A method for encoding / decoding video, a method for transmitting a bitstream, and a recording medium for storing a bitstream.

Abstract

A video encoding / decoding method, a bitstream transmission method, and a computer-readable recording medium storing a bitstream are provided. The video decoding method according to the present disclosure includes the steps of: obtaining a supplemental enhancement information (SEI) message for a neural-network post-filter (NNPF) to be applied to a current picture; determining at least one neural network available as a post-processing filter based on the fact that the SEI message for the NNPF is applied to the current picture, based on at least one neural-network post-filter characteristics (NNPFC) SEI message included in the SEI message for the NNPF; and determining whether a target neural-network post-processing filter applicable to the current picture is activated based on at least one neural-network post-filter activation (NNPFA) SEI message included in the SEI message for the NNPF; wherein formatting information and destination information included in the NNPFC SEI message may be determined based on the fact that the NNPFC SEI message includes a base neural-network post-processing filter.

Description

[Technical Field]

[0001] This disclosure relates to a video encoding / decoding method, a bitstream transmission method, and a recording medium storing a bitstream, and in particular to a neural network. (neural network: the same applies below) This document describes how to process post-processing filters. [Background technology]

[0002] In recent years, demand for high-resolution, high-quality video, such as HD (High Definition) and UHD (Ultra High Definition) video, has been increasing in various fields. The higher the resolution and quality of video data, the greater the amount of information or bits transmitted compared to existing video data. This increase in the amount of information or bits transmitted leads to increased transmission and storage costs.

[0003] Therefore, highly efficient video compression technology is desired to effectively transmit, store, and play back high-resolution, high-quality video information. [Overview of the project] [Problems that the invention aims to solve]

[0004] The purpose of this disclosure is to provide a video encoding / decoding method and apparatus with improved encoding / decoding efficiency.

[0005] Furthermore, this disclosure aims to provide a method for processing NNPFC SEI messages, including a base neural network post-processing filter.

[0006] Furthermore, this disclosure aims to provide a method for processing NNPFC SEI messages, including an updated neural network post-processing filter.

[0007] Furthermore, this disclosure aims to clarify the meaning of NNPFC SEI messages in certain cases.

[0008] Furthermore, this disclosure aims to clearly provide information on the formatting, purpose, and complexity of NNPFC SEI messages.

[0009] Furthermore, this disclosure aims to clarify the formatting and handling of cases where the desired information is not available.

[0010] Furthermore, this disclosure aims to provide a non-temporary computer-readable recording medium for storing a bitstream generated by the video encoding method relating to this disclosure.

[0011] Furthermore, this disclosure aims to provide a non-temporary computer-readable recording medium that stores a bitstream that is received and decoded by the video decoding device relating to this disclosure and used for restoring video.

[0012] Furthermore, this disclosure aims to provide a method for transmitting a bitstream generated by the video encoding method relating to this disclosure.

[0013] The technical challenges addressed in this disclosure are not limited to those mentioned above, and other technical challenges not mentioned above will be clearly understood by those with ordinary skill in the art to which this disclosure pertains from the following description. [Means for solving the problem]

[0014] A video decoding method performed by a video decoding device according to one embodiment of the present disclosure includes the steps of: acquiring an SEI (supplemental enhancement information) message for an NNPF (neural-network post-filter) currently applied to a picture; determining at least one neural network available as a post-processing filter based on at least one NNPFC (neural-network post-filter characteristics) SEI message included in the SEI message for the NNPF, based on the fact that the SEI message for the NNPF is applied to the current picture; and determining whether or not a target neural network post-processing filter applicable to the current picture is activated based on at least one NNPFA (neural-network post-filter activation) SEI message included in the SEI message for the NNPF, wherein the formatting information and target information included in the NNPFC SEI message may be determined based on the fact that the NNPFC SEI message includes a base neural network post-processing filter.

[0015] A video encoding method performed by a video encoding device according to one embodiment of the present disclosure includes the steps of encoding at least one neural network available as a post-processing filter as at least one NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message, and encoding whether or not a target neural network post-processing filter applicable to the picture at present is activated as at least one NNPFA (neural-network post-filter activation) SEI message, wherein the formatting information and target information included in the NNPFC SEI message may be determined based on the fact that the NNPFC SEI message includes a base neural network post-processing filter, based on the fact that the SEI message for the NNPF (neural-network post-filter) is currently applied to the picture in the video decoding device.

[0016] A computer-readable recording medium relating to yet another aspect of this disclosure may store a bitstream generated by a video encoding method or apparatus of this disclosure.

[0017] A transmission method relating to yet another aspect of the present disclosure may transmit a bitstream generated by the video encoding method or apparatus of the present disclosure.

[0018] The features briefly summarized above are merely illustrative examples of the detailed description of the disclosure described below and do not limit the scope of the disclosure. [Effects of the Invention]

[0019] According to this disclosure, it is possible to provide a video encoding / decoding method and apparatus with improved encoding / decoding efficiency.

[0020] Also, according to the present disclosure, the type of information present in the message can be determined based on the type of the NNPFC SEI message.

[0021] Also, according to the present disclosure, the formatting and the processing method of the target information can be determined by the type of the NNPFC SEI message.

[0022] Also, according to the present disclosure, the formatting and the target information can be inferred based on the NNPFC SEI message including the base neural network post-processing filter.

[0023] Also, according to the present disclosure, a non-temporary computer-readable recording medium for storing a bitstream generated by the video encoding method according to the present disclosure can be provided.

[0024] Also, according to the present disclosure, a non-temporary computer-readable recording medium for storing a bitstream received by the video decoding device according to the present disclosure, decoded, and used for video restoration can be provided.

[0025] Also, according to the present disclosure, a method for transmitting a bitstream generated by a video encoding method can be provided.

[0026] The effects obtained by the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those having ordinary knowledge in the technical field to which the present disclosure pertains from the following description.

Brief Description of Drawings

[0027] [Figure 1] It is a schematic diagram showing a video coding system to which an embodiment according to the present disclosure is applicable. [Figure 2] It is a schematic diagram showing a video encoding device to which an embodiment according to the present disclosure is applicable. [Figure 3] It is a schematic diagram showing a video decoding device to which an embodiment according to the present disclosure is applicable. [Figure 4] This diagram illustrates the interleaved method for lumens channel induction. [Figure 5] This is a flowchart illustrating a video encoding method to which the embodiments of this disclosure can be applied. [Figure 6] This is a flowchart illustrating a video decoding method to which the embodiments of this disclosure can be applied. [Figure 7] This figure illustrates a content streaming system to which the embodiments of this disclosure can be applied. [Modes for carrying out the invention]

[0028] Hereafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, so that they can be easily implemented by a person with ordinary skill in the art to which the present disclosure pertains. However, the present disclosure may be embodied in various other forms and is not limited to the embodiments described herein.

[0029] In describing embodiments of this disclosure, if a specific description of a known configuration or function is deemed to obscure the gist of this disclosure, such detailed description will be omitted. In the figures, parts unrelated to the description of this disclosure will be omitted, and similar parts will be denoted by similar reference numerals.

[0030] In this disclosure, when one component is described as being “linked,” “joined,” or “connected” to another component, this may include not only direct linkages but also indirect linkages where other components exist in between. Furthermore, when one component is described as “containing” or “having” another component, this means, unless otherwise specified, that it may contain further other components rather than excluding them.

[0031] In this disclosure, terms such as "first," "second," etc., are used solely to distinguish one component from another, and do not limit the order or importance of the components unless otherwise specified. Therefore, within the scope of this disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment may be referred to as a first component in another embodiment.

[0032] In this disclosure, components are distinguished from each other solely to clearly describe their respective characteristics, and this does not necessarily mean that these components are separate. That is, multiple components may be integrated to constitute a single hardware or software unit, or a single component may be distributed to constitute multiple hardware or software units. Therefore, such integrated or distributed embodiments are also included in the scope of this disclosure, even without specific mention.

[0033] In this disclosure, the components described in various embodiments are not necessarily essential components, and some may be optional components. Therefore, embodiments consisting of a subset of the components described in one embodiment are also included in the scope of this disclosure. Furthermore, embodiments that further include other components in addition to the components described in various embodiments are also included in the scope of this disclosure.

