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 includes performing a conversion between a video and a bitstream of the video, where at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication, the first indication indicates whether quality information of at least one video unit associated with application of the at least one NNPF is present in the bitstream.

Description

Technical Field

[0001] Embodiments of the present disclosure relate generally to video processing techniques, and more particularly, to a neural network post-processing filter (NNPF). Background Art

[0002] Digital video capabilities are now being used in every aspect of our lives. For video encoding and decoding, various video compression technologies have been proposed, including MPEG-2, MPEG-4, ITU-T H.263, ITU-T H.264 / MPEG-4 Part 10 Advanced Video Codec (AVC), ITU-T H.265 High Efficiency Video Codec (HEVC), and Versatile Video Codec (VVC). However, there is a general desire to further improve the encoding and decoding quality 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 provided. The method comprises performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream comprises a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

[0005] According to the method of the first aspect of the present disclosure, an indication is provided to indicate whether quality information of at least one video unit associated with the application of at least one NNPF is present in the bitstream. Compared with conventional solutions, the proposed method can advantageously enable the application of NNPF based on quality information, thereby improving the encoding and decoding quality.

[0006] In a second aspect, a device for video processing is provided. The device includes a processor and a non-volatile memory having instructions thereon. The instructions, when executed by the processor, cause the processor to perform the method according to the first aspect of the present disclosure.

[0007] In a third aspect, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores instructions, which enable a processor to execute the method according to the first aspect of the present disclosure.

[0008] 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, the bitstream of the video being generated by a method performed by an apparatus for video processing. The method includes performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

[0009] In a fifth aspect, a method for storing a bitstream of a video is provided. The method includes: performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream; and storing the bitstream in a non-transitory computer-readable recording medium.

[0010] 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

[0011] 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.

[0012] Figure 1 A block diagram illustrating an example video encoding and decoding system is shown according to some embodiments of the present disclosure;

[0013] Figure 2 shows a block diagram illustrating a first example video encoder according to some embodiments of the present disclosure;

[0014] Figure 3 shows a block diagram illustrating an example video decoder according to some embodiments of the present disclosure;

[0015] Figure 4 An example of raster scan striping of a picture is shown;

[0016] Figure 5 An example of rectangular strip segmentation of a picture is shown;

[0017] Figure 6shows an example of a picture divided into slices and rectangular strips;

[0018] Figure 7 An example of sub-picture segmentation of a picture is shown;

[0019] Figure 8A An example of a CTB that crosses a picture boundary is shown;

[0020] Figure 8B Another example of a CTB that crosses a picture boundary is shown;

[0021] Figure 8C Another example of a CTB that crosses a picture boundary is shown;

[0022] Figure 9 A diagram showing a luminance data channel;

[0023] Figure 10 A flowchart showing a method for video processing according to an embodiment of the present disclosure is shown; and

[0024] Figure 11 A block diagram is shown of a computing device in which various embodiments of the present disclosure may be implemented.

[0025] Throughout the drawings, the same or similar reference numbers generally refer to the same or similar elements. DETAILED DESCRIPTION

[0026] The principles 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, and do not imply 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.

[0027] 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.

[0028] 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 will include that 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 intended that such feature, structure, or characteristic, whether or not explicitly described, be applicable to other embodiments and that it is within the knowledge of those skilled in the art to apply that feature, structure, or characteristic.

[0029] It should be understood that although the terms "first" and "second" and the like 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. 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 example embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0030] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the example embodiments. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprise," "including," "having," "including," and / or "comprising" when used herein 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. Sample Environment

[0031] Figure 1 is a block diagram illustrating an example video codec system 100 that can utilize the techniques of the present disclosure. As shown, the video codec system 100 can include a source device 110 and a destination device 120. The source device 110 can also be referred to as a video encoding device, and the destination device 120 can also be referred to as a video decoding device. In operation, the source device 110 can be configured to generate encoded video data, and the destination device 120 can be configured to decode the encoded video data generated by the source device 110. The source device 110 can include a video source 112, a video encoder 114, and an input / output (I / O) interface 116.

[0032] The video source 112 may include a source such as a video capture device. Examples of a video capture 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.

[0033] 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 sequence of bits that form a codec representation of the video data. The bitstream may include a coded picture and associated data. The coded picture is a coded representation of the picture. The associated data may include a sequence parameter set, a picture parameter set, and other syntax structures. The I / O interface 116 may include a modulator / demodulator and / or a transmitter. The coded video data may be directly sent to the destination device 120 via the network 130A via the I / O interface 116. The coded video data may also be stored on a storage medium / server 130B for access by the destination device 120.

[0034] 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 source device 110 or 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 a user. The display device 122 may be integrated with the destination device 120, or may be external to the destination device 120, the destination device 120 being configured to interface with an external display device.

[0035] 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.

[0036] Figure 2 is a block diagram illustrating an example of a video encoder 200 according to some embodiments of the present disclosure, which may be Figure 1 An example of the video encoder 114 in the system 100 is shown.

[0037] 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 among 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.

[0038] 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.

[0039] 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 the picture in which the current video block is located.

[0040] 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 in the following sections. Figure 2 are shown separately in the example.

[0041] 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.

[0042] The mode selection unit 203 can, for example, select one of a plurality of codec modes (intra-frame codec or inter-frame codec) 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 can select a combined intra-frame and inter-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 can also select a resolution for the motion vector for the block (e.g., sub-pixel precision or integer pixel precision).

[0043] 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.

[0044] 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, "P slices" and "B slices" may refer to portions of a picture consisting of macroblocks that are independent of macroblocks in the same picture.

[0045] In some examples, motion estimation unit 204 may perform unidirectional prediction on the current video block, and motion estimation unit 204 may search the reference pictures in list 0 or list 1 to find a reference video block for the current video block. Motion estimation unit 204 may then generate a reference index and a motion vector, where the reference index indicates the reference picture in list 0 or list 1 that contains the reference video block, and the motion vector indicates the spatial displacement between the current video block and the reference video block. Motion estimation unit 204 may output the reference index, prediction direction indicator, and motion vector as motion information for the current video block. 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 for the current video block.

[0046] 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 multiple reference indices and multiple motion vectors, the multiple reference indices indicating multiple reference pictures in list 0 and list 1 containing multiple reference video blocks, and the multiple motion vectors indicating multiple spatial displacements between the multiple reference video blocks and the current video block. The motion estimation unit 204 may output the multiple reference indices and multiple motion vectors for the current video block as motion information for the current video block. The motion compensation unit 205 may generate a predicted video block for the current video block based on the multiple reference video blocks indicated by the motion information of the current video block.

[0047] In some examples, motion estimation unit 204 may output a complete set of motion information for use in the decoding process of a decoder. Alternatively, in some embodiments, motion estimation unit 204 may signal the motion information of the current video block with reference to the motion information of another video block. For example, motion estimation unit 204 may determine that the motion information of the current video block is sufficiently similar to the motion information of an adjacent video block.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] The intra-frame prediction unit 206 can perform intra-frame prediction on the current video block. When the intra-frame prediction unit 206 performs intra-frame prediction on the current video block, the intra-frame prediction unit 206 can 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 can include a predicted video block and various syntax elements.

[0052] 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 for the current video block may include residual video blocks corresponding to different sample components of the samples in the current video block.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] The inverse quantization unit 210 and the inverse transform unit 211 may apply inverse quantization and inverse transform, respectively, to the transform coefficient video block 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.

[0057] After reconstruction unit 212 reconstructs the video block, a loop filtering operation may be performed to reduce video blocking artifacts in the video block.

[0058] 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.

[0059] Figure 3 is a block diagram illustrating an example of a video decoder 300 according to some embodiments of the present disclosure. The video decoder 300 may be Figure 1 An example of the video decoder 124 in the system 100 is shown.

[0060] Video decoder 300 may be configured to perform any or all of the techniques of this disclosure. Figure 3 In the example of FIG, video decoder 300 includes multiple functional components. The techniques described in this disclosure can be shared among 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.

[0061] exist Figure 3 In the example of FIG. 3 , 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, 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.

[0062] 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 can decode the entropy-encoded video data, and the motion compensation unit 302 can determine motion information, which includes motion vectors, motion vector precision, reference picture list indexes, and other motion information. The motion compensation unit 302 can determine such information, for example, by performing AMVP and Merge mode. AMVP is used, including deriving several most likely candidates based on data from adjacent PBs and reference pictures. 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 regions in B slices, 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 spatially neighboring blocks or temporally neighboring blocks.

[0063] The motion compensation unit 302 may generate a motion compensated block, possibly performing interpolation based on an interpolation filter. Identifiers for the interpolation filters used with sub-pixel precision may be included in the syntax elements.

[0064] Motion compensation unit 302 may calculate interpolated values for sub-integer pixels of a reference block using interpolation filters used by video encoder 200 during encoding of the video block. Motion compensation unit 302 may determine the interpolation filters used by video encoder 200 based on received syntax information, and motion compensation unit 302 may use the interpolation filters to produce a prediction block.

[0065] The motion compensation unit 302 can use at least part of the syntax information to determine the size of the blocks used to encode the (multiple) frames and / or (multiple) slices of the encoded video sequence, partition information describing how each macroblock of the 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-frame coded block, and other information used to decode the encoded video sequence. As used herein, in some aspects, "slice" can 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 can be an entire picture or a region of a picture.

[0066] The intra prediction unit 303 can 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 inverse 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.

[0067] The reconstruction unit 306 can 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-frame prediction unit 303. If necessary, a deblocking filter can also be applied to the decoded block to remove blocking artifacts. The decoded video block is then stored in the buffer 307, which provides reference blocks for subsequent motion compensation / intra-frame prediction and also produces the decoded video for presentation on a display device.

