of the present disclosure.

[0007] In a fourth aspect, another non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video generated by a method performed by an apparatus for video processing. The method includes: applying a neural network filter to a current video unit based at least on auxiliary information associated with the current video unit of the video, the auxiliary information including at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, or codec information of a previously coded video unit; and generating the bitstream based on the application.

[0008] In a fifth aspect, a method for storing a bitstream of a video is provided. The method comprises: applying a neural network filter to a current video unit of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, and encoding and decoding information of a previously encoded and decoded video unit; generating the bitstream based on the application; and storing the bitstream in a non-transitory computer-readable recording medium.

[0009] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become more apparent through the following detailed description with reference to the accompanying drawings. In the exemplary embodiments of the present disclosure, the same reference numerals generally refer to the same components.

[0011] Figure 1 A block diagram illustrating an example video encoding and decoding system is shown according to some embodiments of the present disclosure;

[0012] Figure 2 A block diagram illustrating a first example video encoder is shown according to some embodiments of the present disclosure;

[0013] Figure 3 shows a block diagram illustrating an example video decoder according to some embodiments of the present disclosure;

[0014] Figure 4 A diagram showing the luma data channel of nnpfc_inp_order_idc equal to 3 (informative);

[0015] Figure 5 A flowchart of a method for video processing according to an embodiment of the present disclosure is shown;

[0016] Figure 6A block diagram of a computing device is shown in which various embodiments of the present disclosure may be implemented.

[0017] Throughout the drawings, the same or similar reference numbers generally refer to the same or similar elements. DETAILED DESCRIPTION

[0018] The principle of the present disclosure will now be described with reference to some embodiments. It should be understood that these embodiments are described only for the purpose of illustrating and helping those skilled in the art to understand and implement the present disclosure, without implying any limitation on the scope of the present disclosure. In addition to the methods described below, the disclosure described herein can also be implemented in various ways.

[0019] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0020] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," and the like indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include the particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an example embodiment, it is claimed that such feature, structure, or characteristic, whether or not explicitly described, is within the knowledge of those skilled in the art to affect correlation with other embodiments.

[0021] It should be understood that, although the terms "first" and "second" etc. may be used herein to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish one element from another element. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0022] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an" and "the" are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include", "comprises", "has", "has", "includes" and / or "comprising" are used herein to indicate the presence of the features, elements and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components and / or combinations thereof. Example Environment

[0023] Figure 11 is a block diagram illustrating an example video codec system 100 that may utilize the techniques of the present disclosure. As shown, the video codec system 100 may include a source device 110 and a destination device 120. The source device 110 may also be referred to as a video encoding device, and the destination device 120 may also be referred to as a video decoding device. In operation, the source device 110 may be configured to generate encoded video data, and the destination device 120 may be configured to decode the encoded video data generated by the source device 110. The source device 110 may include a video source 112, a video encoder 114, and an input / output (I / O) interface 116.

[0024] The video source 112 may include a source such as a video acquisition device. Examples of a video acquisition device include, but are not limited to, an interface for receiving video data from a video content provider, a computer graphics system for generating video data, and / or a combination thereof.

[0025] The video data may include one or more pictures. The video encoder 114 encodes the video data from the video source 112 to generate a bitstream. The bitstream may include a bit sequence that forms a codec representation of the video data. The bitstream may include encoded pictures and associated data. The encoded pictures are codec representations of pictures. The associated data may include sequence parameter sets, picture parameter sets, and other grammatical structures. The I / O interface 116 may include a modulator / demodulator and / or a transmitter. The encoded video data may be directly transmitted to the destination device 120 via the network 130A via the I / O interface 116. The encoded video data may also be stored on a storage medium / server 130B for access by the destination device 120.

[0026] The destination device 120 may include an I / O interface 126, a video decoder 124, and a display device 122. The I / O interface 126 may include a receiver and / or a modem. The I / O interface 126 may obtain encoded video data from the source device 110 or the storage medium / server 130B. The video decoder 124 may decode the encoded video data. The display device 122 may display the decoded video data to the user. The display device 122 may be integrated with the destination device 120, or may be outside the destination device 120, which is configured to be connected to an external display device interface.

[0027] The video encoder 114 and the video decoder 124 may operate according to a video compression standard, such as the High Efficiency Video Codec (HEVC) standard, the Versatile Video Codec (VVC) standard, and other existing and / or future standards.

[0028] Figure 2is a block diagram showing an example of a video encoder 200 according to some embodiments of the present disclosure, which may be Figure 1 An example of a video encoder 114 in the system 100 is shown.

[0029] Video encoder 200 may be configured to implement any or all of the techniques of this disclosure. Figure 2 In the example of , video encoder 200 includes multiple functional components. The techniques described in this disclosure can be shared between the various components of video encoder 200. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0030] In some embodiments, the video encoder 200 may include a segmentation unit 201, a prediction unit 202, a residual generation unit 207, a transformation unit 208, a quantization unit 209, an inverse quantization unit 210, an inverse transformation unit 211, a reconstruction unit 212, a cache 213 and an entropy coding unit 214, and the prediction unit 202 may include a mode selection unit 203, a motion estimation unit 204, a motion compensation unit 205 and an intra-frame prediction unit 206.

[0031] In other examples, the video encoder 200 may include more, fewer, or different functional components. In one example, the prediction unit 202 may include an intra-block copy (IBC) unit. The IBC unit may perform prediction in an IBC mode in which at least one reference picture is a picture in which the current video block is located.

[0032] Furthermore, although some components (such as the motion estimation unit 204 and the motion compensation unit 205) may be integrated, for the purpose of explanation, these components are described in detail below. Figure 2 are shown separately in the example.

[0033] The partitioning unit 201 may partition a picture into one or more video blocks. The video encoder 200 and the video decoder 300 may support various video block sizes.

[0034] The mode selection unit 203 may select one of a plurality of codec modes (intra-frame codec or inter-frame codec), for example, based on the error result, and provide the resulting intra-frame coded block or inter-frame coded block to the residual generation unit 207 to generate residual block data, and to the reconstruction unit 212 to reconstruct the coded block for use as a reference picture. In some examples, the mode selection unit 203 may select a combined inter-frame and intra-frame prediction (CIIP) mode in which prediction is based on an inter-frame prediction signal and an intra-frame prediction signal. In the case of inter-frame prediction, the mode selection unit 203 may also select a resolution for a motion vector (e.g., sub-pixel precision or integer pixel precision) for the block.

[0035] To perform inter-frame prediction on the current video block, the motion estimation unit 204 may generate motion information for the current video block by comparing the current video block with one or more reference frames from the cache 213. The motion compensation unit 205 may determine a predicted video block for the current video block based on the motion information and decoded samples of pictures from the cache 213 other than the picture associated with the current video block.

[0036] The motion estimation unit 204 and the motion compensation unit 205 may perform different operations on the current video block, for example, depending on whether the current video block is in an I slice, a P slice, or a B slice. As used herein, an "I slice" may refer to a portion of a picture consisting of macroblocks, all of which are based on macroblocks within the same picture. Furthermore, as used herein, in some aspects, a "P slice" and a "B slice" may refer to a portion of a picture consisting of macroblocks that are independent of macroblocks in the same picture.

[0037] In some examples, the motion estimation unit 204 may perform unidirectional prediction on the current video block, and the motion estimation unit 204 may search the reference pictures of list 0 or list 1 to find the reference video block for the current video block. The motion estimation unit 204 may then generate a reference index and a motion vector, the reference index indicating the reference picture in list 0 or list 1 containing the reference video block, and the motion vector indicating the spatial displacement between the current video block and the reference video block. The motion estimation unit 204 may output the reference index, the prediction direction indicator, and the motion vector as the motion information of the current video block. The motion compensation unit 205 may generate a predicted video block for the current video block based on the reference video block indicated by the motion information of the current video block.

[0038] Alternatively, in other examples, the motion estimation unit 204 may perform bidirectional prediction on the current video block. The motion estimation unit 204 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. The motion estimation unit 204 may then generate a plurality of reference indexes and a plurality of motion vectors, the plurality of reference indexes indicating a plurality of reference pictures in list 0 and list 1 containing a plurality of reference video blocks, and the plurality of motion vectors indicating a plurality of spatial displacements between the plurality of reference video blocks and the current video block. The motion estimation unit 204 may output the plurality of reference indexes and the plurality of motion vectors of the current video block as motion information of the current video block. The motion compensation unit 205 may generate a predicted video block of the current video block based on the plurality of reference video blocks indicated by the motion information of the current video block.

[0039] In some examples, motion estimation unit 204 may output a complete set of motion information for use in a decoding process by a decoder. Alternatively, in some embodiments, motion estimation unit 204 may signal motion information of a current video block with reference to motion information of another video block. For example, motion estimation unit 204 may determine that motion information of a current video block is sufficiently similar to motion information of a neighboring video block.

[0040] In one example, motion estimation unit 204 may indicate a value in a syntax structure associated with the current video block that indicates to video decoder 300 that the current video block has the same motion information as another video block.

[0041] In another example, the motion estimation unit 204 may identify another video block and a motion vector difference (MVD) in a syntax structure associated with the current video block. The motion vector difference indicates the difference between the motion vector of the current video block and the motion vector of the indicated video block. The video decoder 300 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.

[0042] As discussed above, the video encoder 200 may signal motion vectors in a predictive manner.Two examples of prediction signaling techniques that may be implemented by the video encoder 200 include Advanced Motion Vector Prediction (AMVP) and Merge mode signaling.

[0043] The intra prediction unit 206 may perform intra prediction on the current video block. When the intra prediction unit 206 performs intra prediction on the current video block, the intra prediction unit 206 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 prediction video block and various syntax elements.

[0044] The residual generation unit 207 can generate residual data for the current video block by subtracting (e.g., indicated by a minus sign) 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 corresponding to different sample components of samples in the current video block.

[0045] In other examples, such as in skip mode, there may be no residual data for the current video block, and the residual generation unit 207 may not perform a subtraction operation.

[0046] Transform processing unit 208 may generate one or more transform coefficient video blocks for a current video block by applying one or more transforms to the residual video block associated with the current video block.

[0047] After transform processing unit 208 generates a transform coefficient video block associated with the current video block, quantization unit 209 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.

[0048] The inverse quantization unit 210 and the inverse transform unit 211 may apply inverse quantization and inverse transform to the transform coefficient video block, respectively, to reconstruct a residual video block from the transform coefficient video block. The reconstruction unit 212 may add the reconstructed residual video block to corresponding samples from one or more prediction video blocks generated by the prediction unit 202 to generate a reconstructed video block associated with the current video block for storage in the buffer 213.

[0049] After reconstruction unit 212 reconstructs the video block, a loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0050] The entropy encoding unit 214 may receive data from other functional components of the video encoder 200. When the entropy encoding unit 214 receives the data, the entropy encoding unit 214 may perform one or more entropy encoding operations to generate entropy-encoded data and output a bitstream including the entropy-encoded data.

[0051] Figure 3 is a block diagram showing an example of a video decoder 300 according to some embodiments of the present disclosure, which may be Figure 1 An example of a video decoder 124 in the system 100 is shown.

[0052] Video decoder 300 may be configured to perform any or all of the techniques of this disclosure. Figure 3 In the example of , video decoder 300 includes multiple functional components. The techniques described in this disclosure can be shared between the various components of video decoder 300. In some examples, a processor can be configured to perform any or all of the techniques described in this disclosure.

[0053] exist Figure 3 In the example of , the video decoder 300 includes an entropy decoding unit 301, a motion compensation unit 302, an intra prediction unit 303, an inverse quantization unit 304, an inverse transform unit 305, and a reconstruction unit 306 and a buffer 307. In some examples, the video decoder 300 can perform a decoding process that is generally opposite to the encoding process described with respect to the video encoder 200.

[0054] The entropy decoding unit 301 can retrieve the encoded bitstream. The encoded bitstream may include entropy encoded video data (e.g., encoded blocks of video data). The entropy decoding unit 301 may decode the entropy encoded video data, and the motion compensation unit 302 may determine motion information from the entropy decoded video data, the motion information including motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 302 may determine such information, for example, by performing AMVP and Merge mode. AMVP is used, including deriving several most likely candidates based on data and reference pictures from neighboring PBs. The motion information typically includes horizontal motion vector displacement values ​​and vertical motion vector displacement values, one or two reference picture indexes, and in the case of prediction areas in B strips, also includes an identification of which reference picture list is associated with each index. As used herein, in some aspects, "Merge mode" may refer to deriving motion information from spatial neighboring blocks or temporal neighboring blocks.

[0055] The motion compensation unit 302 may generate motion compensated blocks, possibly performing interpolation based on interpolation filters.Identifiers for the interpolation filters used with sub-pixel precision may be included in the syntax elements.

[0056] The motion compensation unit 302 may calculate interpolated values ​​for sub-integer pixels of a reference block using interpolation filters used by the video encoder 200 during encoding of the video block. The motion compensation unit 302 may determine the interpolation filters used by the video encoder 200 based on received syntax information, and the motion compensation unit 302 may use the interpolation filters to generate a prediction block.