[0034] This disclosure relates to the encoding and decoding of video, and unless otherwise defined herein, the terms used herein may have their ordinary meanings in the art to which this disclosure pertains.

[0035] In this disclosure, "picture" generally refers to a unit representing a single video image for a specific time period, and "slice / tile" is an encoding unit that constitutes a part of a picture. A single picture may consist of one or more slices / tiles. A slice / tile may also contain one or more CTUs (coding tree units).

[0036] In this disclosure, “pixel” or “pel” can mean the smallest unit that constitutes a picture (or video). The term “sample” may also be used as a counterpart to pixel. A sample may generally represent a pixel or a pixel value, or it may represent only the pixel / pixel value of the luma component, or only the pixel / pixel value of the chroma component.

[0037] In this disclosure, “unit” may represent a basic unit of image processing. A unit may include at least one of a specific region of a picture and information associated with that region. A unit may, as it may be, be replaced by terms such as “sample array,” “block,” or “area.” In general, an MxN block may include a sample (or sample array) or a set (or array) of transform coefficients consisting of M columns and N rows.

[0038] In this disclosure, “current block” can mean one of the following: “current coding block,” “current coding unit,” “block to encode,” “block to decode,” or “block to process.” When prediction is performed, “current block” can mean “current prediction block” or “block to predict.” When transformation (inverse transformation) / quantization (inverse quantization) is performed, “current block” can mean “current transformation block” or “block to transform.” When filtering is performed, “current block” can mean “block to filter.”

[0039] In this disclosure, "current block" may mean a block containing both a luma component block and a chroma component block, or "the luma block of the current block," unless otherwise explicitly stated as a chroma block. The luma component block of the current block may be expressed with an explicit mention of a luma component block, such as "luma block" or "current luma block." Similarly, the chroma component block of the current block may be expressed with an explicit mention of a chroma component block, such as "chroma block" or "current chroma block."

[0040] In this disclosure, " / " and "," may be interpreted as "and / or." For example, "A / B" and "A, B" may be interpreted as "A and / or B." Also, "A / B / C" and "A, B, C" may mean "at least one of A, B and / or C."

[0041] In this disclosure, “or” may be interpreted as “and / or.” For example, “A or B” may mean 1) “A” only, 2) “B” only, or 3) “A and B.” Alternatively, in this disclosure, “or” may mean “additionally or alternatively.”

[0042] Overview of the video coding system

[0043] Figure 1 is a schematic diagram showing a video coding system to which the embodiments of this disclosure can be applied.

[0044] A video coding system according to one embodiment may include an encoding device 10 and a decoding device 20. The encoding device 10 can transmit encoded video and / or image information or data to the decoding device 20 in file or streaming form via a digital storage medium or network.

[0045] An encoding device 10 according to one embodiment may include a video source generation unit 11, an encoding unit 12, and a transmission unit 13. A decoding device 20 according to one embodiment may include a receiving unit 21, a decoding unit 22, and a rendering unit 23. The encoding unit 12 may be called a video / image encoding unit, and the decoding unit 22 may be called a video / image decoding unit. The transmission unit 13 may be included in the encoding unit 12. The receiving unit 21 may be included in the decoding unit 22. The rendering unit 23 may include a display unit, and the display unit may be composed of a separate device or external component.

[0046] The video source generation unit 11 can acquire video / images through video / image capture, synthesis, or generation processes. The video source generation unit 11 may include a video / image capture device and / or a video / image generation device. The video / image capture device may include, for example, one or more cameras, or a video / image archive containing previously captured video / images. The video / image generation device may include, for example, a computer, a tablet, and a smartphone, and can generate video / images (electronically). For example, virtual video / images may be generated by a computer, in which case the video / image capture process may be replaced by a process in which related data is generated.

[0047] The encoding unit 12 can encode the input video / image data. The encoding unit 12 can perform a series of procedures such as prediction, transformation, and quantization for compression and encoding efficiency. The encoding unit 12 can output the encoded data (encoded video / image information) in the form of a bitstream.

[0048] The transmitting unit 13 can acquire encoded video / image information or data output in bitstream form and transmit it in file or streaming form to the receiving unit 21 of the decoding device 20 or other external object via a digital storage medium or network. The digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, SSD, etc. The transmitting unit 13 may include elements for generating media files in a predetermined file format and may include elements for transmission via a broadcast / communication network. The transmitting unit 13 may be provided as a transmission device separate from the encoding unit 12, in which case the transmission device may include at least one processor that acquires encoded video / image information or data output in bitstream form and a transmitting unit that transmits it in file or streaming form. The receiving unit 21 can extract / receive the bitstream from the storage medium or network and transmit it to the decoding unit 22.

[0049] The decoding unit 22 can decode the video / image by performing a series of procedures such as inverse quantization, inverse transform, and prediction, which correspond to the operation of the encoding unit 12.

[0050] The rendering unit 23 can render the decoded video / image. The rendered video / image may be displayed through the display unit.

[0051] Overview of video encoding equipment

[0052] Figure 2 is a schematic diagram showing a video encoding device to which the embodiments of this disclosure can be applied.

[0053] As shown in Figure 2, the video encoding device 100 may include a video splitting unit 110, a subtraction unit 115, a conversion unit 120, a quantization unit 130, an inverse quantization unit 140, an inverse conversion unit 150, an addition unit 155, a filtering unit 160, a memory 170, an inter-prediction unit 180, an intra-prediction unit 185, and an entropy encoding unit 190. The inter-prediction unit 180 and the intra-prediction unit 185 may be collectively called the "prediction unit". The conversion unit 120, the quantization unit 130, the inverse quantization unit 140, and the inverse conversion unit 150 may be included in the residual processing unit. The residual processing unit may further include a subtraction unit 115.

[0054] Depending on the embodiment, all or at least some of the multiple components constituting the video encoding device 100 may be embodied as a single hardware component (e.g., an encoder or a processor). Furthermore, the memory 170 may include a DPB (decoded picture buffer) and may be embodied by a digital storage medium.

[0055] The video splitting unit 110 can split the input video (or picture, frame) input to the video encoding device 100 into one or more processing units. For example, the processing units may be called coding units (CUs). Coding units can be obtained by recursively splitting a coding tree unit (CTU) or the largest coding unit (LCU) using a QT / BT / TT (Quad-tree / binary-tree / ternary-tree) structure. For example, one coding unit may be split into multiple coding units of deeper depth based on a quad-tree structure, a binary-tree structure, and / or a ternary-tree structure. For the splitting of coding units, a quad-tree structure may be applied first, followed by a binary-tree structure and / or a ternary-tree structure. The coding procedure according to this disclosure may be performed based on the final coding unit that is not further split. The maximum coding unit may be used directly as the final coding unit, or a lower-depth coding unit obtained by dividing the maximum coding unit may be used as the final coding unit. Here, the coding procedure may include procedures such as prediction, transformation, and / or restoration, which will be described later. As another example, the processing unit of the coding procedure may be a prediction unit (PU) or a transformation unit (TU). The prediction unit and the transformation unit may be divided or partitioned from the final coding unit, respectively. The prediction unit may be a unit of sample prediction, and the transformation unit may be a unit that derives transformation coefficients and / or a unit that derives a residual signal from transformation coefficients.

[0056] The prediction unit (inter-prediction unit 180 or intra-prediction unit 185) can make predictions for the block to be processed (current block) and generate a predicted block that includes prediction samples for the current block. The prediction unit can determine whether intra-prediction or inter-prediction is applied to the current block or on a CU basis. The prediction unit can generate various information regarding the prediction of the current block and transmit it to the entropy encoding unit 190. The prediction information may be encoded by the entropy encoding unit 190 and output in the form of a bitstream.