[0068] Some exemplary embodiments of the present disclosure are described in detail below. It should be noted that the section titles used in this document are for ease of understanding and are not intended to limit the embodiments disclosed in a section to that section. In addition, although some embodiments are described with reference to a multifunctional video codec or other specific video codec, the disclosed technology is also applicable to other video codec technologies. In addition, although some embodiments describe the video coding and decoding steps in detail, it should be understood that the corresponding decoding steps of the decoding will be implemented by the decoder. In addition, the term video processing includes video coding 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 a different compression bit rate. 1. Brief Overview The present disclosure relates to image / video codec technology. Specifically, the present disclosure relates to the use and control of neural network post-processing filters transmitted by signal in a video bitstream. In this document, the use and control can be applied in video units (e.g., pictures / slices / CTUs). For video bitstreams encoded or decoded by any codec (e.g., the Versatile Video Codec (VVC) standard and / or the Versatile SEI Message (VSEI) standard for encoded video bitstreams), the concepts can be applied alone or in various combinations. 2. Abbreviation APS Adaptive Parameter Set AU Access Unit CLVS Codec layer video sequence CLVSS coded layer video sequence starts CRC Cyclic Redundancy Check CVS encoded and decoded 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 (Recommendation ITU-T H.274 | ISO / IEC 23002-7) VUI Video Availability Information VVC Versatile Video Codec (Recommendation ITU-T H.266 | ISO / IEC 23090-3) 3. Introduction 3.1 Video Codec 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 Visual, and the two organizations jointly developed H.262 / MPEG-2 Video, H.264 / MPEG-4 Advanced Video Codec (AVC), and H.265 / HEVC. Since H.262, video codec standards have been based on a hybrid video codec architecture that utilizes temporal prediction plus transform coding. To explore future video codec technologies beyond HEVC, the Joint Video Exploration Team (JVET) was jointly established by VCEG and MPEG in 2015. Since then, JVET has adopted many new approaches and incorporated them into reference software called the Joint Exploration Model (JEM). When the Versatile Video Codec (VVC) project officially began, JVET was later renamed the Joint Video Experts Team (JVET). VVC is a new codec standard that aims to reduce bit rate by 50% compared to HEVC. The standard was 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 conventional 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. Definition of Video Unit A picture is divided into one or more slice rows and one or more slice columns. A slice is a sequence of CTUs covering a rectangular area of the picture. The CTUs in a slice are scanned within the slice in raster scan order. A slice consists of an integer number of complete slices or an integer number of consecutive complete CTU rows within a slice of a picture. Therefore, each vertical slice boundary is always also a vertical slice boundary. The horizontal boundary of a slice may not be a slice boundary but instead consist of a horizontal CTU boundary within a slice; this occurs when the slice is divided into multiple rectangular slices, each of which consists of an integer number of consecutive complete CTU rows within the slice. Two modes of slices are supported: raster scan slice mode and rectangular slice mode. In raster scan slice mode, a slice consists of a sequence of complete slices from a slice raster scan of a picture. In rectangular slice mode, a slice consists of several complete slices that together form a rectangular area of the picture, or several consecutive complete CTU rows of a slice that together form a rectangular area of the picture. Slices within a rectangular slice are scanned in slice raster scan order within the rectangular area corresponding to the slice. A sub-picture consists of one or more strips that together cover a rectangular area of the picture. Therefore, every sub-picture boundary is always also a strip boundary, and every vertical sub-picture boundary is always also a vertical slice boundary. For each sub-image and slice, one or both of the following conditions must be met: - All CTUs in a sub-picture belong to the same slice. - All CTUs in a slice belong to the same sub-picture. Figure 4 An example of raster scan stripe partitioning of a picture is shown, where the picture is divided into 12 slices and 3 raster scan stripes. More specifically, a picture with 18 by 12 luma CTUs is partitioned into 12 slices and 3 raster scan stripes. Figure 5 An example of rectangular slice partitioning of a picture is shown, where the picture is divided into 24 slices (6 slice columns and 4 slice rows) and 9 rectangular slices. More specifically, a picture with 18 by 12 luma CTUs is partitioned into 24 slices and 9 rectangular slices. Figure 6 An example of a picture partitioned into slices and rectangular strips is shown, where the picture is divided into 4 slices (2 slice columns and 2 slice rows) and 4 rectangular strips. Figure 7 An example of sub-picture partitioning of a picture is shown, where the picture is partitioned into 18 slices, with the 12 slices on the left each covering one stripe of 4 by 4 CTUs, and the 6 slices on the right each covering two vertically stacked stripes of 2 by 2 CTUs, resulting in a total of 24 slices and 24 sub-pictures (one sub-picture per stripe) of varying sizes. 3.2.1 CTU / CTB Size In VVC, the CTU size signaled by the syntax element log2_ctu_size_minus2 in the SPS can be as small as 4x4. 3.2.2. CTUs in a Picture Assume the CTB / LCU size indicated by M×N (usually M equals N, as defined in HEVC / VVC), and for a CTB located at the boundary of a picture (or slice or strip or other type, with the picture boundary as an example), K×L samples are within the picture boundary, where K < M or L < N. For those CTBs depicted as Figures 8A to 8C in, the CTB size still equals M×N. However, the bottom boundary / right boundary of the CTB is outside the picture. Figure 8A Fig. 800 is an example showing a CTB spanning the picture boundary, where K = M, L < N, and the CTB spans the bottom picture boundary. Figure 8B Fig. 802 is another example showing a CTB spanning the picture boundary, where K < M, L = N, and the CTB spans the right picture boundary. Figure 8C Fig. 804 is yet another example showing a CTB spanning the picture boundary, where K < M, L < N and the CTB spans the right-bottom picture boundary. 3.3. 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 luminance or chrominance samples through the decoding process. A compliant decoder does not need to process this information for output order consistency. Some SEI messages are required for checking bitstream consistency and output timing decoder consistency. No other SEI messages are required for checking bitstream consistency. Annex D of VVC specifies the syntax and semantics of the SEI message payloads for some SEI messages, and specifies the use of the SEI messages and VUI parameters for which the syntax and semantics are specified in ITU-T H.274|ISO / IEC 23002-7. 3.4. Signaling of Neural Network Post-Processing Filters Existing designs include the specification of two SEI messages for signaling neural network post-processing filters, as follows. 4. Question There are several problems in the current design of Neural Network Post-Processing Filter Activation (NNPFA) and Neural Network Post-Processing Filter Characteristic (NNPFC) SEI messages. 1) The NNPFA and / or NNPFC SEI messages are maintained only for the current picture. However, the neural network post-processing filter (NNPF) may be effective only for a portion of the current picture (such as a slice, codec tree unit, codec unit, codec block, or region of interest). The NNPF may also be effective for the entire sequence, making it efficient to signal only one NNPFA and / or NNPFC message instead of signaling an NNPFA and / or NNPFC message for each picture. Therefore, some regional information needs to be supplemented into the NNPFA and / or NNPFC. 2) There may be several NNPFA and / or NNPFC SEI messages for the same picture. And only one post-processing filter specified by nnpfa_id is activated in one SEI message. However, various contents in a video unit (such as a picture, a slice, a codec unit, etc.) may require different post-processing filters. Multiple sets of filters may be useful for different contents, so that multiple sets of syntax elements for multiple sets of filters should be added to one NNPFA and / or NNPFC SEI message, and how to use / switch post-processing filters for video units needs to be supplemented in the NNPFA and / or NNPFC SEI message. 3) Neural network post-processing filters can improve visual quality performance. Generally speaking, NNPFs with higher complexity can produce better performance improvements. In the current design, SEI messages only provide complexity characteristics, but performance characteristics are ignored. 5. Detailed solution In order to solve the above problems, the following methods are disclosed. The solutions should be considered as examples to explain the general concept and should not be interpreted in a narrow way. In addition, these solutions can be applied individually or in combination in any way. 1) It is proposed that the activation and / or enabling and / or presence and / or use of a neural network post-processing filter (NNPF) for a video unit can be controlled by one or more sets of syntax elements in a video message unit. a. In one example, the video message unit may be a SEI message, such as an NNNPF SEI message. b. In one example, the syntax element group may be expressed as SE_activation. i. In one example, SE_activation may include multiple syntax elements. 1. In one example, one or more nnpfa_ids may be included in SE_activation. a. In one example, multiple filters can be nnpfa_id[i] indicator. i. In one example, i is the index of the filter. 2. In one example, the number of NNPFs may be included in SE_activation. a. In one example, the number of NNPFs may be indicated by nnpfa_num_minus1. 3. In one example, the purpose of the range information of the color component may be included in SE_activation. 4. In one example, the range of color components may be included in SE_activation. c. A video unit can be the whole, part or sub-region of a video / sequence / image in the following items. i. In one example, a video unit may be a sequence. ii. In one example, the video unit may be a picture. iii. In one example, the video unit may be a slice. iv. In one example, the video unit may be a slice / brick. v. In one example, the video unit may be a sub-picture. vi. In one example, a video unit may be one or more CTUs / CTBs. vii. In one example, a video unit may be a CTU / CTB row. viii. In one example, a video unit may be one or more CUs / CBs. ix. In one example, a video unit may be one or more VPDUs (Virtual Pipeline Data Units). x. In one example, a video unit can be a sub-region within a picture / slice / slice / tile. d. A video unit can be one or more picture tiles as follows. i. In one example, a tile is a rectangular array of samples of components from a picture. 1. In one example, the components may be luma or chroma components. 2. In one example, the component may be a Y component or a U (Cb) component or a V (Cr) component. 3. In one example, the component may be an R component or a G component or a B component. ii. In one example, tiles may be defined in a video message. 1. In one example, the tile size can be obtained from the NNPFC SEI message. a. In one example, the width of the small block can be nnpfc_patch_width_minus1+1. b. In one example, the tile height can be A multiple of (nnpfc_patch_width_minus1+1). c. In one example, the width of the small block can be nnpfc_patch_height_minus1+1. d. In one example, the block height can be A multiple of (nnpfc_patch_height_minus1+1). e. A video unit can be one or more regions of interest (ROIs) in the following items. i. In one example, a ROI may include one or more initial points. 1. In one example, the initial point may include a horizontal coordinate (x0). 2. In one example, the initial point may include a vertical coordinate (y0). ii. In one example, a ROI may include one or more end points. 1. In one example, the end point may include a horizontal coordinate (x n ). 2. In one example, the end point may include a vertical coordinate (y n ). iii. In one example, a ROI may include one or more size information. 1. In one example, a ROI can include horizontal samples of the area (width). 2. In one example, a ROI can include vertical sampling points of the area (high). iv. In one example, a ROI may be designated or determined based on the output of applying an image / video segmentation algorithm to the decoded output picture. 1. In one example, all foreground regions are considered as ROIs. 2. In one example, all background regions are considered as ROIs. 3. In one example, regions corresponding to certain types of content (eg, cars, people, cats, sky, etc.) are considered ROIs. v. In one example, a ROI may be designated or determined based on applying an image / video object classification / detection algorithm to the decoded output picture. 1. In one example, the region corresponding to a specific / all categories of detected objects is considered as a ROI. 2. In one example, a region that does not contain any detected objects is considered as a ROI. f. In one example, whether one or more sets of syntax elements should be applied to a video unit (eg, a picture or a slice) may depend on the relative relationship between the video unit and the video message unit when they are signaled. i. In one example, one or more sets of syntax elements should be applied to video units signaled after a video message unit. ii. In one example, one or more sets of syntax elements should be applied to video units signaled prior to video message units. 2) The set of syntax elements indicating activation and / or enabling and / or presence and / or use (denoted as SE_activation) may depend on the color component and / or color format. a. In one example, a syntax element indicating the purpose of the range information of a color component (expressed as SE_color_purpose) may be added to the NNPFA SEI message. i. In one example, one (first) purpose may be that only one set of SE_activation needs to be included in the NNPFA SEI message, and the activation and / or enabling and / or presence and / or use controlled by SE_activation are typically used for the available color components specified in the NNPFC SEI message. 1. In one example, the NNPFC SEI message may define the available color components of the post-processing filter identified by the syntax element nnpfc_id, or restrict the filter to be usable only for specific color components determined by the design of the post-processing filter. 2. In one example, a value of one syntax element of SE_color_purpose equal to 0 specifies the first purpose. ii. In one example, one (second) purpose may be that only one set of SE_activation needs to be included in the NNPFA SEI message, and the activation and / or enabling and / or presence and / or use controlled by the SE_activation is generally for all color components in a specified color range (SE_color_range discussed below). 1. In one example, a value of one syntax element of SE_color_purpose equal to 1 specifies the second purpose. iii. In one example, one (third) purpose may be that multiple sets of SE_activation need to be included in the NNPFA SEI message and need to be used for different color components in a specified color range (SE_color_range in the following discussion). 1. In one example, a value of one syntax element of SE_color_purpose equal to 2 specifies the 3rd purpose. iv. In one example, the syntax element SE_color_purpose may not be signaled. 1. In one example, one purpose (whether in the above discussion or not) can be set as the default purpose. b. In one example, a syntax element indicating the range of color components (expressed as SE_color_range) may be added to the NNPFA SEI message. SE_activation may be used for all color components in the specified color range indicated by SE_color_range. i. In one example, the use of SE_color_range may depend on SE_color_purpose. 1. In one example, when the value of a syntax element of SE_color_purpose is equal to 1 or 2 (equivalent to the second purpose or the third purpose in the above discussion) When SE_color_range is set, SE_color_range can be transmitted through the signal. 2. In one example, when the value of one syntax element of SE_color_purpose is equal to 0 (equivalent to purpose 1 in the above discussion), SE_color_range may not be signaled. ii. In one example, SE_activation may be used for color components in a specified color range indicated by SE_color_range. 1. In one example, one set of SE_activation needs to be included in the NNPFA SEI message and is generally used for all available color components. 2. In one example, multiple sets of SE_activation need to be included in the NNPFA SEI message and for different available color components. a. In one example, the number of SE_activation groups may be equal to the number of available color components. iii. In one example, the color range may include a Y component and / or a U (Cb) component and / or a V (Cr) component. iv. In one example, the color range may include an R component and / or a G component and / or a B component. v. In one example, the maximum number of color components in a color range may be 3, 2, or 1. c. In one example, the syntax element (expressed as SE_activation) can be unified for more than one color component. i. In one example, the syntax element may indicate activation and / or enabling and / or presence and / or use of all color components. 1. In one example, the color components include Y components and / or Cb components and / or Cr component. 2. In one example, the color components include R components and / or G components and / or or B component. ii. In one example, the syntax element may indicate activation and / or enabling and / or presence and / or use of chroma components. 1. In one example, the color components include a Cb component and a Cr component. d. In one example, the syntax element (expressed as SE_activation) may be separate for color components. i. In one example, the syntax elements may be different for all color components. 1. In one example, a first set of syntax elements may be used for a first color component. a. In one example, the first color component may be a Y component and / or a Cb component and / or a Cr component. b. In one example, the first color component may be an R component and / or a G component and / or a B component. 2. In one example, a second set of syntax elements may be used for the second color component. a. In one example, the second color component may be a Cb component and / or a Y component and / or a Cr component. b. In one example, the second color component may be a G component and / or an R component and / or a B component. 3. In one example, a third set of syntax elements may be used for a third color component. a. In one example, the third color component may be a Cr component and / or a Y component and / or a Cb component. b. In one example, the third color component may be a B component and / or a G component and / or an R component. ii. In one example, the syntax element (expressed as SE_activation) may be different for luma and chroma color components. 1. In one example, a first set of syntax elements may be used for the luma component. 2. In one example, a second set of syntax elements may be used for chroma components. a. In one example, the second set of syntax elements may be the same for the Cb component and the Cr component. 3) How / whether to signal the syntax element group indicating activation and / or enablement and / or presence and / or use (denoted as SE_activation) may depend on the number of NNPFs. a. In one example, one or more syntax elements indicating the number of NNPFs may be added to the NNPFASEI message. i. In one example, the syntax element may be expressed as nnpfa_num_minus1. 1. In one example, the number of NNPFs may be equal to nnpfa_num_minus1+1. 2. In one example, the value of nnpfa_num_minus1 must be between 0 and 2 k The range is -1 (including the boundary value). a. In one example, k can be an integer, such as 0, 1, 2, 3, 4, 5, 6, 7, …, 32. 3. In one example, the value of nnpfa_num_minus1 must be in the range of 0 to 255 (inclusive). 4. In one example, when nnpfa_num_minus1 does not exist, The value of nnpfa_num_minus1 is inferred to be equal to 0. 5. In one example, nnpfa_num_minus1 may depend on the region type of the NNPF. a. In one example, the region type of the NNPF can be represented by nnpfa_region_type directive. b. In one example, when nnpfa_region_type is equal to a specific value, nnpfa_num_minus1 may not be signaled. c. In one example, when nnpfa_region_type is equal to 0, nnpfa_num_minus1 may not be signaled. ii. In one example, the number of NNPFs may be ue(v) coded. b. In one example, the number of NNPFs may be less than the maximum value of nnpfc_id plus 1. c. In one example, the number of NNPFs may not be signaled to NNPFA SEI message. i. In one example, the number of NNPFs may be set to a default value. ii. In one example, the number of NNPFs may be 1. 4) One or more syntax elements indicating the identity of the NNPF may be added to the NNPFA SEI message. a. In one example, the identifier of the NNPF may be nnpfa_id. b. In one example, the identification of the NNPF may be included in SE_activation. c. In one example, more than one NNPF identifier may be added to NNPFA SEI message. i. In one example, the i-th filter may be indicated by nnpfa_id[i]. ii. In one example, nnpfa_id[i] specifies that the i-th neural network post-processing filter specified by one or more neural network post-processing filter characteristics SEI messages can be used for post-processing filtering of the current picture, wherein the one or more neural network post-processing filter characteristics SEI messages are related to the current picture and have nnpfc_id equal to nnfpa_id[i]. d. In one example, the number of NNPFs identified may depend on the color components. e. In one example, the number of identifications of NNPFs may depend on the number of NNPFs. i. In one example, the number of NNPFs may be indicated by nnpfa_num_minus1. ii. In one example, the number of NNPF identifiers may be equal to the number of NNPFs (nnpfa_num_minus1+1). 5) One or more syntax elements indicating the region type of the NNPF (denoted as SE_region_type) may be added to the NNPFA and / or NNPFC SEI messages. a. In one example, the region type of NNPF may be included in SE_activation. i. In one example, the region type of NNPF may be indicated by nnpfa_region_type. b. In one example, a region can be a type of video unit. c. In one example, one or more syntax elements indicating the region scope (SE_region_scope) of the NNPF may be added to the NNPFA SEI message of the corresponding region type. i. In one example, the area scope of the NNPF may be included in SE_activation. 1. In one example, when the region type is ROI, the region range of NNPF may be included. ii. In one example, the region range may depend on the region type. iii. In one example, when the area type is the same as the setting value, the area range may be transmitted through a signal or may not be transmitted through a signal. 1. In one example, the region type is a picture. d. In one example, a region may be all or part or a sub-region of a video / sequence / image. i. In one example, a region can be a sequence. ii. In one example, the region may be a picture. iii. In one example, the region may be a strip. iv. In one example, a region may be a slice / brick. v. In one example, a region may be a sub-picture. vi. In one example, a region may be one or more CTUs / CTBs. 1. In one example, when the region type is CTU / CTB, one or more syntax elements indicating the identity of the CTU / CTB of the NNPF may be added to the NNPFA SEI message. a. In one example, the identity of a CTU / CTB may be indicated by coordinates. b. In one example, the identities of CTUs / CTBs may be indicated one by one (in sequence) by index. vii. In one example, a region may be a CTU / CTB row. 1. In one example, when the region type is CTU / CTB row, one or more syntax elements indicating the identity of the CTU / CTB row of the NNPF may be added to the NNPFA SEI message. a. In one example, the identification of the CTU / CTB row can be The coordinates of the CTU / CTB rows are indicated. b. In one example, the identification of the CTU / CTB row can be represented by The indices of the CTU / CTB rows are indicated one by one (in sequence). viii. In one example, a region may be one or more CUs / CBs. 1. In one example, when the region type is CTU / CTB, one or more syntax elements indicating the identity of the CU / CB of the NNPF may be added to the NNPFA SEI message. a. In one example, the identity of a CU / CB may be indicated by coordinates. b. In one example, the identities of CUs / CBs may be indicated one by one (in sequence) by index. ix. In one example, a region may be one or more VPDUs (Virtual Pipeline Data Units). 1. In one example, when the region type is CTU / CTB, one or more syntax elements indicating the identity of the VPDU of the NNPF may be added to the NNPFA SEI message. a. In one example, the identity of a VPDU may be indicated by coordinates. b. In one example, the identities of the VPDUs may be indicated one by one (in sequence) by an index. x. In one example, a region may be a sub-region within a picture / strip / slice / tile. e. In one example, a region may be one or more picture tiles. i. In one example, when the region type is small block, one or more syntax elements indicating the size of the small block of the NNPF may be added to the NNPFA SEI message. ii. In one example, when the region type is small tile, one or more syntax elements indicating the horizontal and / or vertical and / or total number of small tiles of the NNPF may be added to the NNPFASEI message. f. In one example, the region may be one or more regions of interest (ROIs). i. In one example, when the region type is ROI, one or more syntax elements indicating the starting point of the ROI of the NNPF may be added to the NNPFA SEI message. ii. In one example, when the region type is ROI, one or more syntax elements indicating the end point of the ROI of the NNPF may be added to the NNPFA SEI message. iii. In one example, when the region type is ROI, one or more syntax elements indicating the horizontal samples (width) of the ROI of the NNPF may be added to the NNPFA SEI message. iv. In one example, when the region type is ROI, one or more syntax elements indicating the vertical samples (height) of the ROI of the NNPF may be added to the NNPFA SEI message. g. In one example, when the region type is different from common region types such as picture, slice, and CTU, the region may be one or more new regions. i. In one example, the new region may be represented by additional information (such as dimensions and / or location and / or coordinates), and the type of the new region may be different from the region types registered in the standard (such as picture, slice, CTU). 