[0057] The motion compensation unit 302 may use at least part of the syntax information to determine the size of blocks used to encode (multiple) frames and / or (multiple) slices of the encoded video sequence, partition information describing how each macroblock of a picture of the encoded video sequence is partitioned, a mode indicating how each partition is encoded, one or more reference frames (and reference frame lists) for each inter-coded block, and other information for decoding the encoded video sequence. As used herein, in some aspects, a "slice" may refer to a data structure that can be decoded independently of other slices of the same picture in terms of entropy coding and decoding, signal prediction, and residual signal reconstruction. A slice may be an entire picture, or it may be a region of a picture.

[0058] The intra prediction unit 303 may use, for example, an intra prediction mode received in the bitstream to form a prediction block from spatially neighboring blocks. The inverse quantization unit 304 inversely quantizes (i.e., dequantizes) the quantized video block coefficients provided in the bitstream and decoded by the entropy decoding unit 301. The inverse transform unit 305 applies an inverse transform.

[0059] The reconstruction unit 306 may obtain the decoded block, for example, by adding the residual block to the corresponding prediction block generated by the motion compensation unit 302 or the intra prediction unit 303. If necessary, a deblocking filter may also be applied to filter the decoded block to remove blocking artifacts. The decoded video block is then stored in a buffer 307, which provides reference blocks for subsequent motion compensation / intra prediction, and the buffer 307 also generates the decoded video for presentation on a display device.