[0057] The intra-prediction unit 185 can predict the current block by referring to a sample in the current picture. The referenced sample may be located in the vicinity of the current block or at a distance from it, depending on the intra-prediction mode and / or intra-prediction method. The intra-prediction mode may include a plurality of non-directional modes and a plurality of directional modes. The non-directional modes may include, for example, a DC mode and a planar mode. The directional modes may include, for example, 33 directional prediction modes or 65 directional prediction modes, depending on the accuracy of the prediction direction. However, this is an example, and more or fewer directional prediction modes may be used depending on the settings. The intra-prediction unit 185 can also determine the prediction mode to be applied to the current block using the prediction modes applied to the surrounding blocks.

[0058] The interprediction unit 180 can derive a predicted block relative to the current block based on a reference block (reference sample array) identified by motion vectors on the reference picture. In this case, in order to reduce the amount of motion information transmitted in interprediction mode, motion information can be predicted in units of blocks, subblocks, or samples based on the correlation of motion information between the surrounding blocks and the current block. The motion information may include motion vectors and reference picture indices. The motion information may further include interprediction direction information (L0 prediction, L1 prediction, Bi prediction, etc.). In the case of interprediction, the surrounding blocks may include spatial neighboring blocks existing in the current picture and temporal neighboring blocks existing in the reference picture. The reference picture containing the reference block and the reference picture containing the temporal neighboring block may be the same or different from each other. The temporal neighboring block may be called a collocated reference block, colCU, etc. The reference picture containing the temporal neighboring block may be called a collocated picture (colPic). For example, the interpretation unit 180 can construct a motion information candidate list based on surrounding blocks and generate information indicating which candidate is used to derive the motion vector and / or reference picture index of the current block. Interpretation may be performed based on various prediction modes; for example, in skip mode and merge mode, the interpretation unit 180 can use the motion information of surrounding blocks as the motion information of the current block. In skip mode, unlike merge mode, the residual signal does not need to be transmitted.In motion vector prediction (MVP) mode, the motion vectors of surrounding blocks are used as motion vector predictors, and the motion vector of the current block can be signaled by encoding the motion vector difference and an indicator for the motion vector predictor. The motion vector difference represents the difference between the motion vector of the current block and the motion vector predictor.

[0059] The prediction unit can generate a prediction signal based on various prediction methods and / or prediction techniques described later. For example, the prediction unit may apply intra-prediction or inter-prediction to predict the current block, or it may apply intra-prediction and inter-prediction simultaneously. A prediction method that applies intra-prediction and inter-prediction simultaneously to predict the current block may be called CIIP (combined inter and intra prediction). The prediction unit can also perform intra-block copy (IBC) to predict the current block. Intra-block copy may be used, for example, for coding content images / videos such as games, as in SCC (screen content coding). IBC is a method of predicting the current block using a reference block that has already been restored in the current picture at a predetermined distance from the current block. When IBC is applied, the position of the reference block in the current picture may be encoded as a vector (block vector) corresponding to the predetermined distance. IBC basically performs prediction within the current picture, but it may be performed similarly to inter-prediction in that it derives the reference block within the current picture. In other words, IBC can use at least one of the interpretation methods described in this disclosure.

[0060] The predicted signal generated by the prediction unit may be used to generate a restored signal or a residual signal. The subtraction unit 115 can generate a residual signal (residual block, residual sample array) by subtracting the predicted signal output from the prediction unit (predicted block, predicted sample array) from the input video signal (original block, original sample array). The generated residual signal may be transmitted to the conversion unit 120.

[0061] The transformation unit 120 can generate transformation coefficients by applying a transformation method to the residual signal. For example, the transformation method may include at least one of the following: DCT (Discrete Cosine Transform), DST (Discrete Sine Transform), KLT (Karhunen-Loeve Transform), GBT (Graph-Based Transform), or CNT (Conditionally Non-linear Transform). Here, GBT refers to the transformation obtained from a graph when the relationship information between pixels is represented by this graph. CNT refers to the transformation obtained by generating a prediction signal using all previously reconstructed pixels and obtaining a transformation based on it. The transformation process may be applied to pixel blocks of the same size and square shape, or to blocks of a variable size instead of square shape.

[0062] The quantization unit 130 can quantize the conversion coefficients and transmit them to the entropy encoding unit 190. The entropy encoding unit 190 can encode the quantized signal (information about the quantized conversion coefficients) and output it as a bitstream. The information about the quantized conversion coefficients may be called residual information. The quantization unit 130 can rearrange the block-shaped quantized conversion coefficients into a one-dimensional vector form based on the coefficient scan order, and can also generate information about the quantized conversion coefficients based on the one-dimensional vector form of the quantized conversion coefficients.

[0063] The entropy encoding unit 190 can perform various encoding methods, such as exponential Golomb, CAVLC (context-adaptive variable length coding), and CABAC (context-adaptive binary arithmetic coding). In addition to the quantized conversion coefficients, the entropy encoding unit 190 can also encode information necessary for video / image restoration (e.g., the values ​​of syntax elements) together or separately. The encoded information (e.g., encoded video / image information) may be transmitted or stored in the form of a bitstream in units of NAL (network abstraction layer) units. The video / image information may further include information about various parameter sets, such as an adaptation parameter set (APS), picture parameter set (PPS), sequence parameter set (SPS), or video parameter set (VPS). The video / image information may also further include general constraint information. The signaling information, transmitted information, and / or syntax elements referred to in this disclosure may be encoded by the encoding procedure described above and included in the bitstream.

[0064] The bitstream may be transmitted over a network or stored on a digital storage medium. Here, the network may include broadcasting networks and / or communication networks, and the digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, SSD, etc. A transmitting unit (not shown) for transmitting the signal output from the entropy encoding unit 190 and / or a storage unit (not shown) for storing it may be provided as an internal / external element of the video encoding device 100, or the transmitting unit may be provided as a component of the entropy encoding unit 190.

[0065] The quantized conversion coefficients output from the quantization unit 130 may be used to generate a resistive signal. For example, by applying inverse quantization and inverse transformation to the quantized conversion coefficients in the inverse quantization unit 140 and the inverse transformation unit 150, a resistive signal (residual block or resistive sample) can be reconstructed.

[0066] The adder 155 can generate a reconstructed signal (reconstructed picture, reconstructed block, reconstructed sample array) by adding the reconstructed residual signal to the predicted signal output from the inter-prediction unit 180 or the intra-prediction unit 185. When there is no residual for the block to be processed, such as when skip mode is applied, the predicted block may be used as the reconstructed block. The adder 155 may be called the reconstruction unit or the reconstructed block generation unit. The generated reconstructed signal may be used for intra-prediction of the next block to be processed in the current picture, or, as described later, may be used for inter-prediction of the next picture after filtering.

[0067] The filtering unit 160 can improve subjective / objective image quality by applying filtering to the restored signal. For example, the filtering unit 160 can apply various filtering methods to the restored picture to generate a modified restored picture, and store the modified restored picture in the memory 170, specifically in the DPB of the memory 170. The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, and bilateral filter. The filtering unit 160 can generate various filtering information and transmit it to the entropy encoding unit 190, as will be described later in the description of each filtering method. The filtering information may be encoded by the entropy encoding unit 190 and output in the form of a bitstream.

[0068] The corrected restored picture transmitted to memory 170 may be used as a reference picture in the interpretation unit 180. This allows the video encoding device 100 to avoid prediction mismatches between the video encoding device 100 and the video decoding device when interpretation is applied, and also improves encoding efficiency.

[0069] The DPB in memory 170 can store the corrected restored picture for use as a reference picture in the inter-prediction unit 180. Memory 170 can store motion information of blocks from which motion information in the current picture has been derived (or encoded) and / or motion information of blocks in the picture that have already been restored. The stored motion information may be transmitted to the inter-prediction unit 180 for use as motion information of spatially surrounding blocks or motion information of temporally surrounding blocks. Memory 170 can store restored samples of restored blocks in the current picture and transmit them to the intra-prediction unit 185.

[0070] Overview of the video decoding device

[0071] Figure 3 is a schematic diagram showing an image decoding device to which the embodiments of this disclosure can be applied.