1. In one example, the dimension information of the new region may include horizontal samples (width) and / or vertical samples (height). 2. In one example, the location information of the new area may include the coordinates of the starting point, such as (x0, y0). 3. In one example, the location information of the new area may include the coordinates of the end point, such as (x1, y1). ii. In one example, a new region may overlap with other new regions. iii. In one example, a new area may not overlap with other new areas. iv. In one example, the dimension information may be the same for all new regions. 1. In one example, uniform dimension information may be transmitted via a signal. v. In one example, the dimension information may be different for all new regions. 1. In one example, dimension information may be signaled for each region. h. In one example, the region type of the NNPF may not be signaled. i. In one example, the region type may be set to a default type. 1. In one example, the region type may be picture level. ii. In one example, the region type may have the lowest level. 1. In one example, the lowest level region type may be the tile level. iii. In one example, the use and / or switching and / or activation of NNPF may be dictated by a specific sequence. 1. In one example, the sequence level can be applied before the picture level. i. In one example, nnpfa_region_type equal to 0 indicates that the SEI message activates a neural network post-processing filter (NNPF) applied to the current picture. i. In one example, when nnpfa_region_type is equal to 0, nnpfa_num_minus1 may not be signaled. j. In one example, nnpfa_region_type greater than 0 indicates that the SEI message activates one or more NNPFs. i. In one example, when nnpfa_region_type is equal to 1, for each slice of the current picture, it is indicated that no neural network post-processing filter is applied or the applied NNPF is indicated. ii. In one example, when nnpfa_region_type is equal to 2, for each CTU of the current picture, it is indicated that no neural network post-processing filter is applied or the applied NNPF is indicated. iii. In one example, when nnpfa_region_type is equal to 3, for the picture and / or each slice and / or each CTU of the current picture, it is indicated that no neural network post-processing filtering is applied or the applied NNPF is indicated. iv. In one example, when nnpfa_region_type is equal to 4, for each sub-region of the current picture, it is indicated that no neural network post-processing filter is applied or the applied NNPF is indicated. k. In one example, the value of nnpfa_region_type shall be in the range of 0 to 31 (inclusive). Values of nnpfa_region_type greater than 2, 3, or 4 are reserved for future specifications by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this version of this specification. l. In one example, a decoder conforming to this specification shall ignore NNPFA SEI messages with nnpfa_region_type greater than 2 or 3 or 4. m. In one example, nnpfa_region_type can be ue(v) codec. 6) One or more syntax elements indicating the use and / or switching and / or activation of NNPF may be added to the NNPFA SEI message. a. Syntax elements may depend on the region type. i. In one example, only syntax elements at the region level that specify the region type may be added to the NNPFASEI message. 1. In one example, the NNPFA SEI message may include a syntax element indicating NNPF at a picture level when the region type is a picture. a. In one example, the use of NNPF at picture level may be indicated by nnpfa_picture_enabling_flag[i]. i. In one example, only one NNPF is represented by NNPFA SEI The nnpfa_id in the message indicates this. b. In one example, the usage of NNPF at picture level may be indicated by nnpfa_picture_index[i]. i. In one example, one or more NNPFs are nnpfa_id[i] indication in NNPFA SEI message. 2. In one example, the NNPFA SEI message may include a syntax element indicating NNPF at a slice level when the region type is a slice. a. In one example, the use of NNPF at the slice level may be indicated by nnpfa_slice_enabling_flag[i]. i. In one example, only one NNPF is represented by NNPFA SEI The nnpfa_id in the message indicates this. b. In one example, the usage of NNPF at the slice level may be indicated by nnpfa_slice_index[i]. i. In one example, one or more NNPFs are nnpfa_id[i] indication in NNPFA SEI message. 3. In one example, the NNPFA SEI message may include a syntax element indicating NNPF at the CTU level when the region type is CTU. a. In one example, the use of NNPF at the CTU level may be indicated by nnpfa_ctu_enabling_flag[i]. i. In one example, only one NNPF is represented by NNPFA SEI The nnpfa_id in the message indicates this. b. In one example, the use of NNPF at CTU level may be indicated by nnpfa_ctu_index[i]. i. In one example, one or more NNPFs are indicated by nnpfa_id[i] in the NNPFA SEI message. 4. In one example, when the region type is a new region type (which may be represented by additional information such as dimensions and / or locations and / or coordinates), NNPFA The SEI message may include a syntax element indicating the NNPF at the new region level. a. In one example, the use of NNPF at CTU level may be indicated by nnpfa_region_enabling_flag[i]. i. In one example, only one NNPF is represented by NNPFA SEI The nnpfa_id in the message indicates this. b. In one example, the usage of NNPF at CTU level may be indicated by nnpfa_region_index[i]. i. In one example, one or more NNPFs are nnpfa_id[i] indication in NNPFA SEI message. b. One or more syntax elements indicating the usage of NNPF at the region (video unit) level may be added to the NNPFA SEI message. i. In one example, syntax elements for different region levels may be signaled in a specific order. 1. In one example, syntax elements of higher area levels may be signaled before lower area levels. 2. In one example, when the region type is equal to nnpfa_region_type, the syntax elements of the region may be signaled. a. In one example, when nnpfa_region_type is equal to 0 or 3, nnpfa_picture_index[i] is signaled. b. In one example, when nnpfa_region_type is equal to 0 or 3, nnpfa_picture_enabling_flag[i] is signaled. c. In one example, when nnpfa_region_type is equal to 1 or 3, nnpfa_slice_index[i] is signaled. d. In one example, when nnpfa_region_type is equal to 1 or 3, nnpfa_slice_enabling_flag[i] is signaled. e. In one example, when nnpfa_region_type is equal to 2 or 3, nnpfa_ctu_index[i] is transmitted through the signal. f. In one example, when nnpfa_region_type is equal to 2 or 3, nnpfa_ctu_enabling_flag[i] is signaled. g. In one example, when nnpfa_region_type is equal to 4, nnpfa_region_index[i] is transmitted through the signal. ii. In one example, a syntax element may indicate whether NNPF is used in the current region level. 1. In one example, a syntax element equal to 0 may indicate that NNPF is not used in the current region. a. In one example, the syntax element can be nnpfa_slice_enabling_flag[i], nnpfa_ctu_enabling_flag[i]. b. In one example, the syntax elements may be nnpfa_slice_index[i], nnpfa_ctu_index[i]. 2. In one example, a syntax element equal to 1 may indicate that NNPF is used in the current region. a. In one example, the syntax element can be nnpfa_slice_enabling_flag[i], nnpfa_ctu_enabling_flag[i]. 3. In one example, a syntax element greater than 0 may indicate that NNPF is used in the current region. a. In one example, the syntax element can be nnpfa_slice_index[i], nnpfa_ctu_index[i]. b. In one example, the syntax element should be less than nnpfa_num_minus1+2. 4. In one example, a syntax element equal to nnpfa_num_minus1+2 may indicate that NNPF is used in a sub-region of the current region. a. In one example, the syntax element can be nnpfa_slice_index[i],nnpfa_ctu_index[i] iii. In one example, a syntax element may indicate how to select an NNPF in the current region level or which NNPF to use in the current region level. 1. In one example, a syntax element greater than 0 may indicate that the NNPF with index (syntax element - 1) is used in the current region. a. In one example, the syntax elements may be nnpfa_slice_index[i], nnpfa_ctu_index[i]. 2. In one example, a syntax element smaller than maxNnpfNum may indicate that the NNPF with index (syntax element) is used in the current region. iv. In one example, a syntax element may indicate whether NNPF is adaptively used in the next (lower) region level. 1. In one example, a syntax element equal to 0 may indicate that the NNPF is adaptively selected in the next region level. 2. In one example, a syntax element equal to maxNnpfNum may indicate that the NNPF is adaptively selected in the next region level. 3. In one example, a syntax element equal to (maxNnpfNum-1) may indicate that the NNPF is adaptively selected in the next region level. v. In one example, the signaling of syntax elements at the current region level may depend on syntax elements at the previous (higher) region level. vi. In one example, the area of region A being greater than the area of region B may indicate that the level of region A is greater than the level of region B and the level of region B is lower than the level of region A. 1. In one example, the picture level is lower than the sequence level. 2. In one example, the stripe level is lower than the picture level. 3. In one example, the CTU level is lower than the slice level. 4. In one example, the CU level is lower than the CTU level. 5. In one example, the CU level is lower than the CTU level. c. One or more syntax elements indicating the usage of NNPF at the sequence level may be added to the NNPFA SEI message. i. In one example, the syntax element may indicate that NNPF is applied at the sequence level or lower. ii. In one example, syntax elements at the sequence level may not be signaled. d. One or more syntax elements indicating the use of NNPF at the TID level may be added to the NNPFA SEI message. i. In one example, syntax elements at the TID level may depend on syntax elements at higher levels. ii. In one example, the syntax element may indicate that NNPF is applied at the TID level or lower. 1. In one example, a syntax element indicating the TID index may be added to the NNPFA SEI message. iii. In one example, syntax elements at the TID level may not be signaled. e. One or more syntax elements indicating the use of NNPF at the picture level may be added to the NNPFA SEI message. i. In one example, syntax elements at the picture level may depend on syntax elements at higher levels. ii. In one example, the syntax element may indicate that NNPF is applied at the picture level or lower level. iii. In one example, the syntax element may indicate whether NNPF is applied or not applied at the picture level. iv. In one example, the syntax element may indicate the index of the NNPF applied at the picture level. v. In one example, syntax elements at the picture level may not be signaled. vi. In one example, the use of NNPF at picture level may be indicated by nnpfa_picture_enabling_flag. 1. In one example, nnpfa_picture_enabling_flag equal to 2 indicates that the post-processing filter is used for the sub-region of the current picture. a. In one example, the sub-region of the current picture may be in slice / sub-block / CTU / CTB / tile level. b. In one example, the use of the i-th sub-region of the current picture may be indicated by nnpfa_slice_enabling_flag[i]. c. In one example, the use of the i-th sub-region of the current picture may be indicated by nnpfa_ctu_enabling_flag[i]. d. In one example, the use of the i-th sub-region of the current picture can be indicated by nnpfa_region_enabling_flag[i]. 2. In one example, nnpfa_picture_enabling_flag equal to 1 indicates that post-processing filters are used for the current picture. 3. In one example, nnpfa_picture_enabling_flag equal to 0 indicates that the post-processing filter is not used for the current picture. vii. In one example, the usage of NNPF at picture level may be indicated by nnpfa_picture_index. 1. In one example, nnpfa_picture_index equal to 0 indicates that neural network post-processing filtering is not used for the current picture. 2. In one example, nnpfa_picture_index greater than 0 indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_picture_index-1] is used for the current picture. a. In one example, nnpfa_picture_index should be less than nnpfa_num_minus1+2. 3. In one example, nnpfa_picture_index equal to nnpfa_num_minus1+2 indicates that the post-processing filter can be used for the sub-region of the current picture. a. In one example, the sub-region of the current picture may be in slice / sub-block / CTU / CTB / tile level. b. In one example, the usage of the i-th sub-region of the current picture can be indicated by nnpfa_slice_index[i]. c. In one example, the usage of the i-th sub-region of the current picture can be indicated by nnpfa_ctu_index[i]. d. In one example, the use of the i-th sub-region of the current picture can be indicated by nnpfa_region_index[i]. 4. In one example, the value of nnpfa_picture_index must be in the range of 0 to nnpfa_num_minus1+1 (including the boundary values). 5. In one example, the value of nnpfa_picture_index must be in the range of 0 to nnpfa_num_minus1+2 (including the boundary values). f. One or more syntax elements indicating the use of NNPF at the slice level may be added to the NNPFA SEI message. i. In one example, syntax elements at a slice level may depend on syntax elements at a higher level. ii. In one example, the syntax element may indicate that NNPF is applied at the slice level or lower level. iii. In one example, syntax elements at the slice level may not be signaled. iv. In one example, the use of NNPF at the slice level may be indicated by nnpfa_slice_enabling_flag[i]. 1. In one example, nnpfa_slice_enabling_flag[i] equal to 2 indicates that the post-processing filter is used for the sub-region of the i-th slice of the current picture. a. In one example, the sub-region of the i-th slice of the current picture may be at the sub-block / CTU / CTB / small block level. b. In one example, the use of the j-th sub-region of the i-th slice of the current picture may be indicated by nnpfa_ctu_enabling_flag[j]. 2. In one example, nnpfa_slice_enabling_flag[i] equal to 1 indicates that the post-processing filter is used for the i-th slice of the current picture. 3. In one example, nnpfa_slice_enabling_flag[i] equal to 0 indicates that the post-processing filter is not used for the i-th slice of the current picture. v. In one example, the usage of NNPF at the slice level may be indicated by nnpfa_slice_index[i]. 1. In one example, nnpfa_slice_index[i] equal to 0 indicates that neural network post-processing filtering is not used for the i-th slice of the current picture. 2. In one example, nnpfa_slice_index[i] greater than 0 indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_slice_index[i]-1] is used for the i-th slice of the current picture. a. In one example, nnpfa_slice_index[i] should be less than nnpfa_num_minus1+2. 3. In one example, nnpfa_slice_index[i] equal to nnpfa_num_minus1+2 indicates that the post-processing filter can be used for the sub-region of the i-th slice of the current picture. a. In one example, the sub-region of the i-th slice of the current picture may be at the sub-block / CTU / CTB / small block level. b. In one example, the use of the j-th sub-region of the i-th slice of the current picture may be indicated by nnpfa_ctu_index[j]. 4. In one example, the value of nnpfa_slice_index[i] must be in the range of 0 to nnpfa_num_minus1+1 (including the boundary values). 5. In one example, the value of nnpfa_slice_index[i] must be in the range of 0 to nnpfa_num_minus1+2 (including the boundary values). g. One or more syntax elements indicating the usage of NNPF at sub-block / CTU / CTB / small-block level may be added to the NNPFA SEI message. i. In one example, syntax elements at the sub-block / CTU / CTB / tile level may depend on syntax elements at a higher level (eg, picture / slice / sequence level). ii. In one example, the syntax element may indicate whether NNPF is applied or not applied at the block / CTU / CTB / tile level. iii. In one example, the syntax element may indicate the index of the NNPF applied at the block / CTU / CTB / tile level. iv. In one example, the syntax element may indicate that NNPF is applied at the sub-block / CTU / CTB / small block level or lower. v. In one example, syntax elements at the sub-block / CTU / CTB / tile level may not be signaled. vi. In one example, the use of NNPF at the CTU level may be indicated by nnpfa_ctu_enabling_flag[i]. 1. In one example, nnpfa_ctu_enabling_flag[i] equal to 1 indicates that the post-processing filter is used for the i-th CTU of the current picture. 2. In one example, nnpfa_ctu_enabling_flag[i] equal to 0 indicates that the post-processing filter is not used for the i-th CTU of the current picture. vii. In one example, the use of NNPF at the CTU level may be indicated by nnpfa_ctu_index[i]. 1. In one example, nnpfa_ctu_index[i] equal to 0 indicates that neural network post-processing filtering is not used for the i-th CTU of the current picture. 2. In one example, nnpfa_ctu_index[i] greater than 0 indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_ctu_index[i]-1] is used for the i-th CTU of the current picture. 3. In one example, the value of nnpfa_ctu_index[i] must be in the range of 0 to nnpfa_num_minus1+1 (including the boundary values). h. One or more syntax elements indicating the usage of NNPF at ROI level may be added to the NNPFA SEI message. i. In one example, syntax elements at the ROI level may depend on syntax elements at higher levels. ii. In one example, the syntax element may indicate that NNPF is applied at the ROI level or lower. iii. In one example, syntax elements at the ROI level may not be signaled. i. One or more syntax elements indicating the use of NNPF at the new region level may be added to the NNPFASEI message. i. In one example, syntax elements at the new region level may depend on syntax elements at a higher level (eg, picture / slice / sequence level). ii. In one example, a syntax element may indicate whether NNPF is applied at the new region level. iii. In one example, the syntax element may indicate the index of the NNPF to be applied at the new region level. iv. In one example, the syntax element may indicate that NNPF is applied at the new region level or at a lower level. v. In one example, syntax elements at the new region level may not be signaled. vi. In one example, the usage of NNPF at the new region level may be indicated by nnpfa_region_enabling_flag[i]. 1. In one example, nnpfa_region_enabling_flag[i] equal to 1 indicates that the post-processing filter is used for the i-th new region of the current picture. 2. In one example, nnpfa_region_enabling_flag[i] equal to 0 indicates that the post-processing filter is not used for the i-th new region of the current picture. vii. In one example, the use of NNPF at a new region level may be indicated by nnpfa_region_index[i]. 1. In one example, nnpfa_region_index[i] equal to 0 indicates that neural network post-processing filtering is not applied to the i-th new region of the current picture. 2. In one example, nnpfa_region_index[i] greater than 0 indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_region_index[i]-1] is used for the i-th new region of the current picture. 3. In one example, the value of nnpfa_region_index[i] must be in the range of 0 to nnpfa_num_minus1+1 (including the boundary values). viii. In one example, additional information of the new region, such as the dimension and / or location of the new region, may be indicated by adding syntax elements to the NNPF SEI message. 1. In one example, the horizontal samples or width of the i-th new region can be indicated by nnpfa_region_width[i]. 2. In one example, the vertical sample or height of the i-th new region can be indicated by nnpfa_region_height[i]. 3. In one example, the starting point of the i-th new region in the horizontal direction or in the x-direction may be indicated by nnpfa_region_x0[i]. 4. In one example, the starting point of the vertical direction or y direction of the i-th new region can be indicated by nnpfa_region_y0[i]. 5. In one example, the end point of the i-th new region in the horizontal direction or in the x-direction may be indicated by nnpfa_region_x1[i]. 6. In one example, the end point of the vertical direction or the y direction of the i-th new region can be indicated by nnpfa_region_y1[i]. 7. In one example, whether the dimension is the same for all new regions can be indicated by nnpfa_region_dim_flag. a. In one example, nnpfa_region_dim_flag equal to 0 indicates that the width and height may be the same for all new regions. b. In one example, nnpfa_region_dim_flag equal to 1 indicates that the width and height may be different for all new regions. 8. In one example, whether the new region overlaps may be indicated by nnpfa_region_overlap_flag. a. In one example, nnpfa_region_overlap_flag A value equal to 0 indicates that the new region does not overlap. b. In one example, nnpfa_region_overlap_flag A value equal to 1 indicates that the new regions have some common points or regions. j. In one example, the syntax elements in the NNPFA SEI message may be used for the same video unit / region until a new sequence / SEI is satisfied. k. In one example, syntax elements in the NNPFA SEI message may be used for the nearest video unit / region. 7) One or more syntax elements indicating improvements / promotions of NNPF may be added to the NNPFA and / or NNPFCSEI messages. a. One or more syntax elements indicating the performance indicator (or purpose) of the NNPF may be added to the NNPFA and / or NNPFC SEI messages. i. In one example, the goal may be to improve subjective / objective quality. b. One or more syntax elements indicating the performance level of the NNPF may be added to NNPFA and / or NNPFC SEI messages. i. In one example, the performance level may be a normalized value. ii. In one example, the performance levels may be different or the same for different performance indicators (purposes). c. One or more syntax elements indicating the complexity level of the NNPF may be added to NNPFA and / or NNPFC SEI messages. i. In one example, the complexity level may be a normalized value. 8) It is proposed that one or more groups of syntax elements may be added to the NNPFC SEI message to indicate multiple NNPFs and / or characteristics of NNPFs. a. In one example, one or more syntax elements indicating the number of NNPFs may be added to the NNPFCSEI message. i. In one example, the syntax element may be expressed as nnpfc_num_minus1. 1. In one example, the number of NNPFs may be equal to nnpfc_num_minus1+1. 2. In one example, the value of nnpfc_num_minus1 must be between 0 and 2 k The range is -1 (including the boundary value). a. In one example, k can be an integer, such as 0, 1, 2, 3, 4, 5, 6, 7, …, 32. ii. In one example, the number of NNPFs may be ue(v) coded. iii. In one example, the number of NNPFs may be less than the maximum value of nnpfc_id plus 1. b. In one example, the number of NNPFs may not be signaled in the NNPFC SEI message. i. In one example, the number of NNPFs may be set to a default value. ii. In one example, the number of NNPFs can be 1, 2, 3, 4, or 5. c. In one example, the number of groups of syntax elements indicating characteristics of NNPFs may depend on the number of groups of NNPFs. i. In one example, the number of groups of syntax elements indicating characteristics of NNPFs may be equal to the number of NNPFs. d. In one example, multiple sets of syntax elements indicating characteristics of the NNPF may be signaled for each / all / different NNPFs. i. In one example, each NNPF may have a set of syntax elements that indicate characteristics of the NNPF. ii. In one example, groups of syntax elements may be signaled in a specific order. 1. In one example, groups of syntax elements may be signaled one by one. iii. In one example, the i-th set of syntax elements indicating characteristics of the NNPF may be used for the i-th NNPF. 1. In one example, the first set of syntax elements indicating characteristics of the NNPF may be used for the first NNPF. 2. In one example, a second set of syntax elements indicating characteristics of the NNPF may be used for the second NNPF. 3. In one example, a third set of syntax elements indicating characteristics of an NNPF may be used for the third NNPF. iv. In one example, the design of each group of syntax elements may be the same. 1. In one example, the number and / or items of each group of syntax elements may be the same. 2. In one example, nnpfc_id may be included in each set of syntax elements. 3. In one example, nnpfc_mode_idc may be included in each set of syntax elements. 9) To solve issue 3, the following one or more syntax elements indicating information about quality improvement brought about by NNPF may be signaled in the NNPFA SEI message. a. In one example, an indication is signaled to indicate whether quality improvement information is signaled. i. In one example, when quality improvement information is signaled, the following one or more syntax elements indicating a quality change and a quality metric type are signaled. 1. In one example, these elements indicate quality improvement for the entire video sequence. 2. In one example, these elements indicate quality improvements of one or more pictures. 3. In one example, the quality metric type is signaled. a. In one example, the quality metric type may be PSNR. b. In one example, the quality metric type may be SSIM. c. In one example, the quality metric type may be MS- SSIM. d. In one example, the quality metric type can be VMAF. 4. In one example, the quality change is signaled and indicated by the type of quality metric signaled. a. In one example, the quality change is the difference in video quality between applying NNPF and not applying NNPF. b. In one example, alternatively, the quality change is the difference in video quality between not applying NNPF and applying NNPF. 5. In one example, multiple quality metric types and quality changes are signaled for one NNPFA SEI message. a. In one example, an indication is signaled to indicate the number of quality metric types. i. In one example, multiple quality metric types and quality changes are signaled following the indication. ii. In one example, when the indication quality improvement information is not transmitted through the signal, No further syntax elements are signaled. b. In one example, quality improvement information is always signaled in the NNPFA SEI message. 6. Examples Following are some example embodiments of the solution aspects outlined above in Section V. The most relevant sections that have been added or modified are Underlined , and some of the deleted parts are shown as There may be some other changes that are editorial in nature and therefore not highlighted. Example 1 6.2. Example 2 6.3. Example 3 6.4. Example 4 6.5. Example 5 6.6. Example 6 6.7. Example 7 6.8. Example 8 6.9. Example 9 6.10. Example 10 Example 11 This example is directed to solution item 9 and all sub-items outlined in Section 5 above. Example 12 This example is directed to solution item 9 and all sub-items outlined in Section 5 above. Example 13 This example is directed to solution item 9 and all sub-items outlined in Section 5 above.