[0060] Some exemplary embodiments of the present disclosure will be described in detail below. It should be noted that the section titles used in this document are for ease of understanding, and the embodiments disclosed in the section are not limited to the section. In addition, although some embodiments are described with reference to general video codecs or other specific video codecs, the disclosed technology is also applicable to other video coding and decoding technologies. In addition, although some embodiments describe the video encoding steps in detail, it should be understood that the corresponding decoding steps of de-encoding will be implemented by the decoder. In addition, the term video processing includes video encoding or compression, video decoding or decompression, and video transcoding, in which video pixels are represented from one compression format to another compression format or at different compression bit rates. 1. Brief Overview The present disclosure relates to image / video codec technology. Specifically, it relates to improvements in neural network post-processing filters. These improvements include signaling visual quality improvement types, signaling more auxiliary input data, processing different chrominance components, and removing invalid operations from existing neural network post-processing filters. For video bitstreams encoded and decoded by any codec (e.g., the Versatile Video Codec (VVC) standard and / or the Versatile SEI Message (VSEI) standard for encoded and decoded video bitstreams), the concepts can be applied alone or in various combinations. 2. Abbreviations APS Adaptive Parameter Set AU Access Unit CLVS Codec layer video sequence CLVSS Codec layer video sequence starts CRC Cyclic Redundancy Check CVS Codec Video Sequence FIR Finite Impulse Response IRAP Intra-frame random access point NAL Network Abstraction Layer PPS Picture Parameter Set PU Picture Unit RASL Random Access Skip Preamble SEI Supplemental Enhancement Information STSA Stepped Temporal Sublayer Access VCL video codec layer VSEI Versatile Supplementary Enhancement Information (Rec.ITU-T H.274|ISO / IEC 23002-7) VUI Video Availability Information VVC Versatile Video Codec (Rec.ITU-T H.266|ISO / IEC 23090-3) 3. Introduction 3.1. Video Coding Standards Video codec standards have evolved primarily through the development of the well-known ITU-T and ISO / IEC standards. ITU-T developed H.261 and H.263, ISO / IEC developed MPEG-1 and MPEG-4 Vision, and the two organizations jointly developed H.262 / MPEG-2 Video and H.264 / MPEG-4 Advanced Video Codec (AVC) and H.265 / HEVC standards. Since H.262, video codec standards have been based on a hybrid video codec structure, where temporal prediction plus transform codec is used. In order to explore future video codec technologies after HEVC, the Joint Video Exploration Team (JVET) was jointly established by VCEG and MPEG in 2015. Since then, JVET has adopted many new methods and put them into reference software called Joint Exploration Model (JEM). When the Versatile Video Codec (VVC) project officially started, JVET was later renamed the Joint Video Experts Group (JVET). VVC is a new codec standard that aims to reduce bit rate by 50% compared to HEVC. The standard has been finalized by JVET at the 19th JVET meeting that ended on July 1, 2020. The Versatile Video Codec (VVC) standard (ITU-T H.266 | ISO / IEC 23090-3) and the associated Versatile Supplementary Enhancement Information (VSEI) standard for coded video bitstreams (ITU-T H.274 | ISO / IEC 23002-7) have been designed for the widest range of applications, including traditional uses such as television broadcasting, video conferencing or playback from storage media, as well as newer and more advanced use cases such as adaptive bitrate streaming, video region extraction, composition and merging of content from multiple coded video bitstreams, multi-view video, scalable layered codecs, and viewport-adaptive 360° immersive media. The Essential Video Codec (EVC) standard (ISO / IEC 23094-1) is another video codec standard that has been recently developed by MPEG. 3.2. General SEI messages and SEI messages in VVC and VSEI SEI messages assist processes related to decoding, display, or other purposes. However, SEI messages are not required for constructing luma or chroma samples through the decoding process. A compliant decoder does not need to process this information to conform to the output order. Some SEI messages are required for checking bitstream consistency and output timing decoder consistency. Other SEI messages are not required for checking bitstream consistency. Annex D of VVC specifies the syntax and semantics of SEI message payloads for some SEI messages, and specifies the use of SEI messages and VUI parameters for which syntax and semantics are specified in ITU-T H.274|ISO / IEC 23002-7. 3.3. Signaling of neural network post-processing filters The specifications of the two SEI messages used for signaling of neural network post-processing filters are shown below. Neural network post-processing filter characteristics SEI message Neural Network Post-Processing Filter Characteristics SEI Message Syntax Neural Network Post-Processing Filter Characteristics SEI Message Semantics This SEI message specifies a neural network that can be used as a post-processing filter. The use of a specified post-processing filter for a particular picture is indicated using a neural network post-processing filter activation SEI message. Use of this SEI message requires the following variables to be defined: - The width and height of the cropped decoded output picture, in units of luma samples, denoted here by CroppedWidth and CroppedHeight, respectively. - the luma sample array CroppedYPic[x][y] and the chroma sample arrays CroppedCbPic[x][y] and CroppedCrPic[x][y] (when present) of the cropped decoded output picture for vertical coordinate y and horizontal coordinate x, where the upper left corner of the sample array has coordinates with y equal to 0 and x equal to 0. - Bit depth BitDepth of the luma sample array for the cropped decoded output picture Y . - The bit depth BitDepth of the chroma sample array (if any) used for the cropped decoded output picture C . - A chroma format indicator, denoted herein by ChromaFormatIdc, as described in item 7.3. - When nnpfc_auxiliary_inp_idc is equal to 1, quantize the strength value StrengthControlVal. When this SEI message specifies a neural network that can be used as a post-processing filter, the semantics specify the derivation of the luma sample array FilteredYPic[x][y] and the chroma sample arrays FilteredCbPic[x][y] and FilteredCrPic[x][y] that include the output of the post-processing filter, as indicated by the value of nnpfc_out_order_idc. The variables SubWidthC and SubHeightC are derived from ChromaFormatIdc as specified in Table 2. nnpfc_id contains an identification number that can be used to identify the post-processing filter. The value of nnpfc_id must be between 0 and 2. 32 -2, including the boundary value. nnpfc_id has values ​​from 256 to 511 (including the boundary values) and from 2 31 to 2 32 The value -2 (inclusive) is reserved for future use by ITU-T|ISO / IEC. 31 to 2 32 Decoders in the range -2 (inclusive) must ignore nnpfc_id. nnpfc_mode_idc equal to 0 specifies that the post-processing filter associated with the nnpfc_id value is determined by external means not specified in this specification. nnpfc_mode_idc equal to 1 specifies that the post-processing filter associated with the nnpfc_id value is a neural network represented by the ISO / IEC 15938-17 bitstream contained in this SEI message. nnpfc_mode_idc equal to 2 specifies that the post-processing filter associated with the nnpfc_id value is a neural network identified by the specified tag uniform resource identifier (URI) (nnpfc_uri_tag[i]) and the neural network information URI (nnpfc_uri[i]). The value of nnpfc_mode_idc MUST be in the range 0 to 255, inclusive. Values ​​of nnpfc_mode_idc greater than 2 are reserved for future specification by ITU-T | ISO / IEC and MUST not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing reserved values ​​of nnpfc_mode_idc. nnpfc_purpose_and_formatting_flag equal to 0 specifies that there are no syntax elements related to filter purpose, input formatting, output formatting, and complexity. nnpfc_purpose_and_formatting_flag equal to 1 specifies that syntax elements related to filter purpose, input formatting, output formatting, and complexity are present. nnpfc_purpose_and_formatting_flag must be equal to 1 when nnpfc_mode_idc is equal to 1 and the current CLVS does not contain a previous neural network post-processing filter characteristics SEI message in decoding order with a value of nnpfc_id equal to the value of nnpfc_id in this SEI message. When the current CLVS contains a previous neural network post-processing filter characteristics SEI message in decoding order with the same value of nnpfc_id equal to the value of nnpfc_id in this SEI message, at least one of the following conditions must apply: - This SEI message has nnpfc_mode_idc equal to 1 and nnpfc_purpose_and_formatting_flag equal to 0 in order to provide neural network updates. - This SEI message has the same content as the previous Neural Network Post-Processing Filter Characteristics SEI message. When this SEI message is the first neural network post-processing filter characteristics SEI message in decoding order with a particular nnpfc_id value within the current CLVS, this SEI message specifies the base post-processing filters that are relevant to the current decoded picture and all subsequent decoded pictures of the current layer in output order until the end of the current CLVS. When this SEI message is not the first neural network post-processing filter characteristics SEI message in decoding order with a specific nnpfc_id value within the current CLVS, this SEI message is relevant 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 the next neural network post-processing filter characteristics SEI message in output order with a specific nnpfc_id value within the current CLVS. nnpfc_purpose indicates the purpose of the post-processing filter as specified in Table 1. The value of nnpfc_purpose must be between 0 and 2. 32 The value of nnpfc_purpose not appearing in Table 1 is reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_purpose. Table 1 - Definition of nnpfc_purpose NOTE 1—When the reserved value of nnpfc_purpose is used by ITU-T | ISO / IEC in the future, the syntax of this SEI message may be extended with multiple syntax elements whose presence depends on nnpfc_purpose. is equal to this value. When SubWidthC is equal to 1 and SubHeightC is equal to 1, nnpfc_purpose must not be equal to 2 or 4. nnpfc_out_sub_c_flag equal to 1 specifies that outSubWidthC is equal to 1 and outSubHeightC is equal to 1. nnpfc_out_sub_c_flag equal to 0 specifies that outSubWidthC is equal to 2 and outSubHeightC is equal to 1. When nnpfc_out_sub_c_flag is not present, outSubWidthC is inferred to be equal to SubWidthC and outSubHeightC is inferred to be equal to SubHeightC. If SubWidthC is equal to 2 and SubHeightC is equal to 1, then nnpfc_out_sub_c_flag shall not be equal to 0. nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specify the width and height, respectively, of the array of luma samples of the picture produced by applying the post-processing filter identified by nnpfc_id to the cropped decoded output picture. When nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not present, they are inferred to be equal to CroppedWidth and CroppedHeight, respectively. nnpfc_component_last_flag equal to 0 specifies that the second dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor obtained from the post-processing filter is used for channels. nnpfc_component_last_flag equal to 1 specifies that the last dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor obtained from the post-processing filter is used for channels. Note 2 - The first dimension in the input and output tensors is used for batch indexing, which is a practice in some neural network frameworks. Although the semantics of this SEI message uses a batch size equal to 1, it is up to the post-processing implementation to determine the batch size used as input for neural network inference. NOTE 3- Color components are examples of channels. nnpfc_inp_format_flag indicates a method of converting the sample values ​​of the cropped decoded output picture into input values ​​of the post-processing filter. When nnpfc_inp_format_flag is equal to 0, the input value of the post-processing filter is a real number, and functions InpY and InpC are specified as follows. InpY(x)=x÷((1< <BitDepth Y )-1) (75) InpC(x)=x÷((1< <BitDepth C )-1) (76) When nnpfc_inp_format_flag is equal to 1, the input values ​​to the post-processing filter are unsigned integers, and the functions InpY and InpC are specified as follows: The variable inpTensorBitDepth is derived from the syntax element nnpfc_inp_tensor_bitdepth_minus8 specified as follows. nnpfc_inp_tensor_bitdepth_minus8 specifies the bit depth of the luma sample values ​​in the input integer tensor by adding 8. The value of inpTensorBitDepth is derived as follows: inpTensorBitDepth=nnpfc_inp_tensor_bitdepth_minus8+8 (78) Bitstream conformance requires that the value of nnpfc_inp_tensor_bitdepth_minus8 must be in the range 0 to 24, inclusive. nnpfc_auxiliary_inp_idc not equal to 0 specifies that auxiliary input data is present in the input tensor of the neural network post-processing filter. nnpfc_auxiliary_inp_idc equal to 0 indicates that the auxiliary input data is not present in the input tensor. nnpfc_auxiliary_inp_idc equal to 1 indicates that the auxiliary input data is derived as specified in Table 4 below. The value of nnpfc_auxiliary_inp_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_auxiliary_inp_idc greater than 1 are reserved for future specifications of ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_auxiliary_inp_idc. nnpfc_separate_colour_description_present_flag equal to 1 indicates that the exact combination of color primaries, transfer characteristics and matrix coefficients of the picture resulting from the post-processing filters is specified in the SEI message syntax structure. nnpfc_separate_colour_description_present_flag equal to 0 indicates that the combination of color primaries, transfer characteristics and matrix coefficients of the picture resulting from the post-processing filters is the same as indicated in the VUI parameters for CLVS. nnpfc_colour_primaries has the same semantics as the vui_colour_primaries syntax element (as specified in item 7.3), except for the following: -nnpfc_colour_primaries specifies the color primaries of the picture resulting from applying the neural network post-processing filters specified in the SEI message, instead of the color primaries used for CLVS. - When nnpfc_colour_primaries is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_colour_primaries is inferred to be equal to vui_colour_primaries. The nnpfc_transfer_characteristics has the same semantics as the vui_transfer_characteristics syntax element (as specified in clause 7.3), except for the following: -nnpfc_transfer_characteristics specifies the transfer characteristics of the picture resulting from applying the neural network post-processing filters specified in the SEI message, instead of the transfer characteristics used for CLVS. - When nnpfc_transfer_characteristics is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_transfer_characteristics is inferred to be equal to vui_transfer_characteristics. nnpfc_matrix_coeffs has the same semantics as the vui_matrix_coeffs syntax element (as specified in Item 7.3), except for the following: -nnpfc_matrix_coeffs specifies the matrix coefficients for the picture resulting from applying the neural network post-processing filters specified in the SEI message, rather than the matrix coefficients used for CLVS. - When nnpfc_matrix_coeffs is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. - The allowed values ​​of nnpfc_matrix_coeffs are not constrained by the chroma format of the decoded video picture indicated by the value of ChromaFormatIdc for the semantics of the VUI parameter. - When nnpfc_matrix_coeffs is equal to 0, nnpfc_out_order_idc must not be equal to 1 or 3. nnpfc_inp_order_idc indicates the method of ordering the sample array of the cropped decoded output picture as the input to the post-processing filter. Table 2 below contains an informative description of the nnpfc_inp_order_idc values. The semantics of nnpfc_inp_order_idc in the range of 0 to 3 (inclusive) are specified in Table 3 below, which specifies the process for deriving the input tensor inputTensor for different values ​​of nnpfc_inp_order_idc and given vertical sample coordinates cTop and horizontal sample coordinates cLeft, which specify the top left sample position of the sample patch included in the input tensor. When the chroma format of the cropped decoded output picture is not 4:2:0, nnpfc_inp_order_idc must not be equal to 3. The value of nnpfc_inp_order_idc must be in the range of 0 to 255 (inclusive). Values ​​of nnpfc_inp_order_idc greater than 3 are reserved for future specification by ITU-T | ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_inp_order_idc. Table 2 - Informative description of nnpfc_inp_order_idc values Figure 4 Diagram 400 of a luma data channel with nnpfc_inp_order_idc equal to 3 is shown (informative). A tile is a rectangular array of samples of a component (eg, a luma component or a chroma component) from a picture. nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any patch size that is a positive integer multiple of the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. When nnpfc_constant_patch_size_flag is equal to 0, the patch size width must be less than or equal to CroppedWidth. When nnpfc_constant_patch_size_flag is equal to 0, the patch size height must be less than or equal to CroppedHeight. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. nnpfc_patch_width_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the horizontal sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_width_minus1+1) can be used as the horizontal sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_width_minus1 must be in the range of 0 to Min(32766, CroppedWidth-1), inclusive. nnpfc_patch_height_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the vertical sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_height_minus1+1) can be used as the vertical sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_height_minus1 must be in the range of 0 to Min(32766, CroppedHeight-1), including the boundary values. nnpfc_overlap specifies the horizontal and vertical sample counts of overlap of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap must be in the range 0 to 16383, inclusive. The variables inpPatchWidth, inpPatchHeight, outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows: Bitstream conformance requires that outPatchWidth*CroppedWidth must be equal to nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight must be equal to nnpfc_pic_height_in_luma_samples*inpPatchHeight. nnpfc_padding_type specifies the process of padding when referring to sample positions outside the boundaries of the cropped decoded output picture, as described in the following Table 3. The value of nnpfc_padding_type must be in the range of 0 to 15, inclusive. Table 3 - Informative description of nnpfc_padding_type values nnpfc_padding_type describe 0 Zero padding 1 Copy Fill 2 Reflection Fill 3 Wrap-around padding 4 Fixed padding 5..15 reserve nnpfc_luma_padding_val specifies the luma value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cb_padding_val specifies the Cb value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cr_padding_val specifies the Cr value used for padding when nnpfc_padding_type is equal to 4. The function InpSampleVal(y, x, picHeight, picWidth, croppedPic) (where the inputs are the vertical sample position y, the horizontal sample position x, the picture height picHeight, the picture width picWidth and the sample array croppedPic) returns the value of sampleVal derived as follows: Table 4 - Process for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft specifying the top left sample position of a sample patch included in the input tensor nnpfc_complexity_idc greater than 0 specifies that one or more syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id may be present. nnpfc_complexity_idc equal to 0 specifies that no syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id are present. The value of nnpfc_complexity_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_complexity_idc greater than 1 are reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_complexity_idc. nnpfc_out_format_flag is equal to 0 to indicate that the sample values ​​output by the post-processing filter are real numbers and are used to convert the luma sample values ​​and chroma sample values ​​output by the post-processing filter to the bit depth BitDepth Y and BitDepth C The integer-valued functions OutY and OutC at are specified as follows: OutY(x)=Clip3(0,(1< <BitDepth Y )-1,Round(x*((1< <BitDepth Y )-1))) (81) OutC(x)=Clip3(0,(1< <BitDepth C )-1,Round(x*((1< <BitDepthc)-1))) (82) nnpfc_out_format_flag equal to 1 indicates that the sample values ​​output by the post-processing filter are unsigned integers, and the functions OutY and OutC are specified as follows: The variable outTensorBitDepth is derived from the syntax element nnpfc_out_tensor_bitdepth_minus8 as described below. nnpfc_out_tensor_bitdepth_minus8 specifies the bit depth of the sample values ​​in the output integer tensor by adding 8. The value of outTensorBitDepth is derived as follows: outTensorBitDepth=nnpfc_out_tensor_bitdepth_minus8+8 (84) Bitstream conformance requires that the value of nnpfc_out_tensor_bitdepth_minus8 must be in the range 0 to 24, inclusive. nnpfc_out_order_idc indicates the output order of samples resulting from the post-processing filters. Table 5 contains an informative description of