[0072] As shown in Figure 3, the video decoding device 200 may include an entropy decoding unit 210, an inverse quantization unit 220, an inverse transformation unit 230, an addition unit 235, a filtering unit 240, a memory 250, an inter-prediction unit 260, and an intra-prediction unit 265. The inter-prediction unit 260 and the intra-prediction unit 265 can be collectively referred to as the "prediction unit". The inverse quantization unit 220 and the inverse transformation unit 230 may be included in the residual processing unit.

[0073] All or at least some of the multiple components constituting the video decoding device 200 may be embodied as a single hardware component (e.g., a decoder or processor) depending on the embodiment. Furthermore, the memory 170 may include a DPB and may be embodied by a digital storage medium.

[0074] A video decoding device 200 that receives a bitstream containing video / image information can restore the image by performing a process corresponding to the process performed by the video encoding device 100 in Figure 2. For example, the video decoding device 200 can perform decoding using the processing unit applied in the video encoding device. Therefore, the decoding processing unit may be, for example, a coding unit. The coding unit may be a coding tree unit, or it may be obtained by dividing the largest coding unit. The restored video signal decoded and output by the video decoding device 200 may then be played back by a playback device (not shown).

[0075] The video decoding device 200 can receive the signal output from the video encoding device shown in Figure 2 in the form of a bitstream. The received signal may be decoded by the entropy decoding unit 210. For example, the entropy decoding unit 210 can parse the bitstream to derive information necessary for video restoration (or picture restoration) (e.g., video / image information). The video / image information may further include information about various parameter sets, such as an adaptation parameter set (APS), a picture parameter set (PPS), a sequence parameter set (SPS), or a video parameter set (VPS). The video / image information may also further include general constraint information. The video decoding device may further utilize the parameter set information and / or the general constraint information to decode the video. The signaling information, received information, and / or syntax elements referred to in this disclosure may be obtained from the bitstream by decoding through the decoding procedure. For example, the entropy decoding unit 210 can decode information in the bitstream based on a coding method such as exponential Golomb coding, CAVLC, or CABAC, and output the values ​​of syntax elements necessary for image restoration and the quantized values ​​of conversion coefficients related to the residual. More specifically, the CABAC entropy decoding method receives bins corresponding to each syntax element in the bitstream, determines a context model using the syntax element information to be decoded and the decoding information of the surrounding blocks and the blocks to be decoded, or symbol / bin information decoded in a previous stage, predicts the probability of bin occurrence based on the determined context model, performs arithmetic decoding of the bins, and generates symbols corresponding to the values ​​of each syntax element.In this case, the CABAC entropy decoding method can update the context model using the decoded symbol / bin information for the context model of the next symbol / bin after determining the context model. Information related to prediction from the information decoded by the entropy decoding unit 210 is provided to the prediction unit (inter-prediction unit 260 and intra-prediction unit 265), and residual values ​​that have been entropy decoded by the entropy decoding unit 210, i.e., quantized conversion coefficients and related parameter information, may be input to the inverse quantization unit 220. In addition, information related to filtering from the information decoded by the entropy decoding unit 210 may be provided to the filtering unit 240. On the other hand, a receiving unit (not shown) that receives signals output from the video encoding device may be further provided as an internal / external element of the video decoding device 200, or the receiving unit may be provided as a component of the entropy decoding unit 210.

[0076] On the other hand, the video decoding device according to this disclosure may be called a video / image / picture decoding device. The video decoding device may include an information decoder (video / image / picture information decoder) and / or a sample decoder (video / image / picture sample decoder). The information decoder may include an entropy decoding unit 210, and the sample decoder may include at least one of an inverse quantization unit 220, an inverse transformation unit 230, an addition unit 235, a filtering unit 240, a memory 250, an inter-prediction unit 260, and an intra-prediction unit 265.

[0077] The inverse quantization unit 220 can inverse quantize the quantized transformation coefficients and output the transformation coefficients. The inverse quantization unit 220 can rearrange the quantized transformation coefficients in a two-dimensional block form. In this case, the rearrangement may be performed based on the coefficient scan order performed by the video encoding device. The inverse quantization unit 220 can perform inverse quantization on the quantized transformation coefficients using quantization parameters (e.g., quantization step size information) and obtain the transformation coefficients.

[0078] The inverse conversion unit 230 can inversely convert the conversion coefficients to obtain residual signals (residual blocks, residual sample arrays).

[0079] The prediction unit can make predictions for the current block and generate a predicted block containing prediction samples for the current block. Based on the prediction information output from the entropy decoding unit 210, the prediction unit can determine whether intra-prediction or inter-prediction is applied to the current block and can determine a specific intra / inter-prediction mode (prediction method).

[0080] As mentioned in the description of the prediction unit of the video coding device 100, the prediction unit can generate prediction signals based on various prediction methods (techniques) described later.

[0081] The intra-prediction unit 265 can predict the current block by referring to the samples in the current picture. The description of the intra-prediction unit 185 may also apply to the intra-prediction unit 265.

[0082] The interprediction unit 260 can derive a predicted block relative to the current block based on a reference block (reference sample array) identified by motion vectors on the reference picture. In this case, in order to reduce the amount of motion information transmitted in interprediction mode, motion information can be predicted in block, subblock, or sample units based on the correlation of motion information between the surrounding block and the current block. The motion information may include motion vectors and reference picture indices. The motion information may further include interprediction direction information (L0 prediction, L1 prediction, Bi prediction, etc.). In the case of interprediction, the surrounding block may include spatially neighboring blocks present in the current picture and temporally neighboring blocks present in the reference picture. For example, the interprediction unit 260 can construct a motion information candidate list based on the surrounding blocks and derive the motion vector and / or reference picture index of the current block based on the received candidate selection information. Interprediction may be performed based on various prediction modes (methods), and the prediction information may include information indicating the mode (method) of interprediction for the current block.

[0083] The adder 235 can generate a restored signal (restored picture, restored block, restored sample array) by adding the acquired residual signal to the predicted signal (predicted block, predicted sample array) output from the prediction unit (including the inter-prediction unit 260 and / or intra-prediction unit 265). When there is no residual for the block to be processed, such as when skip mode is applied, the predicted block may be used as the restored block. The description of the adder 155 may also apply to the adder 235. The adder 235 may be called the restore unit or the restored block generation unit. The generated restored signal may be used for intra-prediction of the next block to be processed in the current picture, or, as described later, may be used for inter-prediction of the next picture after filtering.

[0084] The filtering unit 240 can improve subjective / objective image quality by applying filtering to the restored signal. For example, the filtering unit 240 can apply various filtering methods to the restored picture to generate a modified restored picture, and the modified restored picture can be stored in the memory 250, specifically in the DPB of the memory 250. The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, and bilateral filter.

[0085] The restored picture stored (modified) in the DPB of memory 250 may be used as a reference picture in the inter-prediction unit 260. Memory 250 can store motion information of blocks from which motion information in the current picture has been derived (or decoded) and / or motion information of blocks in the picture that have already been restored. The stored motion information can be transmitted to the inter-prediction unit 260 for use as motion information of spatially surrounding blocks or motion information of temporally surrounding blocks. Memory 250 can store restored samples of restored blocks in the current picture and transmit them to the intra-prediction unit 265.

[0086] In this specification, the embodiments described for the filtering unit 160, inter-prediction unit 180, and intra-prediction unit 185 of the video encoding device 100 may be applied identically or in a corresponding manner to the filtering unit 240, inter-prediction unit 260, and intra-prediction unit 265 of the video decoding device 200, respectively.

[0087] Neural network post-filter characteristics (NNPFC)

[0088] The combination of Tables 1 and 2 represents the NNPFC syntax structure.

[0089] [Table 1]

[0090] [Table 2]

[0091] The NNPFC syntax structures in Tables 1 and 2 may be signaled in the form of SEI (supplemental enhancement information) messages. SEI messages that signal the NNPFC syntax structures in Tables 1 and 2 can be called NNPFC SEI messages.

[0092] NNPFC SEI messages can identify neural networks available as post-processing filters. The use of identified post-processing filters for a particular picture can be indicated using neural-network post-filter activation SEI messages. Here, "post-processing filter" and "post-filter" may have the same meaning.