[0069] More details of embodiments of the present disclosure related to the neural network post-processing filter (NNPF) will be described below. The embodiments of the present disclosure should be considered as examples to explain the general concept and should not be interpreted in a narrow manner. In addition, these embodiments can be applied individually or in combination in any way.

[0070] As used herein, the term "video unit" may refer to a color component, a sub-picture, a picture, a slice, a codec tree unit (CTU), a CTU row, a CTU group, a codec unit (CU), a prediction unit (PU), a transform unit (TU), a codec tree block (CTB), a codec block (CB), a prediction block (PB), a transform block (TB), a sub-block of a video block, a sub-region within a video block, a video processing unit including multiple samples / pixels, etc. A video unit may be rectangular or non-rectangular. In addition, the terms "neural network post-processing filter" and "neural network post-filter" may be used interchangeably.

[0071] As used herein, chrominance components may include Cb components and / or Cr components. For example, the Cb component may represent a blue difference chrominance component, and the Cr component may represent a red difference chrominance component. In another example, the Cb component and the Cr component may be replaced by a U component and a V component. It should be understood that the Cb component and / or the Cr component may represent any other suitable color component. The scope of the present disclosure is not limited in this respect.

[0072] Figure 10 FIG. 1 is a flow chart of a method 1000 for video processing according to some embodiments of the present disclosure. Figure 10 As shown, at 1002, conversion between a video and a bitstream of the video is performed. In some embodiments, the conversion may include encoding the video into a bitstream. Alternatively or additionally, the conversion may include decoding the current video unit from the bitstream.

[0073] At least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with a video. A bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream. By way of example and not limitation, the first indication can be implemented as a syntax element in the bitstream.

[0074] In some embodiments, at least one video unit may include at least one picture associated with the video. For example, the at least one picture may be used as input to the NNPF. In some embodiments, the at least one picture may include at least one decoded picture of the video. Alternatively, the at least one picture may include at least one cropped decoded picture of the video. For example, the decoded picture and / or the cropped decoded picture may be output by a decoder that decodes the video from a bitstream. In some further embodiments, the at least one picture may include the output of another NNPF, which is used to filter one or more decoded pictures or cropped decoded pictures of the video. For example, the NNPF is spliced with another NNPF. It should be understood that the possible implementations of the at least one video unit associated with the video described herein are merely illustrative and should not be construed as limiting the present disclosure in any way.

[0075] In some embodiments, if the first indication indicates that quality information is not present in the bitstream, then at least one indication indicating the quality information may not be present in the bitstream. If the first indication indicates that quality information is present in the bitstream, then at least one indication indicating the quality information may be present in the bitstream. Alternatively, at least one indication indicating quality information may be present in the bitstream independently of the first indication. That is, quality information is always indicated in the bitstream regardless of the first indication.

[0076] In some embodiments, the quality information may include one or more metric types for measuring the quality of at least one video unit. For example, the one or more metric types may include peak signal-to-noise ratio (PSNR), structural similarity (SSIM), multi-scale structural similarity (MS-SSIM), video multi-method assessment fusion (VMAF), etc. Alternatively, one or more predetermined metric types may be used and not indicated in the bitstream.

[0077] Additionally or alternatively, the quality information may include one or more quality changes of at least one video unit corresponding to one or more metric types. Each of the one or more quality changes is caused by the application of at least one NNPF and is measured based on the corresponding metric type. When the quality change indicates a quality improvement, the quality change may also be considered as a gain obtained by applying the at least one NNPF.

[0078] In one example embodiment, one of the one or more quality changes may be determined based on a difference between a quality of at least one video unit after at least one NNPF is applied and a quality of at least one video unit without the at least one NNPF being applied. In another example embodiment, one of the one or more quality changes may be determined based on a difference between a quality of at least one video unit without the at least one NNPF being applied and a quality of at least one video unit after the at least one NNPF is applied.