nnpfc_out_order_idc values. The semantics of nnpfc_out_order_idc in the range of 0 to 3, inclusive, are specified in Table 6, which specifies the process for deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for different values ​​of nnpfc_out_order_idc and given vertical sample coordinates cTop and horizontal sample coordinates cLeft specifying the top left sample position of the sample patch included in the input tensor. When nnpfc_purpose is equal to 2 or 4, nnpfc_out_order_idc must not be equal to 3. The value of nnpfc_out_order_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_out_order_idc greater than 3 are reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_out_order_idc. Table 5 - Informative description of nnpfc_out_order_idc values Table 6 - Filtered output sample array derived from the output tensor outputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft specifying the top left sample position of a sample patch included in the input tensor Process of sample values ​​in FilteredYPic, FilteredCbPic, and FilteredCrPic The base post-processing filter for the cropped decoded output picture picA is the filter identified by the first neural network post-processing filter characteristics SEI message in decoding order with a particular nnpfc_id value within the CLVS. If there is another neural network post-processing filter characteristics SEI message having the same nnpfc_id value, having nnpfc_mode_idc equal to 1, having different content than the neural network post-processing filter characteristics SEI message defining the base post-processing filter and referring to the picture picA, the base post-processing filter is updated by decoding the ISO / IEC 15938-17 bitstream in the neural network post-processing filter characteristics SEI message to obtain the post-processing filter PostProcessingFilter(). Otherwise, the post-processing filter PostProcessingFilter() is assigned to be the same as the base post-processing filter. The following process is used to filter the cropped decoded output picture with a post-processing filter PostProcessingFilter() to generate a filtered picture comprising sample arrays FilteredYPic, FilteredCbPic and FilteredCrPic of Y, Cb and Cr, respectively, as indicated by nnpfc_out_order_idc. nnpfc_reserved_zero_bit must be equal to 0. nnpfc_uri_tag[i] contains a NULL-terminated UTF-8 string specifying the tag URI. The UTF-8 string contains a URI, with syntax and semantics as specified in IETF RFC 4151, that uniquely identifies the format and associated information about the neural network used as the post-processing filter specified by the nnrpf_uri[i] value. NOTE 4 - The nnrpf_uri_tag[i] element represents a 'tag' URI that allows the format of the neural network data specified by the nnrpf_uri[i] value to be uniquely identified without the need for a central registration authority. nnpfc_uri[i] contains a NULL-terminated UTF-8 string as specified in IETF Internet Standard 63. The UTF-8 string contains a URI, with syntax and semantics as specified in IETF Internet Standard 66, identifying neural network information (e.g., data representation) used as a post-processing filter. nnpfc_payload_byte[i] contains the i-th byte of a bitstream conforming to ISO / IEC 15938-17. The byte sequence nnpfc_payload_byte[i] for all present values ​​of i must be a complete bitstream conforming to ISO / IEC 15938-17. nnpfc_parameter_type_idc equal to 0 indicates that the neural network uses only integer parameters. nnpfc_parameter_type_flag equal to 1 indicates that the neural network can use floating point or integer parameters. nnpfc_parameter_type_idc equal to 2 indicates that the neural network uses only binary parameters. nnpfc_parameter_type_idc equal to 3 is reserved for future specifications by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing the reserved value of nnpfc_parameter_type_idc. nnpfc_log2_parameter_bit_length_minus3 equal to 0, 1, 2, and 3 indicates that the neural network does not use parameters with bit lengths greater than 8, 16, 32, and 64, respectively. When nnpfc_parameter_type_idc is present and nnpfc_log2_parameter_bit_length_minus3 is not present, the neural network does not use parameters with bit lengths greater than 1. nnpfc_num_parameters_idc indicates the maximum number of neural network parameters for the post-processing filters in powers of 2048. nnpfc_num_parameters_idc equal to 0 indicates that the maximum number of neural network parameters is not specified. The value of nnpfc_num_parameters_idc must be in the range of 0 to 52, inclusive. Values ​​of nnpfc_num_parameters_idc greater than 52 are reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_num_parameters_idc. If the value of nnpfc_num_parameters_idc is greater than zero, the variable maxNumParameters is derived as follows: maxNumParameters=(2048< <nnpfc_num_parameters_idc)-1 (86) Bitstream conformance requires that the number of neural network parameters of a post-processing filter must be less than or equal to maxNumParameters. nnpfc_num_kmac_operations_idc greater than 0 specifies that the maximum number of multiply-accumulate operations per sample of the post-processing filter is less than or equal to nnpfc_num_kmac_operation_idc * 1000. nnpfc_num_kmac_operation_idc equal to 0 specifies that the maximum number of multiply-accumulate operations of the network is unspecified. The value of nnpfc_num_kmac_operations_idc must be between 0 and 2. 32 -1, including the boundary value. Neural network post-processing filter activation SEI message Neural Network Post-Processing Filter Activation SEI Message Syntax Neural Network Post-Processing Filter Activation SEI Message Semantics This SEI message specifies the neural network post-processing filters that can be used for post-processing filtering of the current picture. Neural network post-processing filter activation SEI messages are maintained only for the current picture. NOTE - There may be several neural network post-processing filter activation SEI messages present for the same picture when the post-processing filters are used for different purposes or filter different color components. nnpfa_id specifies that the neural network post-processing filters specified by one or more neural network post-processing filter characteristics SEI messages related to the current picture and having nnpfc_id equal to nnfpa_id can be used for post-processing filtering for the current picture. 4. Question The current design of SEI message for Neural Network Post-Processing Filter Characteristic (NNPFC) has the following problems: 1) The purpose of the NNPFC SEI message specifying the neural network post-processing filter may be for visual quality improvement. However, visual quality improvement may have different interpretations, such as fidelity-constrained visual quality improvement, GAN-based (generative adversarial network-based) visual quality improvement, film grain-based visual quality improvement, etc. Different video applications may prefer different types of visual quality improvement. For example, fidelity is important in surveillance scenarios, but may not be so critical in some user-generated videos. Therefore, it is necessary to be able to identify the type of visual quality improvement. 2) The NNPFC SEI message specifies auxiliary inputs to the neural network, which only include quantization parameter related data. However, there are other auxiliary inputs that can also be very helpful in improving the performance of post-processing filtering. Therefore, more auxiliary inputs need to be specified. 3) The NNPFC SEI message specifies that the chroma matrix presented in the output tensor of the NN filter includes two channels. However, the ability to process the two chroma components separately may be useful. Therefore, it is necessary to enable the application of the NN filter on only one of the two chroma components. 4) The NNPFC SEI message specifies the process in Table 4 for deriving the input tensor inputTensor. When nnpfc_inp_order_idc is equal to 3, nnpfc_component_last_flag is equal to 0, and nnpfc_auxil-iary_inp_idc is equal to 0, then the auxiliary input matrix should not exist. Therefore, in this case, the assignment operation "inputTensor[0][6][yP+overlapSize][xP+overlapSize]=2" should be removed. (StrengthControlVal–42) / 6 '. 5) The value of nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any small block size that is a positive integer multiple of the small block size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the small block size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. However, on the one hand, nnpfc_constant_patch_size_flag equal to 0 is allowed, while on the other hand, regardless of the value of nnpfc_constant_patch_size_flag, the filtering process specified as part of the semantics of the NNPFC SEI message always uses as input exactly the small block size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. In other words, actual support for taking as input any patch size that is a positive integer multiple of the patch sizes indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1 is missing. 5. Detailed solution In order to solve the above problems, the following method is disclosed. The embodiments should be considered as examples to explain the general concept and should not be interpreted in a narrow way. In addition, these embodiments can be applied alone or in combination in any way. In the following description, the term "picture" may be replaced with any video unit, such as "slice". 1) To solve problem 1, one or more types of visual quality improvement are defined, and the visual quality improvement type of the neural network post-processing filter with the purpose of visual quality improvement is transmitted by signaling in the NNPFC SEI message: a. In one example, the type of visual quality improvement is defined as objective-oriented / fidelity-oriented, where the goal is to increase the fidelity of the reconstructed picture after applying the neural network post-processing filter. Fidelity can be measured by PSNR (peak signal-to-noise ratio), Ms-SSIM (multi-scale structural similarity), etc. b. In one example, the type of visual quality improvement is defined as subjectively oriented, with the goal of increasing the subjective visual quality of the reconstructed picture after applying the neural network post-processing filter. Subjective visual quality can be measured by LPIPS (Learning Perceptual Image Patch Similarity), MOS (Mean Opinion Score), etc. c. In one example, the type of visual quality improvement is defined as film grain oriented, where film grain is synthesized on the reconstructed image after applying the neural network post-processing filter. 2) To solve problem 2, more auxiliary inputs to the neural network post-processing filters are defined. a. In one example, the auxiliary input includes prediction information, such as prediction samples, prediction mode, etc. b. In one example, the auxiliary input includes segmentation information, such as segmentation boundaries. c. In one example, the auxiliary input includes information from a previously decoded picture, such as samples of a co-located block or a motion compensated block of the current block to be processed in the previously decoded picture. d. In one example, different color components share or are allowed to share the same auxiliary input. e. In one example, different color components use or are allowed to use different auxiliary inputs. f. In one example, both chroma components use or are allowed to use the same auxiliary input that is different from the auxiliary input of the luma component. 3) To solve problem 3, the matrix presented in the input tensor and / or output tensor of the NN filter may include a luminance component, and / or a cb component, and / or a cr component, or any combination of these components. a. In one example, there is only a chroma matrix in the input tensor and / or the output tensor, the number of channels is 1, and the components are Cb. b. In one example, there is only a chroma matrix in the input tensor and / or the output tensor, the number of channels is 1, and the components are Cr. c. In one example, there are only luma and chroma matrices in the input tensor and / or output tensor, the number of channels is 2, and the components are luma and Cb. d. In one example, there are only luma and chroma matrices in the input tensor and / or output tensor, the number of channels is 2, and the components are luma and Cr. e. In one example, there are only four luma matrices and one chroma matrix in the input tensor and / or output tensor, the number of channels is 5, and the components are luma and Cb. This can only be used when the chroma format is 4:2:0. f. In one example, there are only four luma matrices and one chroma matrix in the input tensor and / or output tensor, the number of channels is 5, and the components are luma and Cr. This can only be used when the chroma format is 4:2:0. 4) To solve problem 4, when nnpfc_inp_order_idc is equal to 3, nnpfc_component_last_flag is equal to 0, and nnpfc_assistant_inp_idc is equal to 0, no auxiliary input matrix is ​​used. 5) To solve problem 5, one or more of the following aspects are specified: a. In one example, when nnpfc_constant_patch_size_flag is equal to 0, the patch size width represented by inpPatchWidth and the patch size height represented by inpPatchHeight are provided by external means not specified in this document. The value of inpPatchWidth must be a positive integer multiple of nnpfc_patch_width_minus1+1 and must be less than or equal to CroppedWidth. The value of PatchSizeH must be a positive integer multiple of nnpfc_patch_height_minus1+1 and must be less than or equal to CroppedHeight. i. An example of such an external component is an API that passes the values ​​of inpPatchWidth and inpPatchHeight to the decoder and rendering entities in the video application system, and these values ​​can be configured by the user through the user interface of the application. b. In one example, when nnpfc_constant_patch_size_flag is equal to 1, the value of inpPatchWidth is set equal to nnpfc_patch_width_minus1+1, and the value of inpPatchHeight is set equal to nnpfc_patch_height_minus1+1. c. In one example, regardless of the value of nnpfc_constant_patch_size_flag, the filtering process takes as input the patch size width inpPatchWidth and the patch size height inpPatchHeight in the manner specified above. 6. Examples Below are some example embodiments for the case where, for embodiment item 1, embodiment item 2, embodiment item 3, embodiment item 4 and their sub-items outlined in section 5 above, the video unit is a picture. Most relevant parts have been added or modified Underline , and some of the deleted portions are highlighted with strikethrough. There may be some other changes of an editorial nature and therefore not highlighted. 6.1. Example 1 This embodiment is for the case where for embodiment item 1 and all its sub-items outlined in section 5 above, the video unit is a picture. Neural Network Post-Processing Filter Characteristics SEI Message Syntax Neural Network Post-Processing Filter Activation SEI Message Semantics ··· nnpfc_purpose indicates the purpose of the post-processing filter as specified in Table 1. The value of nnpfc_purpose must be between 0 and 2. 32 nnpfc_purpose is in the range -2, inclusive. Values ​​of nnpfc_purpose not appearing in Table 1 are reserved for future specification by ITU-T | ISO / IEC and MUST NOT be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing reserved values ​​of nnpfc_purpose. When SubWidthC is equal to 1 and SubHeightC is equal to 1, nnpfc_purpose must not be equal to 2 or 4. nnpfc_visual_quality_improvement_type indicates the visual quality improvement as specified in Table 7 Type. The value of nnpfc_visual_quality_improvement_type must be in the range 0 to 255, inclusive. Values ​​of nnpfc_visual_quality_improvement_type not appearing in Table 7 are reserved for use by ITU-T | This is a future specification of ISO / IEC and MUST NOT be present in bitstreams conforming to this version of this specification. Native decoders encountering a value of nnpfc_visual_quality_improvement_type greater than 3 MUST ignore it. Table 7 - Definition of nnpfc_visual_quality_improvement_type NOTE x—Reserved value for nnpfc_visual_quality_improvement_type when used by ITU-T in the future | When used by ISO / IEC, the syntax of this SEI message may be extended with multiple syntax elements. Depends on nnpfc_visual_quality_improvement_type being equal to this value. 6.2. Example 2 This embodiment is for the case where for embodiment item 2, embodiment item 3, embodiment item 4 and all sub-items thereof outlined in section 5 above, the video unit is a picture. Neural Network Post-Processing Filter Activation SEI Message Semantics This SEI message specifies a neural network that can be used as a post-processing filter. The use of a specified post-processing filter for a particular picture is indicated using a neural network post-processing filter activation SEI message. Use of this SEI message requires the following variables to be defined: - The width and height of the cropped decoded output picture, in units of luma samples, denoted here by CroppedWidth and CroppedHeight, respectively. - the luma sample array CroppedYPic[x][y] and the chroma sample arrays CroppedCbPic[x][y] and CroppedCrPic[x][y] (when present) of the cropped decoded output picture for vertical coordinate y and horizontal coordinate x, where the upper left corner of the sample array has coordinates with y equal to 0 and x equal to 0. - Bit depth BitDepth of the luma sample array for the cropped decoded output picture Y . - The bit depth BitDepth of the chroma sample array (if any) used for the cropped decoded output picture C . - A chroma format indicator, denoted herein by ChromaFormatIdc, as described in item 7.3. - When nnpfc_auxiliary_inp_idc is equal to 1, quantize the strength value StrengthControlVal. - When nnpfc_auxiliary_inp_idc is equal to 2 or 3, the pruned decoded prediction picture has the same The same size as the cropped decoded output picture. - When nnpfc_auxiliary_inp_idc is equal to 2 or 3, the clipped The decoded prediction picture's luminance prediction array CroppedYPred[x][y] and chrominance prediction array CroppedCbPred [x][y] and CroppedCrPred[x][y] (when present), where the top left corner of the sample array has y equal to 0 and x equal to 0 The coordinates of . When this SEI message specifies a neural network that can be used as a post-processing filter, the semantics specify the derivation of the luma sample array FilteredYPic[x][y] and the chroma sample arrays FilteredCbPic[x][y] and FilteredCrPic[x][y] that include the output of the post-processing filter, as indicated by the value of nnpfc_out_order_idc. The variables SubWidthC and SubHeightC are derived from ChromaFormatIdc as specified in Table 2. nnpfc_id contains an identification number that can be used to identify the post-processing filter. The value of nnpfc_id must be between 0 and 2. 32 -2, including the boundary value. nnpfc_id has values ​​from 256 to 511 (including the boundary values) and from 2 31 to 2 32 The value of -2 (inclusive) is reserved for future use by ITU-T|ISO / IEC. A value of nnpfc_id in the range of 256 to 511 (inclusive) or in 2 31 to 2 32 Decoders with values ​​of nnpfc_id in the range of -2 (inclusive) must ignore nnpfc_id. nnpfc_mode_idc equal to 0 specifies that the post-processing filter associated with the nnpfc_id value is determined by external means not specified in this specification. nnpfc_mode_idc equal to 1 specifies that the post-processing filter associated with the nnpfc_id value is a neural network represented by the ISO / IEC 15938-17 bitstream contained in this SEI message. nnpfc_mode_idc equal to 2 specifies that the post-processing filter associated with the nnpfc_id value is a neural network identified by the specified tag uniform resource identifier (URI) (nnpfc_uri_tag[i]) and the neural network information URI (nnpfc_uri[i]). The value of nnpfc_mode_idc MUST be in the range 0 to 255, inclusive. Values ​​of nnpfc_mode_idc greater than 2 are reserved for future specification by ITU-T | ISO / IEC and MUST not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing reserved values ​​of nnpfc_mode_idc. nnpfc_purpose_and_formatting_flag equal to 0 specifies that there are no syntax elements related to filter purpose, input formatting, output formatting, and complexity. nnpfc_purpose_and_formatting_flag equal to 1 specifies that syntax elements related to filter purpose, input formatting, output formatting, and complexity are present. nnpfc_purpose_and_formatting_flag must be equal to 1 when nnpfc_mode_idc is equal to 1 and the current CLVS does not contain a previous neural network post-processing filter characteristics SEI message in decoding order with a value of nnpfc_id equal to the value of nnpfc_id in this SEI message. When the current CLVS contains a previous neural network post-processing filter characteristics SEI message in decoding order with the same value of nnpfc_id equal to the value of nnpfc_id in this SEI message, at least one of the following conditions must apply: - This SEI message has nnpfc_mode_idc equal to 1 and nnpfc_purpose_and_formatting_flag equal to 0 in order to provide neural network updates. - This SEI message has the same content as the previous Neural Network Post-Processing Filter Characteristics SEI message. When this SEI message is the first neural network post-processing filter characteristics SEI message in decoding order with a particular nnpfc_id value within the current CLVS, this SEI message specifies the base post-processing filters that are relevant to the current decoded picture and all subsequent decoded pictures of the current layer in output order until the end of the current CLVS. When this SEI message is not the first neural network post-processing filter characteristics SEI message in decoding order with a specific nnpfc_id value within the current CLVS, this SEI message is relevant 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 the next neural network post-processing filter characteristics SEI message in output order with a specific nnpfc_id value within the current CLVS. nnpfc_purpose indicates the purpose of the post-processing filter as specified in Table 1. The value of nnpfc_purpose must be between 0 and 2. 