[0093] To use such SEI messages, you may need to define variables like the following:

[0094] - The width and height of the decoded output picture may be cropped in lumen samples, and these widths and heights can be represented by CroppedWidth and CroppedHeight, respectively.

[0095] - The lumens sample arrays of the cropped and decoded output picture, CroppedYPic[idx], and the chromens sample arrays, CroppedCbPic[idx] and CroppedCrPic[idx], may be used as inputs to the post-processing filter if they exist, and idx may be in the range of 0 to numInputPics-1.

[0096] - BitDepth Y This can show the bit depth of the cropped, decoded output picture relative to the lumens sample array.

[0097] - BitDepth C This can show the bit depth of the chroma sample array (if any) of the cropped, decoded output picture.

[0098] - ChromaFormatIdc can indicate a chroma format identifier.

[0099] - If the value of nnpfc_auxiliary_inp_idc is 1, the filtering strength control value StrengthControlVal must be a real number in the range of 0 to 1.

[0100] The variables SubWidthC and SubHeightC may be derived from ChromaFormatIdc. There may be two or more NNPFC SEI messages for the same picture. If two or more NNPFC SEI messages with different nnpfc_id values ​​exist or are activated for the same picture, the two or more NNPFC SEI messages may have identical or different nnpfc_purpose and nnpfc_mode_idx values.

[0101] nnpfc_id may contain an identification number that can be used to identify the post-processing filter. The nnpfc_id value is between 0 and 2. 32It must be within the range of -2. The range is 256~511 and 2 31 ~2 32 -2 range nnpfc_id values ​​may be reserved for future use. Decoders are in the range of 256~511 or 2 31 ~2 32 NNPFC SEI messages with an nnpfc_id in the -2 range must be ignored.

[0102] If an NNPFC SEI message is currently the first NNPFC SEI message in a decoding sequence that has a specific nnpfc_id value within the CLVS (coded layer video sequence), the following may apply:

[0103] - The aforementioned SEI message may indicate a base post-processing filter.

[0104] - The SEI message may, in the output order, be associated with the currently decoded picture and all subsequent decoded pictures of the current layer until the CLVS finishes.

[0105] An NNPFC SEI message may be a repetition of a previous NNPFC SEI message currently in the CLVS in the decoding order, and the subsequent semantics may be applied as if this SEI message were the only NNPFC SEI message currently in the CLVS with the same content.

[0106] If an NNPFC SEI message is not the first NNPFC SEI message in the decoding sequence that currently has a specific nnpfc_id value within the CLVS, the following may apply:

[0107] - The SEI message may be associated in output order with the current CLVS or all subsequent decoded pictures of the currently decoded picture and the current layer until the current CLVS ends, or it may be associated in output order with the next NNPFC SEI message having a specific nnpfc_id value in the current CLVS.

[0108] If an NNPFC SEI message is currently the first NNPFC SEI message in a decoding sequence having a specific nnpfc_id value within the CLVS, a value of 1 for nnpfc_mode_idc may indicate that the basic post-processing filter associated with the nnpfc_id value is a neural network, and the neural network may be identified by a URI represented by nnpfc_uri using the format identified by the tag URI nnpfc_tag_uri.

[0109] If an NNPFC SEI message is not the first NNPFC SEI message in the decoding sequence currently having a specific nnpfc_id value within the CLVS, a value of 1 for nnpfc_mode_idc may indicate that an update to a basic post-processing filter having the same nnpfc_id value is defined by a URI represented by nnpfc_uri using the tag URI nnpfc_tag_uri.

[0110] The value of nnpfc_mode_idc may be restricted to being in the range of 0 to 1 in the bitstream. Values ​​in the range of 2 to 255 for nnpfc_mode_idc may be reserved for future use and do not need to be present in the bitstream. The decoder must ignore NNPFC SEI messages with nnpfc_mode_idc in the range of 2 to 255. Values ​​of nnpfc_mode_idc greater than 255 do not need to be present in the bitstream and do not need to be reserved for future use.

[0111] If the aforementioned SEI message is the first NNPFC SEI message in the decoding sequence currently having a specific nnpfc_id value within CLVS, the PostProcessingFilter() may be assigned the same as the basic postprocessing filter.

[0112] If the aforementioned SEI message is not the first NNPFC SEI message in the decoding sequence currently having a specific nnpfc_id value within CLVS, the PostProcessingFilter() may apply the update defined by the SEI message to the basic postprocessing filter to obtain it.

[0113] Updates are not cumulative; rather, each update may be applied to the basic post-processing filter, which is the post-processing filter specified by the first NNPFC SEI message in the decoding sequence that currently has a specific nnpfc_id value within CLVS.

[0114] nnpfc_reserved_zero_bit_a may be restricted to have the same value as 0 by bitstream restrictions. The decoder may be restricted to ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0115] nnpfc_tag_uri may contain a tag URI having syntax and semantics specified in IETF RFC 4151 that identifies the neural network used as the basic post-processing filter or an update to the basic post-processing filter using the nnpfc_id value identified by nnpfc_uri. Using nnpfc_tag_uri, the format of the neural network data specified by nnpfc_uri can be uniquely identified without a central registration authority. An nnpfc_tag_uri identical to "tag:iso.org,2023:15938-17" can indicate that the neural network data identified by nnpfc_uri complies with ISO / IEC 15938-17.

[0116] nnpfc_uri may contain a URI having the syntax and semantics specified in IETF Internet Standard 66 that identifies a neural network used as a basic post-processing filter or an update to a basic post-processing filter that uses the same nnpfc_id value.

[0117] A value of 1 for nnpfc_formatting_and_purpose_flag indicates the presence of syntax elements related to the filter's purpose, input formatting, output formatting, and complexity. A value of 0 for nnpfc_formatting_and_purpose_flag indicates the absence of syntax elements related to the filter's purpose, input formatting, output formatting, and complexity.

[0118] If the aforementioned SEI message is the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the value of nnpfc_formatting_and_purpose_flag must be the same as 1. If the aforementioned SEI message is not the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the value of nnpfc_formatting_and_purpose_flag must be the same as 0.

[0119] nnpfc_purpose can indicate the purpose of the post-processing filter as specified in Table 3.

[0120] The value of nnpfc_purpose must be within the range of 0 to 5 due to bitstream limitations. Values ​​of nnpfc_purpose between 6 and 1023 do not exist in the bitstream and may be reserved for future use. The decoder must ignore NNPFC SEI messages with nnpfc_purpose in the range of 6 to 1203. nnpfc_purpose values ​​greater than 1023 do not exist in the bitstream and are not reserved for future use.

[0121] [Table 3]

[0122] When a reserved value for nnpfc_purpose is used later, the syntax of this SEI message may be extended to existing syntax elements, provided that nnpfc_purpose is identical to that value.

[0123] If the value of SubWidthC is 1 and the value of SubHeightC is 1, then nnpfc_purpose must not have a value of 2 or 4.

[0124] A value of 1 for nnpfc_out_sub_c_flag indicates that the value of outSubWidthC is 1 and the value of outSubHeightC is 1. A value of 0 for nnpfc_out_sub_c_flag indicates that the value of outSubWidthC is 2 and the value of outSubHeightC is 1. If nnpfc_out_sub_c_flag does not exist, outSubWidthC may be inferred to be the same as SubWidthC, and outSubHeightC may be inferred to be the same as SubHeightC. If the value of ChromaFormatIdc is 2 and nnpfc_out_sub_c_flag exists, the value of nnpfc_out_sub_c_flag must be the same as 1.

[0125] nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples can indicate the width and height of the luma sample array of the picture, respectively, resulting from applying a post-processing filter identified by nnpfc_id to the cropped, decoded output picture. If nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples are not present, they may be inferred to be the same as CroppedWidth and CroppedHeight, respectively. The value of nnpfc_pic_width_in_luma_samples should be in the range of CroppedWidth to CroppedWidth*16-1. The value of nnpfc_pic_height_in_luma_samples should be in the range of CroppedHeight to CroppedHeight*16-1.

[0126] nnpfc_num_input_pics_minus2+2 can indicate the number of decoded output pictures used as input to the post-processing filter.