[0079] In some additional or alternative embodiments, the quality information may include one or more quality values of at least one video unit after at least one NNPF is applied. The one or more quality values correspond to one or more metric types, and each of the one or more quality values is measured based on the corresponding metric type. It should be understood that the quality information may include any other suitable information, and the scope of the present disclosure is not limited in this respect.

[0080] In view of the above, an indication indicates whether quality information of at least one video unit associated with the application of at least one NNPF is present in the bitstream. Compared with traditional solutions, the proposed method can advantageously enable the application of NNPF based on quality information, thereby improving the encoding and decoding quality.

[0081] In some embodiments, at least one video unit may include an entire video sequence of a video. In this case, at least one indication indicates quality information for the entire video sequence. In some other embodiments, at least one video unit may include a single picture of a video. In this case, at least one indication indicates quality information for the single picture. Alternatively, at least one video unit may include multiple pictures of a video. In this case, at least one indication indicates quality information for multiple pictures. It should be understood that at least one video unit may also be a portion of a picture, and the scope of the present disclosure is not limited in this respect.

[0082] In some embodiments, the one or more metric types may include multiple metric types, and the one or more quality changes may also include multiple quality changes. Additionally, the bitstream may include a second indication indicating the number of the multiple metric types. Furthermore, the at least one indication indicating quality information may follow the second indication in the bitstream. In other words, the at least one indication is signaled after the second indication.

[0083] In some embodiments, one or more of the above indications (e.g., the first indication, the second indication, and / or the at least one indication) may be included in a video message unit in the bitstream. By way of example, the video message unit may be a supplemental enhancement information (SEI) message, such as a neural network post-processing filter activation (NNPFA) SEI message. It should be understood that the above indication(s) may be included in any other suitable video message unit, and the scope of the present disclosure is not limited in this respect.

[0084] In view of the above, the solutions according to some embodiments of the present disclosure can advantageously improve the encoding and decoding efficiency of quality information.

[0085] In some embodiments, the bitstream may further include at least one first syntax element indicating a type of at least one video unit. One of the candidates for the type may be a first region type, which may be a new region type different from existing region types in the VVC standard (such as pictures, slices, codec tree units, etc.). For example, the at least one first syntax element may be implemented as a syntax element nnpfa_region_type.

[0086] It should be understood that the names of the instructions and / or grammatical elements are used for illustration only and not for limitation, and the instructions and grammatical elements mentioned throughout this disclosure may be represented by any other suitable string different from the examples in this disclosure. The scope of this disclosure is not limited in this respect.

[0087] In some embodiments, if the type of at least one video unit is a first region type, the at least one video unit may include one or more regions. For example, a region in the one or more regions may be represented by information including the dimensions of the region, the position of the region, and / or the coordinates of the region. By way of example and not limitation, the dimensions of the region may include the width of the region and / or the height of the region. Additionally or alternatively, the dimensions of the region may include the horizontal samples of the region and / or the vertical samples of the region. The position of the region may include the coordinates of the starting point of the region and / or the coordinates of the end point of the region. In some embodiments, all regions in the one or more regions may have the same dimensions. In this case, the same dimensions may be indicated in the bitstream. Alternatively, one or more regions may have different dimensions. In this case, the dimensions for each region in the one or more regions may be indicated in the bitstream.

[0088] In some embodiments, one of the one or more regions may overlap with another region. Alternatively, one of the one or more regions may not overlap with another region.

[0089] In some embodiments, if at least one first syntax element is equal to a first value (such as 3, etc.), no NNPF may be applied to the current picture and / or a slice of the current picture and / or a CTU of the current picture, or the NNPF applied to the current picture is indicated. If at least one first syntax element is equal to a second value (such as 4, etc.), no NNPF may be applied to a sub-region of the current picture, or the NNPF applied to the current picture is indicated.

[0090] In some embodiments, the value of at least one first syntax element may be within a first predetermined range, and the value of at least one first syntax element greater than a third value may be retained and omitted from the bitstream. Additionally, NNPFA SEI messages having at least one first syntax element greater than the third value may be ignored. By way of example and not limitation, the first predetermined range may be 0 to 31, and the third value may be one of 2, 3, or 4. It should be understood that the specific values listed herein are intended to be exemplary and not to limit the scope of the present disclosure.

[0091] In some embodiments, the syntax element nnpfa_picture_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the picture level. For example, only one NNPF in the NNPFA SEI message may be indicated by the syntax element nnpfa_id. In some other embodiments, the syntax element nnpfa_picture_index[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the picture level. For example, one or more NNPFs in the NNPFA SEI message may be indicated by the syntax element nnpfa_id[i].

[0092] In some embodiments, the syntax element nnpfa_slice_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the slice level, and there may be only one NNPF in the NNPFA SEI message indicated by the syntax element nnpfa_id. In some other embodiments, the syntax element nnpfa_slice_index[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the slice level, and one or more NNPFs in the NNPFA SEI message may be indicated by the syntax element nnpfa_id[i].

[0093] In some embodiments, the syntax element nnpfa_ctu_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the codec tree unit (CTU) level, and there may be only one NNPF in the NNPFA SEI message indicated by the syntax element nnpfa_id. In some embodiments, the syntax element nnpfa_ctu_index[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the CTU level, and one or more NNPFs in the NNPFA SEI message may be indicated by the syntax element nnpfa_id[i].

[0094] In some embodiments, if the type of at least one video unit is a first region type, the NNPFA SEI message in the bitstream includes a syntax element indicating activation of at least one NNPF at a region level. By way of example and not limitation, the syntax element nnpfa_region_enabling_flag[i] in the NNPFA SEI message indicates the use of the NNPF at the region level. For example, only one NNPF in the NNPFA SEI message may be indicated by the syntax element nnpfa_id. Alternatively, the syntax element nnpfa_region_index[i] in the NNPFA SEI message in the bitstream indicates the use of the NNPF at the region level. For example, one or more NNPFs in the NNPFA SEI message may be indicated by the syntax element nnpfa_id[i].

[0095] In some embodiments, if at least one first syntax element is equal to a fourth value, the syntax element nnpfa_picture_index[i] and / or the syntax element nnpfa_picture_enabling_flag[i] may be indicated in the bitstream. If at least one first syntax element is equal to a fifth value, the syntax element nnpfa_slice_index[i] and / or the syntax element nnpfa_slice_enabling_flag[i] may be indicated in the bitstream. If at least one first syntax element is equal to a sixth value, the syntax element nnpfa_ctu_index[i] and / or the syntax element nnpfa_ctu_enabling_flag[i] may be indicated in the bitstream. If at least one first syntax element is equal to a seventh value, the syntax element nnpfa_region_index[i] may be indicated in the bitstream. By way of example and not limitation, the fourth value may be 0 or 3, or the fifth value may be 1 or 3, or the sixth value may be 2 or 3, or the seventh value may be 4.

[0096] In some embodiments, the syntax element indicating whether NNPF is used in the current region may be required to be less than an eighth value, which may be determined based on the number of NNPFs. For example, the syntax element should be less than nnpfa_num_minus1+2, where the syntax element nnpfa_num_minus1 is equal to the number of NNPFs minus one.

[0097] In some embodiments, the syntax element indicating whether NNPF is used in a sub-region of the current region is equal to the eighth value indicating that NNPF is used in the sub-region. By way of example and not limitation, the syntax element may be nnpfa_slice_index[i] or nnpfa_ctu_index[i].

[0098] In some embodiments, the bitstream may include a syntax element nnpfa_picture_enabling_flag indicating whether NNPF is used at the picture level. For example, the syntax element nnpfa_picture_enabling_flag being equal to a first value indicates that NNPF may be used for a sub-region of the current picture. By way of example, the sub-region may be at a slice level, a sub-block level, a CTU level, a codec tree block (CTB) level, or a small block level. In some embodiments, i may be an integer, and the use of the i-th sub-region of the current picture may be indicated by the syntax element nnpfa_slice_enabling_flag[i], the syntax element nnpfa_ctu_enabling_flag[i], or the syntax element nnpfa_region_enabling_flag[i].

[0099] The syntax element nnpfa_picture_enabling_flag equal to the second value indicates that NNPF may be used for the current picture. The syntax element nnpfa_picture_enabling_flag equal to the third value indicates that NNPF may not be used for the current picture. By way of example and not limitation, the first value may be 2, the second value may be 1, or the third value may be 0.

[0100] In some embodiments, the bitstream may include a syntax element nnpfa_picture_index indicating whether NNPF is used at the picture level. For example, a syntax element nnpfa_picture_index equal to a first value (such as 0, etc.) indicates that NNPF may not be used for the current picture. A syntax element nnpfa_picture_index greater than the first value indicates that an NNPF with nnpfa_id equal to nnpfa_id[nnpfa_picture_index-1] may be used for the current picture. Alternatively, a syntax element nnpfa_picture_index greater than the first value and less than a second value indicates that an NNPF with nnpfa_id equal to nnpfa_id[nnpfa_picture_index-1] may be used for the current picture. The second value may be determined based on the number of NNPFs, such as nnpfa_num_minus1+2, etc. A syntax element nnpfa_picture_index equal to the second value indicates that NNPF may be allowed to be used for a sub-region of the current picture.

[0101] In some embodiments, the sub-region may be at slice level, sub-block level, CTU level, CTB level, tile level, etc. The use of the i-th sub-region of the current picture may be indicated by the syntax element nnpfa_slice_index[i], the syntax element nnpfa_ctu_index[i], or the syntax element nnpfa_region_index[i].

[0102] In some embodiments, the value of the syntax element nnpfa_picture_index may be within a range determined based on the number of NNPFs. In one example, the value of the syntax element nnpfa_picture_index may be within a range of 0 to nnpfa_num_minus1+1 (inclusive). In another example, the value of the syntax element nnpfa_picture_index may be within a range of 0 to nnpfa_num_minus1+2 (inclusive).

[0103] In some embodiments, the syntax element nnpfa_slice_enabling_flag[i] in the bitstream, which is equal to a first value, indicates that NNPF can be used for a sub-region of the i-th slice of the current picture, and i can be an integer. For example, the sub-region can be at the sub-block level, the CTU level, the CTB level, or the small block level. The bitstream may include a syntax element nnpfa_ctu_enabling_flag[j] indicating the use of the j-th sub-region of the i-th slice of the current picture, and j can be an integer.

[0104] In some embodiments, the bitstream may include a syntax element nnpfa_slice_index[i] indicating whether NNPF is used at the slice level. For example, a syntax element nnpfa_slice_index[i] equal to a first value (such as 0, etc.) indicates that NNPF may not be used for the i-th slice of the current picture. A syntax element nnpfa_slice_index[i] greater than the first value indicates that an NNPF with nnpfa_id equal to nnpfa_slice_index[i]-1] may be used for the i-th slice of the current picture. Alternatively, a syntax element nnpfa_slice_index[i] greater than the first value and less than a second value indicates that an NNPF with nnpfa_id equal to nnpfa_slice_index[i]-1] may be used for the i-th slice of the current picture. The second value may be determined based on the number of NNPFs, such as nnpfa_num_minus1+2, etc. The syntax element nnpfa_slice_index[i] equal to the second value indicates that NNPF may be allowed to be used for a sub-region of the i-th slice of the current picture.

[0105] In some embodiments, the sub-region may be at the sub-block level, the CTU level, the CTB level, or the small block level. The use of the j-th sub-region of the i-th slice of the current picture may be indicated by the syntax element nnpfa_ctu_index[j], and j may be an integer. In some embodiments, the value of the syntax element nnpfa_slice_index[i] may be within a range determined based on the number of NNPFs, such as a range of 0 to nnpfa_num_minus1+2 (inclusive).

[0106] In some embodiments, the NNPFA SEI message in the bitstream may include at least one syntax element indicating whether NNPF is used at a first region level corresponding to a first region type. In one example, the syntax element at the first region level may depend on a syntax element at a level higher than the first region level, such as a picture level, a slice level, or a sequence level. In another example, the syntax element in the bitstream indicates whether NNPF is applied at the first region level.

[0107] In another example, a syntax element in the bitstream indicates an index of the NNPF applied to the first region level. In yet another example, a syntax element in the bitstream indicates whether the NNPF is applied at the first region level or at a level lower than the first region level. In yet another example, a syntax element of the first region level corresponding to the first region type may not be indicated in the bitstream.

[0108] In some embodiments, the bitstream may include a syntax element nnpfa_region_enabling_flag[i] indicating the use of NNPF at a first region level. For example, a syntax element nnpfa_region_enabling_flag[i] equal to a first value (such as 1, etc.) indicates that NNPF may be used for the i-th region of the current picture, where i may be an integer. A syntax element nnpfa_region_enabling_flag[i] equal to a second value (such as 0, etc.) indicates that NNPF may not be used for the i-th region of the current picture.

[0109] In some embodiments, the bitstream may include a syntax element nnpfa_region_index[i] indicating the use of NNPF at a first region level. For example, a syntax element nnpfa_region_index[i] equal to a first value (such as 0) indicates that NNPF may not be used for the i-th region of the current picture, where i may be an integer. A syntax element nnpfa_region_index[i] greater than the first value indicates that an NNPF with nnpfa_id equal to nnpfa_id[nnpfa_region_index[i]-1] may be used for the i-th region of the current picture. In some embodiments, the value of the syntax element nnpfa_region_index[i] may be within a range determined based on the number of NNPFs, such as a range of 0 to nnpfa_num_minus1+1 (including the boundary values).

[0110] In some embodiments, the NNPFA SEI message may also include one or more syntax elements indicating dimensional information and / or position information of at least one region of the first region level. In one example, the one or more syntax elements may include a second syntax element indicating the horizontal sample or width of the i-th region of the at least one region, where i may be an integer. By way of example and not limitation, the second syntax element may be represented as nnpfa_region_width[i]. Additionally or alternatively, the one or more syntax elements may include a third syntax element indicating the vertical sample or height of the i-th region of the at least one region, where i may be an integer. By way of example and not limitation, the third syntax element may be represented as nnpfa_region_height[i].

[0111] In another example, the one or more syntax elements may include a fourth syntax element indicating the horizontal coordinates of a starting point of an i-th region of the at least one region, and i may be an integer. By way of example and not limitation, the fourth syntax element may be represented as nnpfa_region_x0[i]. Additionally or alternatively, the one or more syntax elements may include a fifth syntax element indicating the vertical coordinates of a starting point of an i-th region of the at least one region, and i may be an integer. By way of example and not limitation, the fifth syntax element may be represented as nnpfa_region_y0[i].

[0112] In some embodiments, the one or more syntax elements may include a sixth syntax element indicating the horizontal coordinates of an end point of an i-th region of the at least one region, and i may be an integer. By way of example and not limitation, the sixth syntax element may be represented as nnpfa_region_x1[i]. Additionally or alternatively, the one or more syntax elements may include a seventh syntax element indicating the vertical coordinates of an end point of an i-th region of the at least one region, and i may be an integer. By way of example and not limitation, the seventh syntax element may be represented as nnpfa_region_y1[i].