32 The value of nnpfc_purpose not appearing in Table 1 is reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_purpose. When SubWidthC is equal to 1 and SubHeightC is equal to 1, nnpfc_purpose shall not be equal to 2 or 4. nnpfc_out_sub_c_flag equal to 1 specifies that outSubWidthC is equal to 1 and outSubHeightC is equal to 1. nnpfc_out_sub_c_flag equal to 0 specifies that outSubWidthC is equal to 2 and outSubHeightC is equal to 1. When nnpfc_out_sub_c_flag is not present, outSubWidthC is inferred to be equal to SubWidthC and outSubHeightC is inferred to be equal to SubHeightC. If SubWidthC is equal to 2 and SubHeightC is equal to 1, then nnpfc_out_sub_c_flag shall not be equal to 0. nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples specify the width and height, respectively, of the array of luma samples of the picture produced by applying the post-processing filter identified by nnpfc_id to the cropped decoded output picture. When nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not present, they are inferred to be equal to CroppedWidth and CroppedHeight, respectively. nnpfc_component_last_flag equal to 0 specifies that the second dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor obtained from the post-processing filter is used for channels. nnpfc_component_last_flag equal to 1 specifies that the last dimension in the input tensor inputTensor to the post-processing filter and the output tensor outputTensor obtained from the post-processing filter is used for channels. Note 2 - The first dimension in the input and output tensors is used for batch indexing, which is a practice in some neural network frameworks. Although the semantics of this SEI message uses a batch size equal to 1, it is up to the post-processing implementation to determine the batch size used as input for neural network inference. NOTE 3- Color components are examples of channels. nnpfc_inp_format_flag indicates a method of converting the sample values ​​of the cropped decoded output picture into input values ​​of the post-processing filter. When nnpfc_inp_format_flag is equal to 0, the input value of the post-processing filter is a real number, and functions InpY and InpC are specified as follows. InpY(x)=x÷((1< <BitDepth Y )-1) (75) InpC(x)=x÷((1< <BitDepth C )-1) (76) When nnpfc_inp_format_flag is equal to 1, the input values ​​to the post-processing filter are unsigned integers, and the functions InpY and InpC are specified as follows: The variable inpTensorBitDepth is derived from the syntax element nnpfc_inp_tensor_bitdepth_minus8 specified as follows. nnpfc_inp_tensor_bitdepth_minus8 specifies the bit depth of the luma sample values ​​in the input integer tensor by adding 8. The value of inpTensorBitDepth is derived as follows: inpTensorBitDepth=nnpfc_inp_tensor_bitdepth_minus8+8 (78) Bitstream conformance requires that the value of nnpfc_inp_tensor_bitdepth_minus8 must be in the range 0 to 24, inclusive. nnpfc_auxiliary_inp_idc not equal to 0 specifies that auxiliary input data is present in the input tensor of the neural network post-processing filter. nnpfc_auxiliary_inp_idc equal to 0 indicates that auxiliary input data is not present in the input tensor. nnpfc_auxiliary_inp_idc equal to 1 , 2 or 3 Indicates that the auxiliary input data is derived as specified in Table 4. The value of nnpfc_auxiliary_inp_idc must be in the range of 0 to 255, inclusive. Greater than 1 3 The value of nnpfc_auxiliary_inp_idc is reserved for future specification by ITU-T|ISO / IEC and MUST not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing the reserved value of nnpfc_auxiliary_inp_idc. nnpfc_separate_colour_description_present_flag equal to 1 indicates that the exact combination of color primaries, transfer characteristics and matrix coefficients of the picture resulting from the post-processing filters is specified in the SEI message syntax structure. nnpfc_separate_colour_description_present_flag equal to 0 indicates that the combination of color primaries, transfer characteristics and matrix coefficients of the picture resulting from the post-processing filters is the same as indicated in the VUI parameters for CLVS. nnpfc_colour_primaries has the same semantics as the vui_colour_primaries syntax element (as specified in item 7.3), except for the following: -nnpfc_colour_primaries specifies the color primaries of the picture resulting from applying the neural network post-processing filters specified in the SEI message, instead of the color primaries used for CLVS. - When nnpfc_colour_primaries is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_colour_primaries is inferred to be equal to vui_colour_primaries. The nnpfc_transfer_characteristics has the same semantics as the vui_transfer_characteristics syntax element (as specified in clause 7.3), except for the following: -nnpfc_transfer_characteristics specifies the transfer characteristics of the picture resulting from applying the neural network post-processing filters specified in the SEI message, instead of the transfer characteristics used for CLVS. - When nnpfc_transfer_characteristics is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_transfer_characteristics is inferred to be equal to vui_transfer_characteristics. nnpfc_matrix_coeffs has the same semantics as the vui_matrix_coeffs syntax element (as specified in Item 7.3), except for the following: -nnpfc_matrix_coeffs specifies the matrix coefficients for the picture resulting from applying the neural network post-processing filters specified in the SEI message, rather than the matrix coefficients used for CLVS. - When nnpfc_matrix_coeffs is not present in the neural network post-processing filter characteristics SEI message, the value of nnpfc_matrix_coeffs is inferred to be equal to vui_matrix_coeffs. - The allowed values ​​of nnpfc_matrix_coeffs are not constrained by the chroma format of the decoded video picture indicated by the value of ChromaFormatIdc for the semantics of the VUI parameter. - When nnpfc_matrix_coeffs is equal to 0, nnpfc_out_order_idc must not be equal to 1 or 3. nnpfc_inp_order_idc indicates the method of ordering the sample array of the cropped decoded output picture as the input to the post-processing filter. Table 8 contains an informative description of the nnpfc_inp_order_idc values. The semantics of nnpfc_inp_order_idc in the range of 0 to 39, inclusive, are specified in Table 9, which specifies the process for deriving the input tensor inputTensor for different values ​​of nnpfc_inp_order_idc and given vertical sample coordinates cTop and horizontal sample coordinates cLeft, which specify the top left sample position of the sample patch included in the input tensor. When the chroma format of the cropped decoded output picture is not 4:2:0, nnpfc_inp_order_idc must not be equal to 37, 8, or 9. The value of nnpfc_inp_order_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_inp_order_idc greater than 39 are reserved for future specification by ITU-T | ISO / IEC and MUST not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing reserved values ​​of nnpfc_inp_order_idc. Table 8 - Informative description of nnpfc_inp_order_idc values A tile is a rectangular array of samples of a component (eg, a luma component or a chroma component) from a picture. nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any patch size that is a positive integer multiple of the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. When nnpfc_constant_patch_size_flag is equal to 0, the patch size width must be less than or equal to CroppedWidth. When nnpfc_constant_patch_size_flag is equal to 0, the patch size height must be less than or equal to CroppedHeight. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. nnpfc_patch_width_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the horizontal sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_width_minus1+1) can be used as the horizontal sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_width_minus1 must be in the range of 0 to Min(32766, CroppedWidth-1), inclusive. nnpfc_patch_height_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the vertical sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_height_minus1+1) can be used as the vertical sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_height_minus1 must be in the range of 0 to Min(32766, CroppedHeight-1), including the boundary values. nnpfc_overlap specifies the horizontal and vertical sample counts of overlap of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap must be in the range 0 to 16383, inclusive. The variables inpPatchWidth, inpPatchHeight, outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows: Bitstream conformance requires that outPatchWidth*CroppedWidth must be equal to nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight must be equal to nnpfc_pic_height_in_luma_samples*inpPatchHeight. nnpfc_padding_type specifies the process of padding when referencing sample positions outside the boundaries of the cropped decoded output picture, as described in Table 3. The value of nnpfc_padding_type must be in the range of 0 to 15, inclusive. nnpfc_luma_padding_val specifies the luma value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cb_padding_val specifies the Cb value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cr_padding_val specifies the Cr value used for padding when nnpfc_padding_type is equal to 4. The function InpSampleVal(y, x, picHeight, picWidth, croppedPic) (where the inputs are the vertical sample position y, the horizontal sample position x, the picture height picHeight, the picture width picWidth and the sample array croppedPic) returns the value of sampleVal derived as follows: Table 9 - Procedure for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft specifying the top left sample position of a sample patch included in the input tensor. nnpfc_complexity_idc greater than 0 specifies that one or more syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id may be present. nnpfc_complexity_idc equal to 0 specifies that no syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id are present. The value of nnpfc_complexity_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_complexity_idc greater than 1 are reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_complexity_idc. nnpfc_out_format_flag is equal to 0 to indicate that the sample values ​​output by the post-processing filter are real numbers and are used to convert the luma sample values ​​and chroma sample values ​​output by the post-processing filter to the bit depth BitDepth Y and BitDepth C The integer-valued functions OutY and OutC at are specified as follows: OutY(x)=Clip3(0,(1< <BitDepthY)-1,Round(x*((1<<BitDepthY)-1)))(81) OutC(x)=Clip3(0,(1< <BitDepth C )-1,Round(x*((1< <BitDepth C )-1)))(82) nnpfc_out_format_flag equal to 1 indicates that the sample values ​​output by the post-processing filter are unsigned integers, and the functions OutY and OutC are specified as follows: The variable outTensorBitDepth is derived from the syntax element nnpfc_out_tensor_bitdepth_minus8 as described below. nnpfc_out_tensor_bitdepth_minus8 specifies the bit depth of the sample values ​​in the output integer tensor by adding 8. The value of outTensorBitDepth is derived as follows: outTensorBitDepth=nnpfc_out_tensor_bitdepth_minus8+8 (84) Bitstream conformance requires that the value of nnpfc_out_tensor_bitdepth_minus8 must be in the range 0 to 24, inclusive. nnpfc_out_order_idc indicates the output order of samples resulting from the post-processing filters. Table 10 contains an informative description of the nnpfc_out_order_idc values. The semantics of nnpfc_out_order_idc in the range of 0 to 39 (inclusive) are specified in Table 11, which specifies the process for deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for different values ​​of nnpfc_out_order_idc and given vertical sample coordinates cTop and horizontal sample coordinates cLeft specifying the top left sample position of the sample patch included in the input tensor. When nnpfc_purpose is equal to 2 or 4, nnpfc_out_order_idc must not be equal to 3 7, 8 or 9 The value of nnpfc_out_order_idc must be in the range of 0 to 255, inclusive. Greater than 39 The value of nnpfc_out_order_idc is reserved for future specification by ITU-T|ISO / IEC and MUST NOT be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification MUST ignore SEI messages containing the reserved value of nnpfc_out_order_idc. Table 10 - Informative description of nnpfc_out_order_idc values Table 11 - Process for deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic from the output tensor outputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft specifying the top left sample position of a sample patch included in the input tensor The base post-processing filter for the cropped decoded output picture picA is the filter identified by the first neural network post-processing filter characteristics SEI message in decoding order with a particular nnpfc_id value within the CLVS. If there is another neural network post-processing filter characteristics SEI message having the same nnpfc_id value, having nnpfc_mode_idc equal to 1, having different content than the neural network post-processing filter characteristics SEI message defining the base post-processing filter and referring to the picture picA, the base post-processing filter is updated by decoding the ISO / IEC 15938-17 bitstream in the neural network post-processing filter characteristics SEI message to obtain the post-processing filter PostProcessingFilter(). Otherwise, the post-processing filter PostProcessingFilter() is assigned to be the same as the base post-processing filter. The following process is used to filter the cropped decoded output picture with a post-processing filter PostProcessingFilter() to generate a filtered picture comprising sample arrays FilteredYPic, FilteredCbPic and FilteredCrPic of Y, Cb and Cr, respectively, as indicated by nnpfc_out_order_idc. 6.3. Example 3 This embodiment is directed to the case where the video unit is a picture in regard to embodiment item 4 outlined in section 5 above. Neural Network Post-Processing Filter Characteristics SEI Message Semantics ··· nnpfc_inp_order_idc indicates the method of ordering the sample array of the cropped decoded output picture as the input to the post-processing filter. Table 2 contains an informative description of the nnpfc_inp_order_idc values. The semantics of nnpfc_inp_order_idc in the range of 0 to 3, inclusive, are specified in Table 12, which specifies the process for deriving the input tensor inputTensor for different values ​​of nnpfc_inp_order_idc and given vertical sample coordinates cTop and horizontal sample coordinates cLeft, which specify the top left sample position of the sample patch included in the input tensor. When the chroma format of the cropped decoded output picture is not 4:2:0, nnpfc_inp_order_idc must not be equal to 3. The value of nnpfc_inp_order_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_inp_order_idc greater than 3 are reserved for future specification by ITU-T | ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_inp_order_idc. A tile is a rectangular array of samples of a component (eg, a luma component or a chroma component) from a picture. nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any patch size that is a positive integer multiple of the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. When nnpfc_constant_patch_size_flag is equal to 0, the patch size width must be less than or equal to CroppedWidth. When nnpfc_constant_patch_size_flag is equal to 0, the patch size height must be less than or equal to CroppedHeight. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. nnpfc_patch_width_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the horizontal sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_width_minus1+1) can be used as the horizontal sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_width_minus1 must be in the range of 0 to Min(32766, CroppedWidth-1), inclusive. nnpfc_patch_height_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the vertical sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_height_minus1+1) can be used as the vertical sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_height_minus1 must be in the range of 0 to Min(32766, CroppedHeight-1), including the boundary values. nnpfc_overlap specifies the horizontal and vertical sample counts of overlap of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap must be in the range 0 to 16383, inclusive. The variables inpPatchWidth, inpPatchHeight, outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows: Bitstream conformance requires that outPatchWidth*CroppedWidth must be equal to nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight must be equal to nnpfc_pic_height_in_luma_samples*inpPatchHeight. nnpfc_padding_type specifies the process of padding when referencing sample positions outside the boundaries of the cropped decoded output picture, as described in Table 3. The value of nnpfc_padding_type must be in the range of 0 to 15, inclusive. nnpfc_luma_padding_val specifies the luma value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cb_padding_val specifies the Cb value used for padding when nnpfc_padding_type is equal to 4. nnpfc_cr_padding_val specifies the Cr value used for padding when nnpfc_padding_type is equal to 4. The function InpSampleVal(y, x, picHeight, picWidth, croppedPic) (where the inputs are the vertical sample position y, the horizontal sample position x, the picture height picHeight, the picture width picWidth and the sample array croppedPic) returns the value of sampleVal derived as follows: Table 12 - Process for deriving the input tensor inputTensor for a given vertical sample coordinate cTop and horizontal sample coordinate cLeft specifying the top left sample position of a sample patch included in the input tensor nnpfc_complexity_idc greater than 0 specifies that one or more syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id may be present. nnpfc_complexity_idc equal to 0 specifies that no syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id are present. The value of nnpfc_complexity_idc must be in the range of 0 to 255, inclusive. Values ​​of nnpfc_complexity_idc greater than 1 are reserved for future specification by ITU-T|ISO / IEC and must not be present in bitstreams conforming to this version of this specification. Decoders conforming to this version of this specification must ignore SEI messages containing reserved values ​​of nnpfc_complexity_idc. 6.4. Example 4 This embodiment is for the case where for embodiment item 5 and all its sub-items outlined in section 5 above, the video unit is a picture. Neural Network Post-Processing Filter Characteristics SEI Message Semantics ··· nnpfc_constant_patch_size_flag equal to 0 specifies that the post-processing filter accepts as input any patch size that is a positive integer multiple of the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. When nnpfc_constant_patch_size_flag is equal to 0, the patch size width must be less than or equal to CroppedWidth. When nnpfc_constant_patch_size_flag is equal to 0, the patch size height must be less than or equal to CroppedHeight. nnpfc_constant_patch_size_flag equal to 1 specifies that the post-processing filter accepts as input exactly the patch size indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. nnpfc_patch_width_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the horizontal sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_width_minus1+1) can be used as the horizontal sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_width_minus1 must be in the range of 0 to Min(32766, CroppedWidth-1), inclusive. nnpfc_patch_height_minus1+1, when nnpfc_constant_patch_size_flag is equal to 1, specifies the vertical sample count of the patch size required for the input to the post-processing filter. When nnpfc_constant_patch_size_flag is equal to 0, any positive integer multiple of (nnpfc_patch_height_minus1+1) can be used as the vertical sample count of the patch size for the input to the post-processing filter. The value of nnpfc_patch_height_minus1 must be in the range of 0 to Min(32766, CroppedHeight-1), including the boundary values. Let the variables inpPatchWidth and inpPatchHeight be the width and height of the patch size respectively. If nnpfc_constant_patch_size_flag is equal to 0, the following applies: -The values ​​of inpPatchWidth and inpPatchHeight are provided by external components that are not specified in this document. like, Such an external component can pass the values ​​of inpPatchWidth and inpPatchHeight to the video application The APIs for decoders and rendering entities in the system, and these values ​​can be configured by the user through the application's user interface. -inpPatchWidth must be a positive integer multiple of nnpfc_patch_width_minus1+1 and must be less than The value of inpPatchHeight must be a positive integer of nnpfc_patch_height_minus1+1. An integer multiple of and must be less than or equal to CroppedHeight. Otherwise (nnpfc_constant_patch_size_flag is equal to 1), the value of inpPatchWidth is set equal to =nnpfc_patch_width_minus1+1, and the value of inpPatchHeight is set equal to nnpfc_patch_ height_minus1+1. nnpfc_overlap specifies the horizontal and vertical sample counts of overlap of adjacent input tensors to the post-processing filter. The value of nnpfc_overlap must be in the range 0 to 16383, inclusive. variable outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize are derived as follows: Bitstream conformance requires that outPatchWidth*CroppedWidth must be equal to nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight must be equal to nnpfc_pic_height_in_luma_samples*inpPatchHeight.