[0127] nnpfc_interpolated_pics[i] can indicate the number of interpolated pictures generated by the post-processing filter between the i-th picture and the (i+1)-th picture used as input to the post-processing filter.

[0128] The variables `numInputPics`, which indicates the number of pictures used as input to the post-processing filter, and `numOutputPics`, which indicates the total number of pictures produced as a result of the post-processing filter, may be derived as shown in Table 4.

[0129] [Table 4]

[0130] A value of 1 for nnpfc_component_last_flag indicates that the last dimension of the input tensor inputTensor for the post-processing filter and the output tensor outputTensor, which is the result of the post-processing filter, are currently used for the channel. A value of 0 for nnpfc_component_last_flag indicates that the third dimension of the input tensor inputTensor for the post-processing filter and the output tensor outputTensor, which is the result of the post-processing filter, are currently used for the channel.

[0131] The first dimension of the input and output tensors may be used as a batch index, as used in some neural network frameworks. The formula within the semantics of this SEI message uses a batch size corresponding to a batch index such as 0, but the batch size used as input for neural network inference may be determined by the implementation of post-processing.

[0132] For example, when the value of nnpfc_inp_order_idc is the same as 3 and the value of nnpfc_auxiliary_inp_idc is the same as 1, the input tensor may have 7 channels, including 4 lumer matrices, 2 chroma matrices, and 1 auxiliary input matrix. In this case, the DeriveInputTensors() process can induce each of the 7 channels of the input tensor one by one, and when a particular channel is processed among these channels, that channel may be called the current channel during the process.

[0133] nnpfc_inp_format_idc can indicate how to convert the sample values ​​of the cropped, decoded output picture into input values ​​for the post-processing filter. If nnpfc_inp_format_idc is 0, the input values ​​for the post-processing filter are real numbers, and the InpY() and InpC() functions may be specified as shown in Equation 1.

[0134]

number

[0135] If the value of nnpfc_inp_format_idc is 1, the input values ​​for the post-processing filter are unsigned integer numbers, and the InpY() and InpC() functions may be derived as shown in Table 5.

[0136] [Table 5]

[0137] The variable inpTensorBitDepth may be derived from the syntax element nnpfc_inp_tensor_bitlength_minus8 described below.

[0138] Values ​​of nnpfc_inp_format_idc greater than 1 may be reserved for future use and do not need to be present in the bitstream. The decoder must ignore NNPFC SEI messages containing reserved values ​​for nnpfc_inp_format_idc.

[0139] nnpfc_inp_tensor_bitlength_minus8+8 can represent the bit depth of the rumor sample values ​​in the input integer tensor. The value of inpTensorBitDepth can be derived as shown in equation 2.

[0140]

number

[0141] The value of nnpfc_inp_tensor_bitlength_minus8 may be restricted to being within the range of 0 to 24.

[0142] nnpfc_inp_order_idc can indicate how the sample array of the cropped, decoded output picture is aligned to one of the input pictures for the post-processing filter.

[0143] The value of nnpfc_inp_order_idc must be in the range of 0 to 3 in the bitstream. Values ​​of nnpfc_inp_order_idc between 4 and 255 do not exist in the bitstream. The decoder must ignore NNPFC SEI messages with nnpfc_inp_order_idc in the range of 4 to 255. Values ​​of nnpfc_inp_order_idc greater than 255 do not exist in the bitstream and are not reserved for future use.

[0144] If the value of ChromaFormatIdc is not 1, the value of nnpfc_inp_order_idc must not be 3.

[0145] Table 6 contains explanations regarding the nnpfc_inp_order_idc value.

[0146] [Table 6]

[0147] A patch may be a rectangular array of samples from the picture components (e.g., lumens or chroma components).

[0148] A value of nnpfc_auxiliary_inp_idc greater than 0 indicates the presence of auxiliary input data in the neural network postfilter's input tensor. A value of nnpfc_auxiliary_inp_idc of 0 indicates the absence of auxiliary input data in the input tensor. A value of nnpfc_auxiliary_inp_idc of 1 indicates that the auxiliary input data is induced by the methods disclosed in Tables 7 to 9.

[0149] The value of nnpfc_auxiliary_inp_idc must be in the range of 0 to 1 in the bitstream. Values ​​of nnpfc_inp_order_idc between 2 and 255 do not exist in the bitstream. The decoder must ignore NNPFC SEI messages with nnpfc_inp_order_idc in the range of 2 to 255. Values ​​of nnpfc_inp_order_idc greater than 255 do not exist in the bitstream and are not reserved for future use.

[0150] The process DeriveInputTensors() for deriving the input tensor inputTensor for given vertical sample coordinates cTop and horizontal sample coordinates cLeft which specify the upper-left sample position of the sample patch included in the input tensor can be shown as a join in Tables 7-9.

[0151] [Table 7]

[0152] [Table 8]

[0153] [Table 9]

[0154] A value of 1 for nnpfc_separate_colour_description_present_flag indicates that a unique combination of color primaries, transformation characteristics, and matrix coefficients for the picture applied by the post-processing filter is specified in the SEI message syntax structure. A value of 0 for nnfpc_separate_colour_description_present_flag indicates that the combination of color primaries, transformation characteristics, and matrix coefficients for the picture applied by the post-processing filter is identical to that displayed in the CLVS VUI parameters.

[0155] nnpfc_colour_primaries may have the same semantics as defined for the vui_colour_primaries syntax element, except as follows:

[0156] - nnpfc_colour_primaries can indicate the primary colors of the picture that appear as a result of applying the neural network postfilter specified in the SEI message, rather than the primary colors used in CLVS.

[0157] - If nnpfc_colour_primaries is not present in the NNPFC SEI message, the value of nnpfc_colour_primaries may be inferred to be the same as the value of vui_colour_primaries.

[0158] nnpfc_transfer_characteristics may have the same semantics as defined for the vui_transfer_characteristics syntax element, except as follows:

[0159] - nnpfc_transfer_characteristics can indicate the transformation characteristics of the picture that appears as a result of applying the specified neural network postfilter to the SEI message, rather than the transformation characteristics used in CLVS.

[0160] - If nnpfc_transfer_characteristics is not present in the NNPFC SEI message, the value of nnpfc_transfer_characteristics may be inferred to be the same as the value of vui_transfer_characteristics.

[0161] nnpfc_matrix_coeffs may have the same semantics as specified for the vui_matrix_coeffs syntax element, except as follows:

[0162] - nnpfc_matrix_coeffs can indicate the matrix coefficients of the picture that appear as a result of applying the specified neural network postfilter to the SEI message, rather than the matrix coefficients used in CLVS.

[0163] - If nnpfc_matrix_coeffs is not present in the NNPFC SEI message, the value of nnpfc_matrix_coeffs can be inferred to be the same as the value of vui_matrix_coeffs.

[0164] - The acceptable values ​​for nnpfc_matrix_coeffs do not need to be restricted by the chroma format of the decoded video picture, as shown by the ChromaFormatIdc value for the semantics of the VUI parameter.

[0165] - If the value of nnpfc_matrix_coeffs is the same as 0, the value of nnpfc_out_order_idc must not be the same as 1 or 3.

[0166] The value 0 of nnpfc_out_format_id indicates that for the bit depth bitDepth required for subsequent post - processing or display, the sample values output by the post - processing filter are real numbers linearly mapped from the range of values from 0 to 1 to the range of unsigned integer values from 0 to (1 << bitDepth)-1. The value 1 of nnpfc_out_format_flag can indicate that the sample values output by the post - processing filter are unsigned integers in the range from 0 to (1 << (nnpfc_out_tensor_bitlength_minus8 + 8))-1. Values of nnpfc_out_format_idc greater than 1 do not exist in the bitstream. The decoder must ignore NNPFC SEI messages containing reserved values of nnpfc_out_format_idc. "+8" can indicate the bit depth of the sample values in the output integer tensor. The value of nnpfc_out_tensor_bitlength_minus8 must exist in the range from 0 to 24.