[0113] In some embodiments, the one or more syntax elements may include an eighth syntax element that indicates whether all regions in the at least one region have the same dimensions. By way of example and not limitation, the eighth syntax element may be denoted as nnpfa_region_dim_flag. For example, an eighth syntax element equal to a first value (such as 0) indicates that all regions in the at least one region have the same dimensions. An eighth syntax element equal to a second value (such as 1) indicates that the at least one region has different dimensions.

[0114] In some embodiments, the one or more syntax elements may include a ninth syntax element indicating whether all regions in the at least one region can be overlapped. By way of example and not limitation, the ninth syntax element may be represented as nnpfa_region_overlap_flag. For example, a ninth syntax element equal to a first value (such as 0) indicates that all regions in the at least one region can be overlapped. A ninth syntax element equal to a second value (such as 1) indicates that at least one region can be overlapped.

[0115] 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, and the bitstream of the video is generated by a method performed by an apparatus for video processing. In the method, conversion between a video and a bitstream is performed. At least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of at least one video unit associated with the application of at least one NNPF is present in the bitstream.

[0116] According to some further embodiments of the present disclosure, a method for storing a bitstream of a video is provided. In the method, conversion between a video and a bitstream is performed. At least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream. In addition, the bitstream is stored in a non-transitory computer-readable recording medium.

[0117] The embodiments of the present disclosure may be described according to the following items, the features of which may be combined in any reasonable way.

[0118] Item 1. A method for video processing, comprising: performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

[0119] Item 2. A method according to Item 1, wherein the quality information includes at least one of the following: one or more metric types for measuring the quality of at least one video unit, one or more quality changes of at least one video unit corresponding to the one or more metric types, each of the one or more quality changes being caused by the application of at least one NNPF and being measured based on the corresponding metric type, or one or more quality values of at least one video unit after the at least one NNPF is applied, one or more quality values corresponding to the one or more metric types, and each of the one or more quality values being measured based on the corresponding metric type.

[0120] Clause 3. The method of any of Clauses 1 to 2, wherein the first indication indicates that quality information is present in the bitstream, and at least one indication is present in the bitstream, the at least one indication indicating quality information.

[0121] Item 4. The method of any one of Items 1 to 3, wherein at least one video unit comprises one of: an entire video sequence of a video, a single picture of a video, or a plurality of pictures of a video.

[0122] Item 5. A method according to any one of Items 2 to 4, wherein the one or more metric types include at least one of the following: peak signal-to-noise ratio (PSNR), structural similarity (SSIM), multi-scale structural similarity (MS-SSIM), or video multi-method assessment fusion (VMAF).

[0123] Item 6. A method according to any one of items 2 to 4, wherein a quality change among the one or more quality changes is determined based on one of the following: a difference between the quality of at least one video unit after at least one NNPF is applied and the quality of at least one video unit when at least one NNPF is not applied, or a difference between the quality of at least one video unit when at least one NNPF is not applied and the quality of at least one video unit after at least one NNPF is applied.

[0124] Clause 7. The method of any one of Clauses 2 to 6, wherein the one or more metric types comprises a plurality of metric types, and the one or more mass changes comprises a plurality of mass changes.

[0125] Clause 8. The method of clause 7, wherein the bitstream comprises a second indication indicating a number of the plurality of metric types.

[0126] Clause 9. The method of clause 8, wherein the at least one indication indicative of the quality information follows the second indication in the bitstream.

[0127] Clause 10. The method of any of Clauses 1 to 2, wherein the first indication indicates that quality information is not present in the bitstream, and at least one indication is not present in the bitstream, the at least one indication indicating the quality information.

[0128] Clause 11. The method of any one of clauses 1 to 9, wherein at least one indication indicative of quality information is present in the bitstream independently of the first indication.

[0129] Clause 12. A method according to any of clauses 2 to 11, wherein the at least one indication is included in a video message unit in the bitstream.

[0130] Clause 13. The method of clause 12, wherein the video message unit is a Supplemental Enhancement Information (SEI) message.

[0131] Item 14. The method of Item 13, wherein the SEI message is a Neural Network Post-Processing Filter Activation (NNPFA) SEI message.

[0132] Item 15. A method according to any one of items 1 to 14, wherein the bitstream further comprises at least one first syntax element indicating a type of at least one video unit, and one of the candidates for the type is a first region type different from a picture, a slice, and a codec tree unit.

[0133] Item 16. The method of Item 15, wherein if the type of the at least one video unit is the first region type, the at least one video unit includes one or more regions.

[0134] Item 17. The method of Item 16, wherein a region of the one or more regions is represented by information comprising at least one of: a dimension of the region, a position of the region, or coordinates of the region.

[0135] Item 18. A method according to Item 17, wherein the dimension of the region includes at least one of the width of the region or the height of the region, or the position of the region includes at least one of the coordinates of the starting point of the region or the coordinates of the end point of the region.

[0136] Item 19. The method according to any one of Items 16 to 18, wherein one of the one or more regions overlaps with another region, or one of the one or more regions does not overlap with another region.

[0137] Item 20. The method of any one of Items 16 to 20, wherein all of the one or more regions have the same dimensions.

[0138] Clause 21. The method of clause 20, wherein the same dimension is indicated in the bitstream.

[0139] Item 22. The method of any one of Items 16 to 20, wherein one or more regions have different dimensions.

[0140] Clause 23. The method of clause 22, wherein a dimension for each of the one or more regions is indicated in the bitstream.

[0141] Item 24. A method according to any one of items 15 to 23, wherein if at least one first syntax element is equal to a first value, no NNPF is applied to the current picture and / or a slice of the current picture and / or a CTU of the current picture, or the NNPF applied to the current picture is indicated, or if at least one first syntax element is equal to a second value, no NNPF is applied to a sub-region of the current picture, or the NNPF applied to the current picture is indicated.

[0142] Item 25. The method of Item 24, wherein the first value is 3, or the second value is 4.

[0143] Item 26. The method of any one of Items 15 to 25, wherein a value of the at least one first syntax element is within a first predetermined range, and a value of the at least one first syntax element greater than a third value is retained and omitted from the bitstream.

[0144] Clause 27. The method of clause 26, wherein NNPFA SEI messages having at least one first syntax element greater than a third value are ignored.

[0145] Clause 28. The method of any one of Clauses 26 to 27, wherein the first predetermined range is from 0 to 31, or the third value is one of 2, 3, or 4.

[0146] Clause 29. The method of any of Clauses 1 to 28, wherein the syntax element nnpfa_picture_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates usage of NNPF at picture level.

[0147] Clause 30. The method of clause 29, wherein only one NNPF in the NNPFA SEI message is indicated by the syntax element nnpfa_id.

[0148] Clause 31. The method of any of Clauses 1 to 28, wherein the syntax element nnpfa_picture_index[i] in the NNPFA SEI message in the bitstream indicates usage of NNPF at picture level.

[0149] Clause 32. The method of clause 31, wherein one or more NNPFs in the NNPFA SEI message are indicated by the syntax element nnpfa_id[i].

[0150] Clause 33. The method of any of Clauses 1 to 32, wherein the syntax element nnpfa_slice_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates usage of NNPF at the slice level, and there is only one NNPF in the NNPFA SEI message indicated by the syntax element nnpfa_id.

[0151] Clause 34. The method of any of clauses 1 to 23, wherein a syntax element nnpfa_slice_index[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at a slice level, and one or more NNPFs in the NNPFA SEI message are indicated by a syntax element nnpfa_id[i].

[0152] Item 35. The method of any one of Items 1 to 34, wherein the syntax element nnpfa_ctu_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates usage of NNPF at codec tree unit (CTU) level, and only one NNPF in the NNPFA SEI message is indicated by the syntax element nnpfa_id.

[0153] Clause 36. The method of any one of clauses 1 to 35, wherein a syntax element nnpfa_ctu_index[i] in an NNPFA SEI message in the bitstream indicates usage of an NNPF at a CTU level, and one or more NNPFs in the NNPFA SEI message are indicated by a syntax element nnpfa_id[i].

[0154] Item 37. The method of any one of Items 15 to 36, wherein if the type of at least one video unit is the first region type, the NNPFA SEI message in the bitstream includes a syntax element indicating activation of at least one NNPF at a region level.

[0155] Clause 38. The method of clause 37, wherein the syntax element nnpfa_region_enabling_flag[i] in the NNPFA SEI message indicates usage of NNPF at a region level.

[0156] Clause 39. The method of clause 38, wherein only one NNPF in the NNPFA SEI message is indicated by the syntax element nnpfa_id.

[0157] Clause 40. The method of clause 37, wherein a syntax element nnpfa_region_index[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at a region level.

[0158] Clause 41. The method of clause 40, wherein one or more NNPFs in the NNPFA SEI message are indicated by a syntax element nnpfa_id[i].

[0159] Item 42. A method according to any of items 15 to 41, wherein if at least one first syntax element is equal to a fourth value, at least one syntax element of the syntax element nnpfa_picture_index[i] or the syntax element nnpfa_picture_enabling_flag[i] is indicated in the bitstream, or if at least one first syntax element is equal to a fifth value, at least one syntax element of the syntax element nnpfa_slice_index[i] or the syntax element nnpfa_slice_enabling_flag[i] is indicated in the bitstream, or if at least one first syntax element is equal to a sixth value, at least one syntax element of the syntax element nnpfa_ctu_index[i] or the syntax element nnpfa_ctu_enabling_flag[i] is indicated in the bitstream, or if at least one first syntax element is equal to a seventh value, the syntax element nnpfa_region_index[i] is indicated in the bitstream.

[0160] Item 43. The method of Item 42, wherein the fourth value is 0 or 3, or the fifth value is 1 or 3, or the sixth value is 2 or 3, or the seventh value is 4.

[0161] Item 44. The method of any one of items 1 to 43, wherein the syntax element indicating whether an NNPF is used in the current region is required to be less than an eighth value, the eighth value being determined based on the number of NNPFs.

[0162] Item 45. The method of Item 44, wherein the syntax element indicating whether NNPF is used in a sub-region of the current region is equal to an eighth value indicating that NNPF is used in the sub-region.

[0163] Item 46. The method of Item 45, wherein the syntax element is nnpfa_slice_index[i] or nnpfa_ctu_index[i].

[0164] Clause 47. The method of any one of clauses 1 to 46, wherein the bitstream comprises a syntax element nnpfa_picture_enabling_flag indicating whether NNPF is used at the picture level.

[0165] Item 48. The method of item 47, wherein the syntax element nnpfa_picture_enabling_flag equal to the first value indicates that NNPF is used for the sub-region of the current picture, or the syntax element nnpfa_picture_enabling_flag equal to the second value indicates that NNPF is used for the current picture, or the syntax element nnpfa_picture_enabling_flag equal to the third value indicates that NNPF is not used for the current picture.

[0166] Item 49. The method of item 48, wherein the sub-region is at a slice level, a sub-block level, a CTU level, a codec tree block (CTB) level, or a tile level.

[0167] Item 50. The method of any one of items 48 to 49, wherein i is an integer and usage of the i-th sub-region of the current picture is indicated by one of the following: the syntax element nnpfa_slice_enabling_flag[i], the syntax element nnpfa_ctu_enabling_flag[i], or the syntax element nnpfa_region_enabling_flag[i].

[0168] Item 51. The method of any one of Items 48 to 50, wherein the first value is 2, the second value is 1, or the third value is 0.

[0169] Clause 52. The method of any one of clauses 1 to 46, wherein the bitstream comprises a syntax element nnpfa_picture_index indicating whether NNPF is used at picture level.

[0170] Item 53. A method according to item 52, wherein the syntax element nnpfa_picture_index equal to a first value indicates that NNPF is not used for the current picture, or the syntax element nnpfa_picture_index greater than the first value indicates that an NNPF with nnpfa_id equal to nnpfa_id[nnpfa_picture_index-1] is used for the current picture, or the syntax element nnpfa_picture_index greater than the first value and less than a second value indicates that an NNPF with nnpfa_id[nnpfa_picture_index-1] is used for the current picture, the second value is determined based on the number of NNPFs, or the syntax element nnpfa_picture_index equal to the second value indicates that NNPF is allowed to be used for a sub-region of the current picture.

[0171] Item 54. The method of Item 53, wherein the first value is 0.

[0172] Item 55. The method of any one of items 53 to 54, wherein the sub-region is at a slice level, a sub-block level, a CTU level, a CTB level, or a tile level.

[0173] Item 56. The method of any one of Items 53 to 55, wherein the use of the i-th sub-region of the current picture is indicated by one of the following: the syntax element nnpfa_slice_index[i], the syntax element nnpfa_ctu_index[i], or the syntax element nnpfa_region_index[i].

[0174] Clause 57. The method of any of Clauses 52 to 56, wherein the value of the syntax element nnpfa_picture_index is within a range determined based on the number of NNPFs.

[0175] Item 58. The method of any one of Items 1 to 46, wherein the syntax element nnpfa_slice_enabling_flag[i] in the bitstream equal to the first value indicates that NNPF is used for the sub-region of the i-th slice of the current picture, and i is an integer.

[0176] Item 59. The method of item 58, wherein the sub-region is at a sub-block level, a CTU level, a CTB level, or a small block level.

[0177] Item 60. The method of any one of Items 58 to 59, wherein the bitstream comprises a syntax element nnpfa_ctu_enabling_flag[j] indicating usage of the j-th sub-region of the i-th slice of the current picture, and j is an integer.

[0178] Clause 61. The method of any of Clauses 1 to 46, wherein the bitstream comprises a syntax element nnpfa_slice_index[i] indicating whether NNPF is used at a slice level.

[0179] Item 62. The method according to item 61, wherein the syntax element nnpfa_slice_index[i] being equal to a first value indicates that NNPF is not used for the i-th slice of the current picture, or the syntax element nnpfa_slice_index[i] being greater than the first value indicates that an NNPF having nnpfa_id equal to nnpfa_slice_index[i]-1] is used for the i-th slice of the current picture, or the syntax element nnpfa_slice_index[i] being greater than the first value and less than a second value indicates that an NNPF having nnpfa_id equal to nnpfa_slice_index[i]-1] is used for the i-th slice of the current picture, the second value being determined based on the number of NNPFs, or the syntax element nnpfa_slice_index[i] being equal to the second value indicates that NNPF is allowed to be used for a sub-region of the i-th slice of the current picture.

[0180] Item 63. The method of Item 62, wherein the first value is 0.

[0181] Item 64. A method according to any one of items 62 to 63, wherein the sub-region is at a sub-block level, a CTU level, a CTB level or a small block level.