[0061] Figure 5 A flow chart of a method 500 for video processing according to an embodiment of the present disclosure is shown. The method 500 is implemented for conversion between a current video unit of a video and a bitstream of the video. In some embodiments, the conversion between the current video unit and the bitstream may include encoding the current video unit into the bitstream. Alternatively or additionally, the conversion may include decoding the current video unit from the bitstream.

[0062] At block 510, a neural network (NN) filter is applied to the current video unit based at least on auxiliary information associated with the current video unit. The auxiliary information includes at least one of prediction information for the current video unit, segmentation information for the current video unit, or encoding information for a previously encoded video unit. For example, the neural network filter may be a neural network post-processing filter. In some example embodiments, the auxiliary information may also include quantization parameter related data. That is, more auxiliary inputs in addition to the quantization parameter related data may be input to the NN filter, such as a NN post-processing filter. At block 520, based on the application, the conversion is performed.

[0063] The method 500 enables the application of NN filters (e.g., NN post-processing filters) based on more auxiliary inputs (e.g., prediction information, segmentation information, and / or information from previously decoded video units). In this way, such auxiliary information or auxiliary inputs can be very helpful in improving the performance of NN post-processing filtering. Therefore, the codec efficiency and codec effectiveness of video processing can be improved.

[0064] In some embodiments, method 500 further includes: determining, based on at least one syntax element in the bitstream, whether a condition for excluding auxiliary information from an input to the neural network is satisfied; and if it is determined that the condition is satisfied, applying the neural network to the current video unit without inputting the auxiliary information to the neural network filter.

[0065] In some embodiments, the at least one syntax element includes: a first syntax element for indicating a rule for ordering the sample array of the cropped decoded output picture as an input to the neural network filter; a second syntax element for specifying the dimensions in the input tensor to the neural network filter and the output tensor obtained from the neural network filter to be used for channels; and a third syntax element for indicating whether auxiliary information is present in the input tensor of the neural network filter. In some example embodiments, the condition is that the first syntax element is 3, the second syntax element is 0, and the third syntax element is 0. For example, if nnpfc_inp_order_idc is equal to 3, nnpfc_component_last_flag is equal to 0, and nnpfc_auxiliary_inp_idc is equal to 0, then no auxiliary input matrix is ​​used.

[0066] In some embodiments, the prediction information of the current video unit includes at least one of the following: a prediction sample of the current video unit, or a prediction mode of the current video unit.

[0067] In some embodiments, the partition information of the current video unit includes a partition boundary of the current video unit.

[0068] In some embodiments, the codec information of the previously coded video unit includes: samples of at least one of a co-located block or a motion compensation block in the previously coded video unit, the co-located block is co-located with the current video block in the current video unit, and the motion compensation block is associated with the current video block. For example, the auxiliary input may include information from a previously decoded picture, such as samples of a co-located block or a motion compensation block of the current block to be processed in the previously decoded picture.

[0069] In some embodiments, the first color component and the second color component of the current video unit share the same auxiliary information, or the first color component and the second color component are allowed to share the same auxiliary information. That is, different color components share the same auxiliary input or are allowed to share the same auxiliary input.

[0070] In some embodiments, the first color component and the second color component of the current video unit use different auxiliary information, or the first color component and the second color component are allowed to use different auxiliary information. That is, different color components use different auxiliary inputs or are allowed to use different auxiliary inputs.

[0071] In some embodiments, a first chroma component and a second chroma component of a current video unit use the same auxiliary information or are allowed to use the same auxiliary information, and a luma component of the current video unit uses first auxiliary information that is different from second auxiliary information used by the first chroma component and the second chroma component. For example, the two chroma components use the same auxiliary input or are allowed to use the same auxiliary input that is different from the auxiliary input of the luma component.

[0072] In some embodiments, at least one matrix associated with the neural network filter includes at least one of the following: a luma component, a first chroma component, or a second chroma component. That is, the matrix presented in the input tensor and / or output tensor of the NN filter may include a luma component, and / or a Cb component, and / or a Cr component, or any combination of these components.

[0073] In some embodiments, the at least one matrix comprises at least one of: an input matrix in an input tensor of the neural network filter, or an output matrix in an output tensor of the neural network filter.

[0074] In some embodiments, the at least one matrix includes a chrominance matrix, and the number of channels of the input tensor or the output tensor of the neural network filter is 1. That is, only the chrominance matrix is ​​present in the input tensor and / or the output tensor, the number of channels is 1, and the components are Cb or Cr.

[0075] In some embodiments, the at least one matrix includes a chrominance matrix and a luminance matrix including a luminance component, and the number of channels of the input tensor or the output tensor of the neural network filter is 2. That is, only the luminance matrix and the chrominance matrix are present in the input tensor and / or the output tensor, the number of channels is 2, and the components are luminance and Cb or luminance and Cr.

[0076] In some embodiments, at least one matrix includes a chrominance matrix and four luminance matrices including luminance components, and the number of channels of the input tensor or the output tensor of the neural network filter is 5. That is, there are only four luminance matrices and one chrominance matrix in the input tensor and / or the output tensor, the number of channels is 5, and the components are luminance and Cb or luminance and Cr.

[0077] In some embodiments, the chroma format of the current video unit is 4:2:0.

[0078] In some embodiments, the chrominance matrix includes one of: a first chrominance component, or a second chrominance component. The two chrominance components may be processed separately by applying a NN filter to one of the two chrominance components.

[0079] In some embodiments, at least one type of visual quality improvement of the neural network filter is included in the bitstream. For example, one or more types of visual quality improvement may be defined.

[0080] In some embodiments, the at least one type is included in a neural network post-processing filter characteristic (NNPFC) supplemental enhancement information (SEI) message. That is, the visual quality improvement type of the NN filter with the purpose of visual quality improvement can be transmitted by signal in the NNPFC SEI message.

[0081] In some embodiments, if the purpose of the neural network filter is visual quality improvement, at least one type is included in the bitstream.

[0082] In some embodiments, the at least one type includes at least one of: an objectively oriented type, a fidelity oriented type, a subjectively oriented type, or a film grain oriented type.

[0083] In some embodiments, the at least one type of visual quality improvement includes an objective-oriented type or a fidelity-oriented type, and the fidelity of the current video unit is determined based on at least one of the following: a peak signal-to-noise ratio of the current video unit, or a multi-scale structural similarity (Ms-SSIM) of the current video unit. That is, the type of visual quality improvement is defined as objective-oriented / fidelity-oriented, and the goal is to increase the fidelity of the reconstructed picture after applying the neural network post-processing filter. Fidelity can be measured by PSNR, Ms-SSIM, etc.

[0084] In some embodiments, the at least one type of visual quality improvement includes a subjectively oriented type, and the subjective visual quality of the current video unit is determined based on at least one of the following: a learned perceptual image patch similarity (LPIPS) of the current video unit, or a mean opinion score (MOS) of the current video unit. That is, the type of visual quality improvement is defined as subjectively oriented, with the goal of increasing the subjective visual quality of the reconstructed picture after applying the neural network post-processing filter. The subjective visual quality can be measured by LPIPS, MOS, etc.

[0085] In some embodiments, the at least one type of visual quality improvement includes a film grain guided type, and the film grain is obtained on a video unit reconstructed after applying a neural network filter to the current video unit. That is, the type of visual quality improvement is defined as film grain guided, where film grain is synthesized on a reconstructed image after applying a neural network post-processing filter.

[0086] In some cases, different video applications may prefer different types of visual quality improvements. For example, fidelity is important in surveillance scenarios, but may not be so critical in some user-generated videos. By including the type of visual quality improvement in the bitstream, the type of visual quality improvement can be identified by, for example, a decoder.

[0087] In some embodiments, the current video unit may be a picture, a slice, or any other video unit.

[0088] In some embodiments, method 500 further includes: receiving a patch width and a patch height from an external source; and determining a patch size for input to the neural network filter based on the patch width and the patch height. For example, the patch width (also referred to as inpPatchWidth) and the patch height (also referred to as inpPatchHeight) may be provided by an unspecified external component.

[0089] In some embodiments, the small block width and small block height are received via an application programming interface. In some embodiments, the application programming interface is at a decoder associated with the conversion. In some embodiments, the entity associated with the video is presented in a video application system, and the small block width and small block height are configured by the user via the user interface of the video application system. For example, an external component can be an API that passes the values ​​of inpPatchWidth and inpPatchHeight to a decoder and a rendering entity in the video application system, and these values ​​can be configured by the user through the user interface of the application.