[0167] nnpfc_out_order_idc can indicate the output order of samples output from the post - processing filter. The value of nnpfc_out_order_idc must exist in the range from 0 to 3 in the bitstream. Values from 4 to 255 for nnpfc_out_order_idc do not exist in the bitstream. The decoder must ignore NNPFC SEI messages having nnpfc_out_order_idc in the range from 4 to 255. Values of nnpfc_out_order_idc greater than 255 do not exist in the bitstream and are not reserved for future use. When the value of nnpfc_purpose is 2 or 4, the value of nnpfc_out_order_idc must not be the same as 3.

[0168] Table 10 shows the explanations for the values of nnpfc_out_order_idc.

[0169] [Table 10]

[0170] The StoreOutputTensors() process for deriving sample values ​​in the output sample arrays FilteredYPic, FilteredCbPic, and FilteredCrPic, filtered from the output tensor outputTensor, which is based on the given vertical sample coordinate cTop and the horizontal sample coordinate cLeft indicating the top-left sample position for the sample patch contained in the input tensor, may be expressed as the joins in Tables 11 and 12.

[0171] [Table 11]

[0172] [Table 12]

[0173] A value of 1 for nnpfc_constant_patch_size_flag indicates that the post-processing filter accepts the exact patch size specified by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1 as input. A value of 0 for nnpfc_constant_patch_size_flag indicates that the post-processing filter accepts any patch size that is a positive integer multiple of the patch size specified by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1 as input.

[0174] npfc_patch_width_minus1+1 can indicate the number of horizontal samples of the patch size required for the input to the post-processing filter when the value of nnpfc_constant_patch_size_flag is 1. The value of nnpfc_patch_width_minus1 must be in the range of 0 to Min(32766,CroppedWidth-1).

[0175] npfc_patch_height_minus1+1 can indicate the number of vertical samples in the patch size required for the post-processing filter input when the value of nnpfc_constant_patch_size_flag is 1. The value of nnpfc_patch_height_minus1 must be in the range of 0 to Min(32766,CroppedHeight-1).

[0176] The inpPatchWidth and inpPatchHeight variables may be set to the patch size width and patch size height, respectively.

[0177] If the value of nnpfc_constant_patch_size_flag is 0, the following may be applied.

[0178] - The values ​​of inpPatchWidth and inpPatchHeight may be provided by external means or set by the post-processor itself.

[0179] - The value of inpPatchWidth must be a positive integer multiple of nnpfc_patch_width_minus1+1 and must be less than or equal to CroppedWidth. The value of inpPatchHeight must be a positive integer multiple of nnpfc_patch_height_minus1+1 and must be less than or equal to CroppedHeight.

[0180] Otherwise, (if the value of nnpfc_constant_patch_size_flag is 1), the value of inpPatchWidth may be set to the same as nnpfc_patch_width_minus1+1, and the value of inpPatchHeight may be set to the same as nnpfc_patch_height_minus1+1.

[0181] nnpfc_overlap can indicate the number of horizontal and vertical overlapping samples of adjacent input tensors in the post-processing filter. The value of nnpfc_overlap must be in the range of 0 to 16383.

[0182] The variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize may be derived as shown in Table 13.

[0183] [Table 13]

[0184] The requirement for bitstream conformance is that outPatchWidth*CroppedWidth must be the same as nnpfc_pic_width_in_luma_samples*inpPatchWidth, and outPatchHeight*CroppedHeight must be the same as nnpfc_pic_height_in_luma_samples*inpPatchHeight.

[0185] nnpfc_padding_type can indicate the padding process when referencing sample locations outside the boundaries of the cropped decoded output picture, as described in Table 14. The value of nnpfc_padding_type must be in the range of 0 to 15.

[0186] [Table 14]

[0187] nnpfc_luma_padding_val can indicate the luma value to be used for padding when the value of nnpfc_padding_type is 4.

[0188] nnpfc_cb_padding_val can indicate the Cb value to be used for padding when the value of nnpfc_padding_type is 4.

[0189] nnpfc_cr_padding_val can indicate the Cr value to be used for padding when the value of nnpfc_padding_type is 4.

[0190] The InpSampleVal(y,x,picHeight,picWidth,CroppedPic) function, whose inputs are the vertical sample position y, the horizontal sample position x, the picture height picHeight, the picture width picWidth, and the sample array CroppedPic, can return the derived SampleVal value as shown in Table 15.

[0191] For inputs to the InpSampleVal() function, vertical positions may be listed before horizontal positions for compatibility with the input tensor rules of some inference engines.

[0192] [Table 15]

[0193] The processes in Table 16 may be used to generate filtered pictures by patching the cropped decoded output pictures using the PostProcessingFilter() post-processing filter, which may include a Y sample array FilteredYPic, a Cb sample array FilteredCbPic, and a Cr sample array FilteredCrPic, as shown by nnpfc_out_order_idc.

[0194] [Table 16]

[0195] A value of 1 for nnpfc_complexity_info_present_flag indicates that there is one or more syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id. A value of 0 for nnpfc_complexity_info_present_flag indicates that there are no syntax elements indicating the complexity of the post-processing filter associated with nnpfc_id.

[0196] A value of 0 for nnpfc_parameter_type_idc can indicate that the neural network uses only integer parameters. A value of 1 for nnpfc_parameter_type_flag can indicate that the neural network can use floating-point or integer parameters. A value of 2 for nnpfc_parameter_type_idc can indicate that the neural network uses only binary parameters. A value of 3 for nnpfc_parameter_type_idc may be reserved for future use and is not present in the bitstream. The decoder must ignore NNPFC SEI messages where the value of nnpfc_parameter_type_idc is 3.

[0197] The values ​​0, 1, 2, and 3 for nnpfc_log2_parameter_bit_length_minus3 indicate that the neural network will not use parameters with bit lengths greater than 8, 16, 32, and 64, respectively. If nnpfc_parameter_type_idc exists and nnpfc_log2_parameter_bit_length_minus3 does not exist, the neural network does not need to use parameters with bit lengths greater than 1.

[0198] nnpfc_num_parameters_idc can indicate the maximum number of neural network parameters for the post-processing filter in units of 2048. A value of 0 for nnpfc_num_parameters_idc indicates that the maximum number of neural network parameters is unknown. The value of nnpfc_num_parameters_idc must be in the range of 0 to 52. Values ​​of nnpfc_num_parameters_idc greater than 52 do not exist in the bitstream. The decoder must ignore NNPFC SEI messages with nnpfc_num_parameters_idc greater than 52.

[0199] If the value of nnpfc_num_parameters_idc is greater than 0, the maxNumParameters variable may be derived as shown in Equation 3.

[0200]

number

[0201] The number of neural network parameters in the post-processing filter may be limited to a number less than or equal to maxNumParameters.

[0202] A nnpfc_num_kmac_operations_idc greater than 0 can indicate that the maximum number of multiply-accumulate operations per sample of the post-processing filter is less than or equal to nnpfc_num_kmac_operations_idc * 1000. A value of 0 for nnpfc_num_kmac_operations_idc can indicate that the maximum number of multiply-accumulate operations of the network is unknown. The value of nnpfc_num_kmac_operations_idc must be in the range of 0 to 2 32 -1.

[0203] A nnpfc_total_kilobyte_size greater than 0 can indicate the total size (kilobytes) required to store the uncompressed parameters of the neural network. The total size in bits may be a number greater than or equal to the sum of the bits used to store each parameter. nnpfc_total_kilobyte_size may be the result of rounding up the total size (bits) divided by 8000. A value of 0 for nnpfc_total_kilobyte_size can indicate that the overall size required to store the parameters for the neural network is unknown. The value of nnpfc_total_kilobyte_size must be in the range of 0 to 2 32 -1.

[0204] nnpfc_reserved_zero_bit_b must be identical to 0 in the bitstream. The decoder must ignore NNPFC SEI messages where nnpfc_reserved_zero_bit_b is not 0.

[0205] nnpfc_payload_byte[i] may contain the i-th byte of the bitstream. The byte sequence nnpfc_payload_byte[i] for all existing values ​​of i must be a complete bitstream compliant with ISO / IEC 15938-17.

[0206] Neural network post-filter activation (NNFPA)

[0207] Table 17 shows the syntax structure for NNFPA.