[0182] Item 65. The method of any one of Items 62 to 64, wherein usage of the j-th sub-region of the i-th slice of the current picture is indicated by the syntax element nnpfa_ctu_index[j], and j is an integer.

[0183] Item 66. The method of any one of Items 61 to 65, wherein the value of the syntax element nnpfa_slice_index[i] is within a range determined based on the number of NNPFs.

[0184] Item 67. The method of any of Items 15 to 66, wherein the NNPFA SEI message in the bitstream includes at least one syntax element indicating whether NNPF is used at a first region level corresponding to the first region type.

[0185] Item 68. The method of Item 67, wherein the syntax elements at the first region level depend on syntax elements at a level higher than the first region level.

[0186] Item 69. A method according to any one of items 67 to 68, wherein a syntax element in the bitstream indicates whether NNPF is applied at the first region level.

[0187] Item 70. The method of any one of items 67 to 69, wherein a syntax element in the bitstream indicates an index of the NNPF applied at the first region level.

[0188] Item 71. The method of any one of items 67 to 70, wherein a syntax element in the bitstream indicates whether the NNPF is applied at the first region level or at a level lower than the first region level.

[0189] Item 72. A method according to any of items 15 to 66, wherein syntax elements of the first region level corresponding to the first region type are not indicated in the bitstream.

[0190] Item 73. The method of any one of Items 67 to 71, wherein the bitstream comprises a syntax element nnpfa_region_enabling_flag[i] indicating usage of NNPF at the first region level.

[0191] Item 74. The method of item 73, wherein the syntax element nnpfa_region_enabling_flag[i] equal to a first value indicates that NNPF is used for the i-th region of the current picture, i being an integer, or the syntax element nnpfa_region_enabling_flag[i] equal to a second value indicates that NNPF is not used for the i-th region of the current picture, i being an integer.

[0192] Item 75. The method of Item 74, wherein the first value is 1 and the second value is 0.

[0193] Item 76. The method of any one of Items 67 to 71, wherein the bitstream comprises a syntax element nnpfa_region_index[i] indicating usage of the NNPF at the first region level.

[0194] Item 77. The method according to item 76, wherein the syntax element nnpfa_region_index[i] equal to the first value indicates that an NNPF is not used for the i-th region of the current picture, i is an integer, or the syntax element nnpfa_region_index[i] greater than the first value indicates that an NNPF with nnpfa_id equal to nnpfa_id[nnpfa_region_index[i]-1] is used for the i-th region of the current picture.

[0195] Item 78. The method of Item 77, wherein the first value is 0.

[0196] Item 79. The method of any one of Items 76 to 78, wherein the value of the syntax element nnpfa_region_index[i] is within a range determined based on the number of NNPFs.

[0197] Clause 80. The method of any one of clauses 67 to 79, wherein the NNPFA SEI message further comprises one or more syntax elements indicating at least one of dimensional information or position information of at least one region at the first region level.

[0198] Item 81. The method of Item 80, wherein the one or more syntax elements include a second syntax element indicating a horizontal sample or width of an i-th region of the at least one region, and i is an integer.

[0199] Item 82. The method of Item 81, wherein the second syntax element is represented as nnpfa_region_width[i].

[0200] Item 83. A method according to any one of items 80 to 82, wherein the one or more syntax elements include a third syntax element indicating a vertical sample or height of an i-th region of the at least one region, and i is an integer.

[0201] Item 84. The method of Item 83, wherein the third syntax element is represented as nnpfa_region_height[i].

[0202] Item 85. A method according to any one of items 80 to 84, wherein the one or more syntax elements include a fourth syntax element, the fourth syntax element indicating the horizontal coordinates of a starting point of an i-th region of the at least one region, and i is an integer.

[0203] Item 86. The method of Item 85, wherein the fourth syntax element is denoted as nnpfa_region_x0[i].

[0204] Item 87. A method according to any one of items 80 to 86, wherein the one or more syntax elements include a fifth syntax element, the fifth syntax element indicating the vertical coordinate of the starting point of an i-th region of the at least one region, and i is an integer.

[0205] Item 88. The method of Item 87, wherein the fifth syntax element is represented as nnpfa_region_y0[i].

[0206] Item 89. A method according to any one of items 80 to 88, wherein the one or more syntax elements include a sixth syntax element, the sixth syntax element indicating the horizontal coordinates of an end point of an i-th region of the at least one region, and i is an integer.

[0207] Item 90. The method of Item 89, wherein the sixth syntax element is denoted as nnpfa_region_x1[i].

[0208] Item 91. A method according to any one of items 80 to 90, wherein the one or more syntax elements include a seventh syntax element, the seventh syntax element indicating the vertical coordinate of an end point of an i-th region of the at least one region, and i is an integer.

[0209] Item 92. The method of Item 91, wherein the seventh syntax element is denoted as nnpfa_region_y1[i].

[0210] Item 93. A method according to any one of items 80 to 92, wherein the one or more syntax elements include an eighth syntax element, the eighth syntax element indicating whether all regions of the at least one region have the same dimension.

[0211] Item 94. The method of Item 93, wherein the eighth syntax element is denoted as nnpfa_region_dim_flag.

[0212] Item 95. A method according to any one of items 93 to 94, wherein the eighth syntax element being equal to the first value indicates that all regions of the at least one region have the same dimension, or the eighth syntax element being equal to the second value indicates that the at least one region has a different dimension.

[0213] Item 96. The method of Item 95, wherein the first value is 0, or the second value is 1.

[0214] Item 97. A method according to any one of items 80 to 96, wherein the one or more syntax elements include a ninth syntax element indicating whether all regions of the at least one region overlap.

[0215] Item 98. The method of Item 97, wherein the ninth syntax element is denoted as nnpfa_region_overlap_flag.

[0216] Item 99. A method according to any one of items 97 to 98, wherein the ninth syntax element being equal to the first value indicates that all of the at least one region overlap, or the ninth syntax element being equal to the second value indicates that at least one region overlaps.

[0217] Item 100. The method of Item 99, wherein the first value is 0, or the second value is 1.

[0218] Item 101. The method of any one of Items 1 to 100, wherein converting comprises encoding the video into a bitstream.

[0219] Item 102. The method of any one of Items 1 to 100, wherein converting comprises decoding the video from a bitstream.

[0220] Item 103. An apparatus for video processing, comprising a processor and non-transitory memory having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to perform the method according to any one of Items 1 to 102.

[0221] Item 104. A non-transitory computer-readable storage medium storing instructions that cause a processor to perform the method according to any one of Items 1 to 102.

[0222] Item 105. 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 an apparatus for video processing, wherein the method comprises: performing a conversion between the video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

[0223] Item 106. A method for storing a bitstream of a video, comprising: performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream; and storing the bitstream in a non-transitory computer-readable recording medium. Example device

[0224] Figure 11 A block diagram of a computing device 1100 in which various embodiments of the present disclosure may be implemented is shown. The computing device 1100 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).

[0225] It should be understood that Figure 11 The computing device 1100 shown in FIG. 1 is for illustrative purposes only and is not intended to in any way imply any limitation on the functionality and scope of the disclosed embodiments.

[0226] like Figure 11As shown, computing device 1100 comprises a general computing device 1100. Computing device 1100 may include at least one or more processors or processing units 1110, memory 1120, storage unit 1130, one or more communication units 1140, one or more input devices 1150, and one or more output devices 1160.

[0227] In some embodiments, the computing device 1100 can be implemented as any user terminal or server terminal with computing capabilities. 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 e-book device, a gaming device, or any combination thereof, including accessories and peripherals of these devices, or any combination thereof. It is conceivable that the computing device 1100 can support any type of interface to the user (such as a "wearable" circuit device, etc.).

[0228] Processing unit 1110 may be a physical processor or a virtual processor and may implement various processes based on a program stored in memory 1120. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of computing device 1100. Processing unit 1110 may also be referred to as a central processing unit (CPU), a microprocessor, a controller, or a microcontroller.

[0229] The computing device 1100 typically includes various computer storage media. Such media can be any media accessible by the computing device 1100, including but not limited to volatile media and non-volatile media, or removable media and non-removable media. The memory 1120 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM) or flash memory), or any combination thereof. The storage unit 1130 can be any removable or non-removable medium and can include machine-readable media, such as 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 1100.

[0230] The computing device 1100 may also include additional removable / non-removable storage media, volatile / non-volatile storage media. Figure 11 Although not shown, a magnetic disk drive for reading from and / or writing to a removable nonvolatile magnetic disk, and an optical disk 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 a bus (not shown) via one or more data medium interfaces.

[0231] The communication unit 1140 communicates with another computing device via a communication medium. In addition, the functionality of the components in the computing device 1100 can be implemented by a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the computing device 1100 can operate in a networked environment using logical connections to one or more other servers, networked personal computers (PCs), or other general-purpose network nodes.

[0232] Input device 1150 may be one or more of various input devices, such as a mouse, keyboard, trackball, voice input device, and the like. Output device 1160 may be one or more of various output devices, such as a display, speaker, printer, and the like. With the aid of communication unit 1140, computing device 1100 may also communicate with one or more external devices (not shown), such as storage devices and display devices, one or more devices that enable a user to interact with computing device 1100, or, if desired, any device that enables computing device 1100 to communicate with one or more other computing devices (e.g., a network card, a modem, and the like). Such communication may be performed via an input / output (I / O) interface (not shown).

[0233] In some embodiments, some or all components of the computing device 1100 may also be arranged in a cloud computing architecture rather than being integrated into a single device. In a cloud computing architecture, components can be provided remotely and work together to implement the functionality described in this disclosure. In some embodiments, cloud computing provides computing, software, data access, and storage services without requiring the end user to know the physical location or configuration of the systems or hardware providing these services. In various embodiments, cloud computing provides services via a wide area network (such as the Internet) using appropriate protocols. For example, a cloud computing provider provides an application via a wide area network that 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 servers in a remote location. Computing resources in a cloud computing environment may be consolidated or distributed across remote data centers. Cloud computing infrastructure can provide services through shared data centers, although to users, they appear as a single access point. Therefore, cloud computing architecture can be used to provide the components and functionality described herein from a service provider in a remote location. Alternatively, the components and functionality described herein may be provided by a conventional server or installed directly or otherwise on a client device.

[0234] In embodiments of the present disclosure, the computing device 1100 may be used to implement video encoding / decoding. The memory 1120 may include one or more video encoding / decoding modules 1125 having one or more program instructions. These modules are accessible and executable by the processing unit 1110 to perform the functions of the various embodiments described herein.

[0235] In an example embodiment performing video encoding, input device 1150 may receive video data as input to be encoded 1170. The video data may be processed, for example, by video codec module 1125 to generate an encoded bitstream. The encoded bitstream may be provided as output 1180 via output device 1160.

[0236] In an example embodiment performing video decoding, input device 1150 may receive an encoded bitstream as input 1170. The encoded bitstream may be processed, for example, by video codec module 1125 to generate decoded video data. The decoded video data may be provided as output 1180 via output device 1160.

[0237] Although the present disclosure has been specifically shown and described with reference to the preferred embodiments of the present disclosure, it will be understood by those skilled in the art that various changes in form and details may be made without departing from the spirit and scope of the present application as defined by the appended claims. Such variations 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: Performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

2. The method according to claim 1, wherein the quality information comprises at least one of the following: one or more metric types for measuring the quality of the at least one video unit, one or more quality changes of the at least one video unit corresponding to the one or more metric types, each quality change of the one or more quality changes being caused by the application of the at least one NNPF and being measured based on a corresponding metric type, or One or more quality values of the at least one video unit after the at least one NNPF is applied, the one or more quality values corresponding to the one or more metric types, and each of the one or more quality values being measured based on the corresponding metric type.

3. The method according to any one of claims 1 to 2, wherein the first indication indicates that the quality information is present in the bitstream, and at least one indication is present in the bitstream, the at least one indication indicating the quality information.

4. The method according to any one of claims 1 to 3, wherein the at least one video unit comprises one of the following: the entire video sequence of said video, A single image from the video, or A plurality of pictures of the video.

5. The method according to any one of claims 2 to 4, wherein the one or more metric types include at least one of the following: Peak signal-to-noise ratio (PSNR), Structural similarity (SSIM), Multi-scale structural similarity (MS-SSIM) or Video Multi-Method Assessment Fusion (VMAF).

6. The method according to any one of claims 2 to 4, wherein a mass change in the one or more mass changes is determined based on one of: a difference between a quality of the at least one video unit after the at least one NNPF is applied and a quality of the at least one video unit without the at least one NNPF being applied, or A difference between a quality of the at least one video unit without the at least one NNPF being applied and a quality of the at least one video unit after the at least one NNPF is applied.

7. The method of any one of claims 2 to 6, wherein the one or more metric types comprises a plurality of metric types, and the one or more quality changes comprises a plurality of quality changes.

8. The method of claim 7, wherein the bitstream comprises a second indication indicating a number of the plurality of metric types.

9. The method of claim 8, wherein at least one indication indicating the quality information follows the second indication in the bitstream.

10. The method according to any of claims 1 to 2, wherein the first indication indicates that the quality information is not present in the bitstream, and at least one indication is not present in the bitstream, the at least one indication indicating the quality information.

11. The method according to any one of claims 1 to 9, wherein at least one indication indicating the quality information is present in the bitstream independently of the first indication.

12. The method according to any one of claims 2 to 11, wherein the at least one indication is included in a video message unit in the bitstream.

13. The method of claim 12, wherein the video message unit is a Supplemental Enhancement Information (SEI) message.

14. The method of claim 13, wherein the SEI message is a Neural Network Post-Processing Filter Activation (NNPFA) SEI message.

15. The method according to any one of claims 1 to 14, wherein the bitstream further comprises at least one first syntax element indicating a type of the at least one video unit, and one of the candidates for the type is a first region type different from a picture, a slice, and a codec tree unit.

16. The method of claim 15, wherein if the type of the at least one video unit is the first region type, the at least one video unit includes one or more regions.

17. The method of claim 16, wherein one of the one or more areas is represented by information comprising at least one of: the dimensions of the region, The location of the area or The coordinates of the region.

18. The method of claim 17, wherein the dimension of the region comprises at least one of a width of the region or a height of the region, or The position of the area includes at least one of coordinates of a start point of the area or coordinates of an end point of the area.

19. The method according to any one of claims 16 to 18, wherein one of the one or more regions overlaps with another region, or One of the one or more regions does not overlap with another region.

20. The method of any one of claims 16 to 20, wherein all of the one or more regions have the same dimensions. The method of claim 20 , wherein the same dimension is indicated in the bitstream.