[0090] In some example embodiments, regardless of the value of nnpfc_constant_patch_size_flag, the patch size may be determined based on the received patch width and patch height. For example, regardless of the value of nnpfc_constant_patch_size_flag, the filtering process takes as input the patch size width inpPatchWidth and the patch size height inpPatchHeight (as indicated below).

[0091] In some embodiments, the tile width is a positive integer multiple of the sum of the fourth syntax element in the bitstream and a predefined value such as 1, and the tile height is a positive integer multiple of the sum of the fifth syntax element in the bitstream and the predefined value.

[0092] In some embodiments, the fourth syntax element (eg, nnpfc_patch_width_minus1) indicates the horizontal sample count of the small block size required for input to the neural network filter. The fifth syntax element (eg, nnpfc_patch_height_minus1) indicates the vertical sample count of the small block size required for input to the neural network filter.

[0093] In some embodiments, the tile width is less than or equal to a threshold width, and the tile height is less than or equal to a threshold height.

[0094] In some embodiments, the threshold width (e.g., CroppedWidth) is the width of the cropped decoded output picture in units of luma samples, and the threshold height (e.g., CroppedHeight) is the height of the cropped decoded output picture in units of luma samples. The threshold width and threshold height are included in the bitstream.

[0095] As an example, the value of inpPatchWidth may be a positive integer multiple of nnpfc_patch_width_minus1+1, and may be less than or equal to CroppedWidth. The value of PatchSizeH may be a positive integer multiple of nnpfc_patch_height_minus1+1, and may be less than or equal to CroppedHeight.

[0096] In some embodiments, the method 500 further includes: if it is determined that the sixth syntax element (e.g., nnpfc_constant_patch_size_flag) in the bitstream is a first value (e.g., 0), receiving a small block width and a small block height. That is, if nnpfc_constant_patch_size_flag is equal to 0, the small block size width represented by inpPatchWidth and the small block size height represented by inpPatchHeight are provided by an external component.

[0097] In some embodiments, the method 500 further includes: if it is determined that the sixth syntax element is a second value (e.g., 1), determining the small block width based on the predefined value and the fourth syntax element in the bitstream; and determining the small block height based on the predefined value and the fifth syntax element in the bitstream. For example, if nnpfc_constant_patch_size_flag is equal to 1, the value of inpPatchWidth is set equal to nnpfc_patch_width_minus1+1, and the value of inpPatchHeight is set equal to nnpfc_patch_height_minus1+1.

[0098] In some embodiments, the sixth syntax element indicates that the neural network filter accepts a tile size that is a positive integer multiple of another tile size, the other tile size indicated by the fourth syntax element and the fifth syntax element.

[0099] In some embodiments, the fourth syntax element indicates a horizontal sample count of a small block size required for input to the neural network filter, and wherein the fifth syntax element indicates a vertical sample count of a small block size required for input to the neural network filter.

[0100] According to another embodiment of the present disclosure, a non-transitory computer-readable recording medium is provided. The non-transitory computer-readable recording medium stores a bitstream of a video generated by a method performed by a device for video processing. In the method, a neural network filter is applied to a current video unit of the video based at least on auxiliary information associated with the current video unit. The auxiliary information includes at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, or encoding and decoding information of a previously encoded and decoded video unit. Based on the application, the bitstream is generated.

[0101] According to some further embodiments of the present disclosure, a method for storing a bitstream of a video is provided. In the method, a neural network filter is applied to a current video unit of the video based at least on auxiliary information associated with the current video unit. The auxiliary information includes at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, or encoding and decoding information of a previously encoded and decoded video unit. Based on the application, the bitstream is generated. The bitstream is stored in a non-transitory computer-readable recording medium.

[0102] Implementations of the present disclosure may be described according to the following clauses, features of which may be combined in any reasonable way.

[0103] Item 1. A method for video processing, comprising: for conversion between a current video unit of a video and a bitstream of the video, applying a neural network filter to the current video unit based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, or encoding and decoding information of a previously encoded and decoded video unit; and performing the conversion based on the application.

[0104] Item 2. The method according to Item 1 further includes: determining whether a condition for excluding the auxiliary information from the input of the neural network is met based on at least one syntax element in the bitstream; and if it is determined that the condition is met, applying the neural network to the current video unit without inputting the auxiliary information to the neural network filter.

[0105] Item 3. A method according to Item 2, wherein the at least one syntax element includes: a first syntax element for indicating a rule for ordering the sample array of the cropped decoded output picture as an input to the neural network filter, a second syntax element for specifying the dimensions in the input tensor to the neural network filter and the output tensor obtained from the neural network filter to be used for channels, and a third syntax element for indicating whether the auxiliary information is present in the input tensor of the neural network filter, and wherein the condition is that the first syntax element is 3, the second syntax element is 0, and the third syntax element is 0.

[0106] Item 4. A method according to any one of Items 1 to 3, wherein the neural network filter comprises a neural network post-processing filter.

[0107] Item 5. The method according to any one of Items 1 to 4, wherein the prediction information of the current video unit includes at least one of the following: a prediction sample of the current video unit, or a prediction mode of the current video unit.

[0108] Item 6. A method according to any one of Items 1 to 5, wherein the partition information of the current video unit includes a partition boundary of the current video unit.

[0109] Item 7. A method according to any one of Items 1 to 5, wherein the encoding and decoding information of the previously encoded and decoded video unit includes: samples of at least one of a co-located block and a motion compensation block in the previously encoded and decoded video unit, the co-located block is co-located with the current video block in the current video unit, and the motion compensation block is associated with the current video block.

[0110] Item 8. A method according to any one of Items 1 to 7, wherein the first color component and the second color component of the current video unit share the same auxiliary information, or the first color component and the second color component are allowed to share the same auxiliary information.

[0111] Item 9. A method according to any one of Items 1 to 7, wherein the first color component and the second color component of the current video unit use different auxiliary information, or the first color component and the second color component are allowed to use different auxiliary information.

[0112] Item 10. A method according to any one of Items 1 to 7, wherein a first chroma component and a second chroma component of the current video unit use the same auxiliary information or are allowed to use the same auxiliary information, and a luminance component of the current video unit uses first auxiliary information, which is different from second auxiliary information used by the first chroma component and the second chroma component.

[0113] Item 11. A method according to any one of Items 1 to 10, wherein at least one matrix associated with the neural network filter includes at least one of the following: a luminance component, a first chrominance component, or a second chrominance component.

[0114] Item 12. A method according to Item 11, wherein the at least one matrix includes at least one of the following: an input matrix in an input tensor of the neural network filter, or an output matrix in an output tensor of the neural network filter.

[0115] Item 13. A method according to Item 11 or Item 12, wherein the at least one matrix includes a chrominance matrix, and the number of channels of the input tensor or the output tensor of the neural network filter is 1.

[0116] Item 14. A method according to Item 11 or Item 12, wherein the at least one matrix includes a chrominance matrix and a luminance matrix including a luminance component, and the number of channels of the input tensor or the output tensor of the neural network filter is 2.

[0117] Item 15. A method according to Item 11 or Item 12, wherein the at least one matrix includes a chrominance matrix and four luminance matrices including luminance components, and the number of channels of the input tensor or the output tensor of the neural network filter is 5.

[0118] Item 16. The method of Item 15, wherein the chroma format of the current video unit is 4:2:0.

[0119] Item 17. A method according to any one of Items 13 to 16, wherein the chrominance matrix includes one of the following: the first chrominance component, or the second chrominance component.

[0120] Item 18. A method according to any one of Items 1 to 17, wherein at least one type of visual quality improvement of the neural network filter is included in the bitstream.

[0121] Item 19. A method according to Item 18, wherein at least one of the types is included in a neural network post-processing filter characteristics (NNPFC) supplemental enhancement information SEI message.

[0122] Item 20. A method according to Item 18 or Item 19, wherein if the purpose of the neural network filter is visual quality improvement, at least one of the types is included in the bitstream.

[0123] Item 21. A method according to any one of Items 18 to 20, wherein the at least one type comprises at least one of the following: an objective-oriented type, a fidelity-oriented type, a subjective-oriented type, and a film grain-oriented type.

[0124] Item 22. A method according to Item 21, wherein the at least one type of visual quality improvement includes the objective-oriented type or the fidelity-oriented type, and the fidelity of the current video unit is determined based on at least one of: a peak signal-to-noise ratio of the current video unit, or a multi-scale structural similarity (Ms-SSIM) of the current video unit.

[0125] Item 23. A method according to Item 21, wherein the at least one type of visual quality improvement includes the subjectively guided type, and the subjective visual quality of the current video unit is determined based on at least one of: a learned perceptual image patch similarity (LPIPS) of the current video unit, or a mean opinion score (MOS) of the current video unit.

[0126] Item 24. A method according to Item 21, wherein the at least one type of visual quality improvement includes the film grain-oriented type, and the film grain is obtained on a video unit reconstructed after applying the neural network filter to the current video unit.

[0127] Item 25. A method according to any one of Items 1 to 24, wherein the current video unit comprises a picture or a slice.

[0128] Item 26. The method according to any one of Items 1 to 25 further includes: receiving a patch width and a patch height from an external source; and determining a patch size for input to the neural network filter based on the patch width and the patch height.

[0129] Item 27. A method according to item 26, wherein the small block width is a positive integer multiple of the sum of a predefined value and a fourth syntax element in the bitstream, and the small block height is a positive integer multiple of the sum of the predefined value and a fifth syntax element in the bitstream.

[0130] Item 28. A method according to Item 27, wherein the fourth syntax element indicates a horizontal sample count of a small block size required for input to the neural network filter, and wherein the fifth syntax element indicates a vertical sample count of a small block size required for input to the neural network filter.

[0131] Item 29. A method according to Item 27 or Item 28, wherein the tile width is less than or equal to a threshold width, and the tile height is less than or equal to a threshold height.

[0132] Item 30. A method according to Item 29, wherein the threshold width is the width of the cropped encoded output picture in units of luma samples, the threshold height is the height of the cropped encoded output picture in units of luma samples, and the threshold width and the threshold height are included in the bitstream.

[0133] Item 31. A method according to any one of Items 26 to 30, wherein the tile width and the tile height are received via an application programming interface.

[0134] Item 32. A method according to Item 31, wherein the application programming interface is at a decoder associated with the conversion.

[0135] Item 33. A method according to any one of Items 26 to 32, wherein the entity associated with the video is presented in a video application system, and the small block width and the small block height are configured by a user via a user interface of the video application system.

[0136] Item 34. The method of any one of Items 26 to 33, further comprising: if it is determined that a sixth syntax element in the bitstream is a first value, receiving the small block width and the small block height.

[0137] Item 35. The method according to Item 34 further includes: if it is determined that the sixth syntax element is a second value, determining the width of the small slice based on a predefined value and a fourth syntax element in the bitstream; and determining the height of the small slice based on the predefined value and a fifth syntax element in the bitstream.

[0138] Item 36. A method according to Item 35, wherein the sixth syntax element indicates that the neural network filter accepts a block size that is a positive integer multiple of another block size, and the other block size is indicated by the fourth syntax element and the fifth syntax element.

[0139] Item 37. A method according to Item 35 or Item 36, wherein the fourth syntax element indicates a horizontal sample count of a small block size required for input to the neural network filter, and wherein the fifth syntax element indicates a vertical sample count of a small block size required for input to the neural network filter.

[0140] Item 38. A method according to any one of Items 1 to 37, wherein the converting comprises encoding the current video unit into the bitstream.

[0141] Item 39. A method according to any one of Items 1 to 37, wherein the converting comprises decoding the current video unit from the bitstream.

[0142] Item 40. An apparatus for video processing, comprising a processor and a non-volatile memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform a method according to any one of items 1 to 39.

[0143] Item 41. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform a method according to any one of Items 1 to 39.

[0144] Item 42. A non-transitory computer-readable recording medium storing a bitstream of a video, the bitstream of the video being generated by a method performed by a device for video processing, wherein the method comprises: applying a neural network filter to a current video unit of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of the following: prediction information of the current video unit, segmentation information of the current video unit, or encoding and decoding information of a previously encoded and decoded video unit; and generating the bitstream based on the application.

[0145] Item 43. A method for storing a bitstream of a video, comprising: applying a neural network filter to a current video unit of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of: prediction information for the current video unit, segmentation information for the current video unit, or encoding and decoding information for a previously encoded and decoded video unit; generating the bitstream based on the application; and storing the bitstream in a non-transitory computer-readable recording medium. Example Device

[0146] Figure 6 A block diagram of a computing device 600 in which various embodiments of the present disclosure may be implemented is shown. The computing device 600 may be implemented as a source device 110 (or video encoder 114 or 200) or a destination device 120 (or video decoder 124 or 300), or may be included in a source device 110 (or video encoder 114 or 200) or a destination device 120 (or video decoder 124 or 300).