22. The method of any one of claims 16 to 20, wherein the one or more regions have different dimensions.

23. The method of claim 22, wherein a dimension for each of the one or more regions is indicated in the bitstream.

24. The method according to any one of claims 15 to 23, wherein if the at least one first syntax element is equal to a first value, no NNPF is applied to the current picture and / or a slice of the current picture and / or a CTU of the current picture, or the NNPF applied to the current picture is indicated, or If the at least one first syntax element is equal to the second value, no NNPF is applied to the sub-region of the current picture, or the NNPF applied to the current picture is indicated. The method of claim 24 , wherein the first value is 3, or the second value is 4.

26. The method according to any one of claims 15 to 25, wherein a value of the at least one first syntax element is within a first predetermined range, and values of the at least one first syntax element greater than a third value are retained and omitted from the bitstream.

27. The method of claim 26, wherein NNPFA SEI messages having the at least one first syntax element greater than the third value are ignored.

28. The method according to any one of claims 26 to 27, wherein the first predetermined range is from 0 to 31, or the third value is one of 2, 3 or 4.

29. The method according to any one of claims 1 to 28, wherein a syntax element nnpfa_picture_enabling_flag[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at picture level.

30. The method of claim 29, wherein only one NNPF in the NNPFA SEI message is indicated by a syntax element nnpfa_id.

31. The method according to any one of claims 1 to 28, wherein a syntax element nnpfa_picture_index[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at picture level.

32. The method of claim 31, wherein one or more NNPFs in the NNPFA SEI message are indicated by a syntax element nnpfa_id[i].

33. The method according to any one of claims 1 to 32, wherein a syntax element nnpfa_slice_enabling_flag[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at a slice level, and only one NNPF in the NNPFA SEI message is indicated by a syntax element nnpfa_id.

34. The method according to any one of claims 1 to 23, wherein the syntax element nnpfa_slice_index[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the slice level, and one or more NNPFs in the NNPFA SEI message are indicated by the syntax element nnpfa_id[i].

35. The method according to any one of claims 1 to 34, wherein the syntax element nnpfa_ctu_enabling_flag[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the codec tree unit (CTU) level, and only one NNPF in the NNPFA SEI message is indicated by the syntax element nnpfa_id.

36. The method according to any one of claims 1 to 35, wherein the syntax element nnpfa_ctu_index[i] in the NNPFA SEI message in the bitstream indicates the use of NNPF at the CTU level, and one or more NNPFs in the NNPFA SEI message are indicated by the syntax element nnpfa_id[i].

37. The method according to any one of claims 15 to 36, wherein if the type of the at least one video unit is the first region type, an NNPFA SEI message in the bitstream includes a syntax element indicating activation of the at least one NNPF at a region level.

38. The method of claim 37, wherein a syntax element nnpfa_region_enabling_flag[i] in the NNPFA SEI message indicates usage of NNPF at the region level.

39. The method of claim 38, wherein only one NNPF in the NNPFA SEI message is indicated by a syntax element nnpfa_id.

40. The method of claim 37, wherein a syntax element nnpfa_region_index[i] in an NNPFA SEI message in the bitstream indicates usage of NNPF at the region level.

41. The method of claim 40, wherein one or more NNPFs in the NNPFA SEI message are indicated by a syntax element nnpfa_id[i].

42. The method according to any one of claims 15 to 41, wherein if the at least one first syntax element is equal to a fourth value, at least one of the syntax element nnpfa_picture_index[i] or the syntax element nnpfa_picture_enabling_flag[i] is indicated in the bitstream, or If the at least one first syntax element is equal to the fifth value, at least one syntax element of the syntax element nnpfa_slice_index[i] or the syntax element nnpfa_slice_enabling_flag[i] is indicated in the bitstream, or If the at least one first syntax element is equal to the sixth value, at least one syntax element of the syntax element nnpfa_ctu_index[i] or the syntax element nnpfa_ctu_enabling_flag[i] is indicated in the bitstream, or If the at least one first syntax element is equal to a seventh value, the syntax element nnpfa_region_index[i] is indicated in the bitstream.

43. The method of claim 42, wherein the fourth value is 0 or 3, or the fifth value is 1 or 3, or the sixth value is 2 or 3, or the seventh value is 4.

44. The method according to any one of claims 1 to 43, wherein the syntax element indicating whether NNPF is used in the current region is required to be less than an eighth value, and the eighth value is determined based on the number of the NNPFs.

45. The method of claim 44, wherein the syntax element indicating whether NNPF is used in a sub-region of the current region is equal to the eighth value indicating that the NNPF is used in the sub-region.

46. The method of claim 45, wherein the syntax element is nnpfa_slice_index[i] or nnpfa_ctu_index[i].

47. The method according to any one of claims 1 to 46, wherein the bitstream comprises a syntax element nnpfa_picture_enabling_flag indicating whether NNPF is used at picture level.

48. The method of claim 47, wherein the syntax element nnpfa_picture_enabling_flag equal to a first value indicates that the NNPF is used for a sub-region of a current picture, or The syntax element nnpfa_picture_enabling_flag equal to a second value indicates that the NNPF is used for the current picture, or The syntax element nnpfa_picture_enabling_flag equal to the third value indicates that the NNPF is not used for the current picture.

49. The method of claim 48, wherein the sub-region is in a slice level, a sub-block level, a CTU level, a codec tree block (CTB) level, or a tile level.

50. The method according to any one of claims 48 to 49, wherein i is an integer and the use of the i-th sub-region of the current picture is indicated by one of the following: Syntax element nnpfa_slice_enabling_flag[i], Syntax element nnpfa_ctu_enabling_flag[i] or Syntax element nnpfa_region_enabling_flag[i].

51. The method of any one of claims 48 to 50, wherein the first value is 2, the second value is 1, or the third value is 0.

52. The method according to any one of claims 1 to 46, wherein the bitstream comprises a syntax element nnpfa_picture_index indicating whether NNPF is used at picture level.

53. The method of claim 52, wherein the syntax element nnpfa_picture_index being equal to a first value indicates that the NNPF is not used for a current picture, or The syntax element nnpfa_picture_index being greater than the first value indicates that the NNPF with nnpfc_id equal to nnpfa_id[nnpfa_picture_index-1] is used for the current picture, or The syntax element nnpfa_picture_index being greater than the first value and less than a second value determined based on the number of the NNPFs indicates that the NNPF having nnpfa_id equal to nnpfa_id[nnpfa_picture_index-1] is used for the current picture, or The syntax element nnpfa_picture_index being equal to the second value indicates that the NNPF is allowed to be used for a sub-region of the current picture. The method of claim 53 , wherein the first value is zero.

55. The method according to any one of claims 53 to 54, wherein the sub-region is in a slice level, a sub-block level, a CTU level, a CTB level or a tile level.

56. The method according to any one of claims 53 to 55, wherein the use of the i-th sub-region of the current picture is indicated by one of the following: Syntax element nnpfa_slice_index[i], Syntax element nnpfa_ctu_index[i] or Syntax element nnpfa_region_index[i].

57. The method according to any one of claims 52 to 56, wherein a value of the syntax element nnpfa_picture_index is within a range determined based on the number of the NNPFs.

58. The method according to any one of claims 1 to 46, wherein the syntax element nnpfa_slice_enabling_flag[i] in the bitstream equal to a first value indicates that NNPF is used for a sub-region of the i-th slice of the current picture, and i is an integer.

59. The method of claim 58, wherein the sub-region is in a sub-block level, a CTU level, a CTB level, or a tile level.

60. The method according to any one of claims 58 to 59, wherein the bitstream comprises a syntax element nnpfa_ctu_enabling_flag[j] indicating usage of the j-th sub-region of the i-th slice of the current picture, and j is an integer.

61. The method according to any one of claims 1 to 46, wherein the bitstream comprises a syntax element nnpfa_slice_index[i] indicating whether NNPF is used at a slice level.

62. The method of claim 61 , wherein the syntax element nnpfa_slice_index[i] being equal to a first value indicates that the NNPF is not used for the i-th slice of the current picture, or the syntax element nnpfa_slice_index[i] being greater than the first value indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_slice_index[i]-1] is used for the i-th slice of the current picture, or the syntax element nnpfa_slice_index[i] being greater than the first value and less than a second value indicating that the NNPF having nnpfa_id equal to nnpfa_id[nnpfa_slice_index[i]-1] is used for the i-th slice of the current picture, or The syntax element nnpfa_slice_index[i] equal to the second value indicates that the NNPF is allowed to be used for a sub-region of the i-th slice of the current picture. The method of claim 62 , wherein the first value is zero.

64. The method according to any one of claims 62 to 63, wherein the sub-region is in a sub-block level, a CTU level, a CTB level or a tile level.

65. The method according to any one of claims 62 to 64, wherein the use of the j-th sub-region of the i-th slice of the current picture is indicated by the syntax element nnpfa_ctu_index[j], and j is an integer.

66. The method according to any one of claims 61 to 65, wherein the value of the syntax element nnpfa_slice_index[i] is within a range determined based on the number of the NNPFs.

67. The method according to any one of claims 15 to 66, wherein the NNPFA SEI message in the bitstream comprises at least one syntax element indicating whether NNPF is used at a first region level corresponding to the first region type.

68. The method of claim 67, wherein syntax elements at the first region level are dependent on syntax elements at a level higher than the first region level.

69. The method of any one of claims 67 to 68, wherein a syntax element in the bitstream indicates whether NNPF is applied at the first region level.

70. The method according to any one of claims 67 to 69, wherein a syntax element in the bitstream indicates an index of the NNPF applied at the first region level.

71. The method of any one of claims 67 to 70, wherein a syntax element in the bitstream indicates whether NNPF is applied at the first region level or at a level lower than the first region level.

72. The method according to any one of claims 15 to 66, wherein syntax elements of a first region level corresponding to the first region type are not indicated in the bitstream.

73. The method according to any one of claims 67 to 71, wherein the bitstream comprises a syntax element nnpfa_region_enabling_flag[i] indicating usage of NNPF at the first region level.

74. The method of claim 73, wherein the syntax element nnpfa_region_enabling_flag[i] equal to a first value indicates that the NNPF is used for the i-th region of the current picture, i being an integer, or The syntax element nnpfa_region_enabling_flag[i] equal to the second value indicates that the NNPF is not used for the i-th region of the current picture, i being an integer.

75. The method of claim 74, wherein the first value is 1 and the second value is 0.

76. The method according to any one of claims 67 to 71, wherein the bitstream comprises a syntax element nnpfa_region_index[i] indicating usage of NNPF at the first region level.

77. The method of claim 76, wherein the syntax element nnpfa_region_index[i] equal to a first value indicates that the NNPF is not used for the i-th region of the current picture, i being an integer, or The syntax element nnpfa_region_index[i] being greater than the first value indicates that the NNPF with nnpfa_id equal to nnpfa_id[nnpfa_region_index[i]-1] is used for the i-th region of the current picture.

78. The method of claim 77, wherein the first value is 0.

79. The method according to any one of claims 76 to 78, wherein the value of the syntax element nnpfa_region_index[i] is within a range determined based on the number of the NNPFs.

80. The method according to any one of claims 67 to 79, wherein the NNPFA SEI message further comprises one or more syntax elements indicating at least one of dimension information or position information of at least one region at the first region level.

81. The method of claim 80, wherein the one or more syntax elements include a second syntax element indicating a horizontal sample or width of an i-th region of the at least one region, and i is an integer.

82. The method of claim 81, wherein the second syntax element is represented as nnpfa_region_width[i].

83. The method of any one of claims 80 to 82, wherein the one or more syntax elements include a third syntax element indicating a vertical sample or height of an i-th region of the at least one region, and i is an integer.

84. The method of claim 83, wherein the third syntax element is represented as nnpfa_region_height[i].

85. The method according to any one of claims 80 to 84, wherein the one or more syntax elements include a fourth syntax element, the fourth syntax element indicating the horizontal coordinate of the starting point of the i-th region of the at least one region, and i is an integer.

86. The method of claim 85, wherein the fourth syntax element is denoted as nnpfa_region_x0[i].

87. The method according to any one of claims 80 to 86, wherein the one or more syntax elements include a fifth syntax element, the fifth syntax element indicating the vertical coordinate of the starting point of the i-th region of the at least one region, and i is an integer.

88. The method of claim 87, wherein the fifth syntax element is represented as nnpfa_region_y0[i].

89. The method according to any one of claims 80 to 88, wherein the one or more syntax elements include a sixth syntax element, the sixth syntax element indicating the horizontal coordinate of an end point of an i-th region of the at least one region, and i is an integer.

90. The method of claim 89, wherein the sixth syntax element is denoted as nnpfa_region_x1[i].

91. The method according to any one of claims 80 to 90, wherein the one or more syntax elements include a seventh syntax element, the seventh syntax element indicating the vertical coordinate of the end point of the i-th region of the at least one region, and i is an integer.

92. The method of claim 91, wherein the seventh syntax element is denoted as nnpfa_region_y1[i].

93. The method according to any one of claims 80 to 92, wherein the one or more syntax elements include an eighth syntax element, the eighth syntax element indicating whether all regions of the at least one region have the same dimension.

94. The method of claim 93, wherein the eighth syntax element is represented as nnpfa_region_dim_flag.

95. The method according to any one of claims 93 to 94, wherein the eighth syntax element equal to the first value indicates that all regions of the at least one region have the same dimension, or The eighth syntax element being equal to the second value indicates that the at least one region has different dimensions.

96. The method of claim 95, wherein the first value is 0 or the second value is 1.

97. The method according to any one of claims 80 to 96, wherein the one or more syntax elements include a ninth syntax element indicating whether all regions of the at least one region overlap.

98. The method of claim 97, wherein the ninth syntax element is denoted as nnpfa_region_overlap_flag.

99. The method according to any one of claims 97 to 98, wherein the ninth syntax element equal to the first value indicates that all of the at least one region overlap, or The ninth syntax element being equal to the second value indicates that the at least one region overlaps.

100. The method of claim 99, wherein the first value is 0 or the second value is 1.

101. The method of any one of claims 1 to 100, wherein the converting comprises encoding the video into the bitstream.

102. The method of any one of claims 1 to 100, wherein the converting comprises decoding the video from the bitstream.

103. 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 the method according to any one of claims 1 to 102.

104. A non-transitory computer-readable storage medium storing instructions, wherein the instructions cause a processor to execute the method according to any one of claims 1 to 102.

105. A non-transitory computer-readable recording medium storing a bitstream of a video, wherein the bitstream of the video is generated by a method performed by an apparatus for video processing, wherein the method comprises: Performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information of the at least one video unit associated with the application of the at least one NNPF is present in the bitstream.

106. A method for storing a bitstream of a video, comprising: performing conversion between a video and a bitstream of the video, wherein at least one neural network post-processing filter (NNPF) is applied to at least one video unit associated with the video, and the bitstream includes a first indication indicating whether quality information for the at least one video unit associated with the application of the at least one NNPF is present in the bitstream; as well as The bitstream is stored in a non-transitory computer-readable recording medium.

Images