[0147] It should be understood that Figure 6The computing device 600 shown in FIG. 6 is for illustrative purposes only and is not intended to in any way imply any limitation on the functionality and scope of the embodiments of the present disclosure.

[0148] like Figure 6 As shown, computing device 600 comprises a general computing device 600. Computing device 600 may include at least one or more processors or processing units 610, memory 620, storage unit 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660.

[0149] In some embodiments, the computing device 600 can be implemented as any user terminal or server terminal with computing power. The server terminal can be a server, a large computing device, etc. provided by a service provider. The user terminal can be, for example, any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a station, a unit, a device, a multimedia computer, a multimedia tablet computer, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It is conceivable that the computing device 600 can support any type of interface to the user (such as a "wearable" circuit device, etc.).

[0150] The processing unit 610 may be a physical processor or a virtual processor and may implement various processes based on a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capability of the computing device 600. The processing unit 610 may also be referred to as a central processing unit (CPU), a microprocessor, a controller, or a microcontroller.

[0151] The computing device 600 typically includes various computer storage media. Such media can be any media accessible by the computing device 600, including but not limited to volatile media and non-volatile media, or removable media and non-removable media. The memory 620 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (such as a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM) or flash memory) or any combination thereof. The storage unit 630 can be any removable or non-removable medium, and can include machine-readable media, such as a memory, a flash drive, a disk, or other media that can be used to store information and / or data and can be accessed in the computing device 600.

[0152] The computing device 600 may also include additional removable / non-removable storage media, volatile / non-volatile storage media. Figure 6 Although not shown in the figure, a disk drive for reading from and / or writing to a removable nonvolatile disk and an optical drive for reading from and / or writing to a removable nonvolatile optical disk may be provided. In this case, each drive may be connected to the bus (not shown) via one or more data medium interfaces.

[0153] The communication unit 640 communicates with another computing device via a communication medium. In addition, the functions of the components in the computing device 600 can be implemented by a single computing cluster or multiple computing machines, which can communicate via a communication connection. Therefore, the computing device 600 can operate in a networked environment using logical connections to one or more other servers, networked personal computers (PCs), or other general network nodes.

[0154] The input device 650 may be one or more of various input devices, such as a mouse, keyboard, trackball, voice input device, etc. The output device 660 may be one or more of various output devices, such as a display, a speaker, a printer, etc. With the aid of the communication unit 640, the computing device 600 may also communicate with one or more external devices (not shown), such as storage devices and display devices, and the computing device 600 may also communicate with one or more devices that enable a user to interact with the computing device 600, or, if necessary, the computing device 600 may also communicate with any device (e.g., a network card, a modem, etc.) that enables the computing device 600 to communicate with one or more other computing devices. Such communication may be performed via an input / output (I / O) interface (not shown).

[0155] In some embodiments, some or all components of the computing device 600 may also be arranged in a cloud computing architecture rather than being integrated in a single device. In a cloud computing architecture, components may be provided remotely and work together to implement the functions described in the present disclosure. In some embodiments, cloud computing provides computing, software, data access and storage services, which will not require the end user to know the physical location or configuration of the system or hardware that provides these services. In various embodiments, cloud computing provides services via a wide area network (such as the Internet) using a suitable protocol. For example, a cloud computing provider provides an application via a wide area network, which can be accessed through a web browser or any other computing component. The software or components of the cloud computing architecture and the corresponding data may be stored on a server at a remote location. The computing resources in a cloud computing environment may be merged or distributed at the location of a remote data center. Cloud computing infrastructure can provide services through a shared data center, although they appear as a single access point to the user. Therefore, the cloud computing architecture may be used to provide the components and functions described herein from a service provider at a remote location. Alternatively, the components and functions described herein may be provided by a conventional server, or may be installed on a client device directly or otherwise.

[0156] In an embodiment of the present disclosure, the computing device 600 may be used to implement video encoding / decoding. The memory 620 may include one or more video encoding / decoding modules 625 having one or more program instructions. These modules are accessible and executable by the processing unit 610 to perform the functions of the various embodiments described herein.

[0157] In an example embodiment performing video encoding, input device 650 may receive video data as input 670 to be encoded. The video data may be processed, for example, by video codec module 625 to generate an encoded bitstream. The encoded bitstream may be provided as output 680 via output device 660.

[0158] In an example embodiment performing video decoding, input device 650 may receive an encoded bitstream as input 670. The encoded bitstream may be processed, for example, by video codec module 625 to generate decoded video data. The decoded video data may be provided as output 680 via output device 660.

[0159] Although the present disclosure has been specifically shown and described with reference to the preferred embodiments of the present disclosure, it will be appreciated by those skilled in the art that various changes may be made in form and detail without departing from the spirit and scope of the present application as defined by the appended claims. These modifications are intended to be encompassed by the scope of the present application. Therefore, the foregoing description of the embodiments of the present application is not intended to be limiting.

Claims

1. A method for video processing, comprising: For conversion between a current video unit of a video and a bitstream of the video, a neural network filter is applied to the current video unit based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of: prediction information of the current video unit, The segmentation information of the current video unit, or codec information for previously encoded video units; and Based on the application, the conversion is performed.

2. The method according to claim 1, further comprising: determining, based on at least one syntax element in the bitstream, whether a condition for excluding the side information from an input to the neural network is satisfied; as well as If it is determined that the condition is satisfied, the neural network is applied to the current video unit without inputting the auxiliary information into the neural network filter.

3. The method of claim 2, wherein the at least one syntax element comprises: a first syntax element for indicating a rule for ordering sample arrays of a cropped decoded output picture as input to the neural network filter, a second syntax element for specifying that the dimensions of the input tensor to the neural network filter and the output tensor from the neural network filter are used for channels, and a third syntax element for indicating whether the auxiliary information is present in the input tensor of the neural network filter, and The condition is that the first syntax element is 3, the second syntax element is 0, and the third syntax element is 0.

4. The method of any one of claims 1 to 3, wherein the neural network filter comprises a neural network post-processing filter.

5. The method according to any one of claims 1 to 4, wherein the prediction information of the current video unit comprises at least one of the following: The predicted sample of the current video unit, or The prediction mode of the current video unit. 6 . The method according to claim 1 , wherein the partition information of the current video unit comprises a partition boundary of the current video unit.

7. The method according to any one of claims 1 to 5, wherein the codec information of the previously encoded video unit comprises: Samples of at least one of a co-located block and a motion compensated block in the previously coded video unit, the co-located block being co-located with a current video block in the current video unit, the motion compensated block being associated with the current video block.

8. The method according to any one of claims 1 to 7, wherein the first color component and the second color component of the current video unit share the same auxiliary information, or The first color component and the second color component are allowed to share the same side information.

9. The method according to any one of claims 1 to 7, wherein the first color component and the second color component of the current video unit use different auxiliary information, or The first color component and the second color component are allowed to use different auxiliary information.

10. The method according to any one of claims 1 to 7, wherein the first chroma component and the second chroma component of the current video unit use the same auxiliary information or are allowed to use the same auxiliary information, and A luma component of the current video unit uses first auxiliary information that is different from second auxiliary information used by the first chroma component and the second chroma component.

11. The method according to any one of claims 1 to 10, wherein at least one matrix associated with the neural network filter comprises at least one of the following: Luminance component, The first chrominance component, or The second chrominance component.

12. The method of claim 11, wherein the at least one matrix comprises at least one of: an input matrix in an input tensor of the neural network filter, or an output matrix in an output tensor of the neural network filter.

13. A method according to claim 11 or claim 12, wherein the at least one matrix includes a chrominance matrix, and the number of channels of the input tensor or the output tensor of the neural network filter is 1.

14. The method according to claim 11 or claim 12, wherein the at least one matrix includes a chrominance matrix and a brightness matrix including a brightness component, and the number of channels of the input tensor or the output tensor of the neural network filter is 2.

15. The method according to claim 11 or claim 12, wherein the at least one matrix includes a chrominance matrix and four brightness matrices including brightness components, and the number of channels of the input tensor or the output tensor of the neural network filter is 5.

16. The method of claim 15, wherein the chroma format of the current video unit is 4:2:

0.

17. The method according to any one of claims 13 to 16, wherein the chrominance matrix comprises one of: the first chrominance component, or the second chrominance component.

18. The method of any one of claims 1 to 17, wherein at least one type of visual quality improvement of the neural network filter is included in the bitstream.

19. The method of claim 18, wherein the at least one type is included in a Neural Network Post-Processing Filter Characteristics (NNPFC) Supplemental Enhancement Information (SEI) message.

20. The method of claim 18 or claim 19, wherein the at least one type is included in the bitstream if the purpose of the neural network filter is visual quality improvement.

21. The method according to any one of claims 18 to 20, wherein the at least one type comprises at least one of: Objective oriented type, Fidelity-oriented type, Subjective orientation type, Film grain guide type.

22. The method of claim 21, wherein the at least one type of visual quality improvement comprises the objective-oriented type or the fidelity-oriented type, and the fidelity of the current video unit is determined based on at least one of: the peak signal-to-noise ratio of the current video unit, or The multi-scale structural similarity (Ms-SSIM) of the current video unit.

23. The method of claim 21, wherein the at least one type of visual quality improvement comprises the subjectively directed type, and the subjective visual quality of the current video unit is determined based on at least one of: the learned perceptual image patch similarity (LPIPS) of the current video unit, or The mean opinion score (MOS) of the current video unit.

24. The method of claim 21, wherein the at least one type of visual quality improvement comprises the film grain guide type, and Film grain is obtained on a video unit reconstructed after applying the neural network filter to the current video unit.

25. The method of any one of claims 1 to 24, wherein the current video unit comprises a picture or a slice.

26. The method according to any one of claims 1 to 25, further comprising: Receive a tile width and a tile height from an external source; as well as Based on the patch width and the patch height, a patch size for an input to the neural network filter is determined.

27. The method of claim 26, wherein the small block width is a positive integer multiple of a sum of a predefined value and a fourth syntax element in the bitstream, and The small block height is a positive integer multiple of a sum of the predefined value and a fifth syntax element in the bitstream.

28. The method of claim 27, wherein the fourth syntax element indicates a horizontal sample count of a desired tile size input to the neural network filter, and The fifth syntax element indicates a vertical sample count of a small block size required for input to the neural network filter.

29. The method of claim 27 or claim 28, wherein the tile width is less than or equal to a threshold width, and The small block height is less than or equal to a threshold height.

30. The method of claim 29, wherein the threshold width is the width of the cropped encoded output picture in units of luma samples, The threshold height is the height of the cropped encoded output picture in units of luma samples, and The threshold width and the threshold height are included in the bitstream.

31. The method of any one of claims 26 to 30, wherein the tile width and the tile height are received via an application programming interface.

32. The method of claim 31, wherein the application programming interface is at a decoder associated with the conversion.

33. A method according to any one of claims 26 to 32, wherein the entity associated with the video is presented in a video application system, and the small block width and the small block height are configured by a user via a user interface of the video application system.

34. The method according to any one of claims 26 to 33, further comprising: If it is determined that the sixth syntax element in the bitstream is the first value, the small block width and the small block height are received.

35. The method of claim 34, further comprising: If it is determined that the sixth syntax element is the second value, Determining the slice width based on a predefined value and a fourth syntax element in the bitstream; as well as The slice height is determined based on the predefined value and a fifth syntax element in the bitstream.

36. The method of claim 35, wherein the sixth syntax element indicates that the neural network filter accepts a tile size that is a positive integer multiple of another tile size, the other tile size indicated by the fourth syntax element and the fifth syntax element.

37. A method according to claim 35 or claim 36, wherein the fourth syntax element indicates a horizontal sample count of a small block size required for input to the neural network filter, and The fifth syntax element indicates a vertical sample count of a small block size required for input to the neural network filter.

38. The method of any one of claims 1 to 37, wherein the converting comprises encoding the current video unit into the bitstream.

39. The method of any one of claims 1 to 37, wherein the converting comprises decoding the current video unit from the bitstream.

40. An apparatus for video processing, comprising a processor and a non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method of any one of claims 1 to 39.

41. A non-transitory computer readable storage medium storing instructions, the instructions causing a processor to execute the method according to any one of claims 1 to 39.

42. A non-transitory computer-readable recording medium storing a bit stream of a video, the bit stream of the video being generated by a method performed by an apparatus for video processing, wherein the method comprises: Applying a neural network filter to a current video unit of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of: prediction information of the current video unit, The segmentation information of the current video unit, or codec information for previously encoded video units; and Based on the application, the bitstream is generated.

43. A method for storing a bitstream of a video, comprising: Applying a neural network filter to a current video unit of the video based at least on auxiliary information associated with the current video unit, the auxiliary information comprising at least one of: prediction information of the current video unit, The segmentation information of the current video unit, or Codec information of previously encoded video units; Based on the application, generating the bitstream; as well as The bit stream is stored in a non-transitory computer-readable recording medium.

Images