[0208] [Table 17]

[0209] The NNPFA syntax structure shown in Table 17 may be signaled in the form of an SEI message. An SEI message that signals the NNPFA syntax structure shown in Table 17 can be called an NNPFA SEI message.

[0210] The NNPFA SEI message can activate or deactivate the possible use of the target neural network post-processing filter identified by nnpfa_target_id for post-processing filtering of the picture set.

[0211] Multiple NNPFA SEI messages may exist for the same picture if the post-processing filter is used for a different purpose or to filter out a different color component.

[0212] nnpfa_target_id can indicate a target neural network post-processing filter specified by one or more NNPFC SEI messages that currently have the same nnpfc_id as nnfpa_target_id in relation to the picture.

[0213] The value of nnpfa_target_id is 0 to 2 32 It must be within the range of -2. The range of 256~511 and 231 ~2 32 nnpfa_target_id values ​​within the range of -2 may be reserved for future use. Decoders are 256~511 or 2 31 ~2 32 NNPFA SEI messages with an nnpfa_target_id within the range of -2 must be ignored.

[0214] An NNPFA SEI message with a specific value for nnpfa_target_id must not currently exist in the PU unless one or both of the following conditions are true:

[0215] - Currently, within CLVS, there exists an NNPFC SEI message whose nnpfc_id is identical to a specific value of nnpfa_target_id in the PU that precedes the current PU in the decoding order.

[0216] - Currently, there exists an NNPFC SEI message with an nnpfc_id that matches a specific value of nnpfa_target_id in the PU.

[0217] If a PU contains all NNPFC SEI messages with a specific value for nnpfc_id and all NNPFA SEI messages with the same nnpfa_target_id as the specific value for nnpfc_id, then the NNPFC SEI messages must precede the NNPFA SEI messages in the decoding order.

[0218] A value of 1 for nnpfa_cancel_flag can indicate that the persistence of the target network post-processing filter, which was set by any previous NNPFA SEI message having the same nnpfa_target_id as the current SEI message, is canceled. That is, the target network post-processing filter will not be used any further unless it is activated by another NNPFA SEI message having the same nnpfa_target_id as the current SEI message and the same nnpfa_cancel_flag of 0. A value of 0 for nnpfa_cancel_flag can indicate that nnpfa_persistence_flag will continue.

[0219] The nnpfa_persistence_flag can indicate the persistence of the target neural network post-processing filter for the current layer. A value of nnpfa_persistence_flag of 0 indicates that the target neural network post-processing filter can only be used for post-processing filtering on the current picture. A value of nnpfa_persistence_flag of 1 indicates that the target neural network post-processing filter can be used for post-processing filtering on the current picture and all subsequent pictures in the current layer in output order until one or more of the following conditions are true.

[0220] - A new CLVS for the current layer is started.

[0221] - Bitstream ends

[0222] - The picture in the current layer associated with the NNPFA SEI message that has the same nnpfa_target_id as the current SEI message and the same nnpfa_cancel_flag as 1 will be output after the current picture in the output order.

[0223] The target neural network post-processing filter is not applied to subsequent pictures in the current layer associated with NNPFA SEI messages that have the same nnpfa_target_id and nnpfa_cancel_flag as the current SEI message.

[0224] Post-filter hint

[0225] Table 18 shows the syntax structure for post-filter hints.

[0226] [Table 18]

[0227] The post-filter hint syntax structures in Table 18 may be signaled in the form of SEI messages. SEI messages that signal the post-filter hint syntax structures in Table 18 can be called post-filter hint SEI messages.

[0228] Post-filter hint SEI messages can provide post-filter coefficients or correlation information for post-filter design, potentially allowing the decoded and output picture set to be used in post-processing to obtain improved display quality.

[0229] A value of 1 for `filter_hint_cancel_flag` indicates that the persistence of a previous post-filter hint SEI message is canceled in the output order in which the SEI message is applied to the current layer. A value of 0 for `filter_hint_cancel_flag` indicates that post-filter hint information follows.

[0230] The `filter_hint_persistence_flag` can indicate the persistence of the post-filter hint SEI message for the current layer. A value of 0 for `filter_hint_persistence_flag` indicates that the post-filter hint applies only to the currently decoded picture. A value of 1 for `filter_hint_persistence_flag` indicates that the post-filter hint SEI message applies to the currently decoded picture and persists for all subsequent pictures in the current layer by output order until one or more of the following conditions are true.

[0231] - A new CLVS for the current layer is started.

[0232] - Bitstream ends

[0233] - Post-filter hints: Pictures in the current layer of the AU associated with SEI messages are output after the current picture in the output order.

[0234] `filter_hint_size_y` can represent the filter coefficient or the vertical size of the correlation array. The value of `filter_hint_size_y` must be in the range of 1 to 15.

[0235] `filter_hint_size_x` can represent the filter coefficient or the horizontal size of the correlation array. The value of `filter_hint_size_x` must be in the range of 1 to 15.

[0236] `filter_hint_type` can indicate the type of filter hint transmitted, as shown in Table 19. The value of `filter_hint_type` must be in the range of 0 to 2. A `filter_hint_type` value equal to 3 does not exist in the bitstream. The decoder must ignore post-filter hint SEI messages where `filter_hint_type` is 3.

[0237] [Table 19]

[0238] A value of 1 for filter_hint_chroma_coeff_present_flag indicates that a filter coefficient exists for the chroma. A value of 0 for filter_hint_chroma_coeff_present_flag indicates that no filter coefficient exists for the chroma.

[0239] `filter_hint_value[cIdx][cy][cx]` can represent the filter coefficients, or the cross-correlation matrix elements between the original signal and the decoded signal, with 16-bit precision. The value of `filter_hint_value[cIdx][cy][cx]` is -2 31 +1~2 31 It must be within the range of -1. cIdx may indicate the associated color element, cy may indicate the vertical counter, and cx may indicate the horizontal counter. Depending on the value of filter_hint_type, the following may be applied:

[0240] - If the value of filter_hint_type is 0, the coefficients of a 2D FIR (Finite Impulse Response) filter of size filter_hint_size_y * filter_hint_size_x may be transmitted.

[0241] - On the other hand, if the value of filter_hint_type is 1, the filter coefficients of two one-dimensional FIR filters may be transmitted. In this case, the value of filter_hint_size_y must be 2. An index cy of 0 can indicate the filter coefficient of a horizontal filter, and a cy of 1 can indicate the filter coefficient of a vertical filter. In the filtering process, the horizontal filter may be applied first, and the result may be filtered by the vertical filter.

[0242] - Otherwise (if the value of filter_hint_type is 2), the transmitted hint can indicate the cross-correlation matrix between the original signal s and the decoded signal s'.

[0243] The normalized cross-correlation matrix for the associated color component identified by cIdx of size filter_hint_size_y * filter_hint_size_x may be defined as in Equation 4.

[0244]

Equation

[0245] In Equation 4, s represents the sample array of the color component cIdx of the original picture, s' represents the corresponding array of the decoded picture, h represents the vertical height of the associated color component, w represents the horizontal width of the associated color component, bitDepth represents the bit depth of the color component. Also, OffsetY is the same as (filter_hint_size_y >> 1), OffsetX is the same as (filter_hint_size_x >> 1), the range of cy is 0 <= cy < filter_hint_size_y, and the range of cx is 0 <= cx < filter_hint_size_x.

[0246] The decoder can derive the Wiener post-filter from the cross-correlation matrix between the original signal and the decoded signal and the auto-cross-correlation matrix of the decoded signal.

[0247] Problems with conventional technology

[0248] For the neural-network post-filter characteristics (NNPFC) SEI message, the flag nnpfc_formatting_and_puropose_flag is included to control the presence of syntax elements associated with some descriptions including descriptions related to the filter complexity information, formatting, and purpose. The presence of the flag is specified as follows:

[0249] -----Snippet start-----

[0250] If a particular SEI message is the first NNPFC SEI message with a particular nnpfc_id value in the current CLVS in decoding order, the value of nnpfc_formatting_and_purpose_flag must be 1. On the other hand, if a particular SEI message is not the first NNPFC SEI message with a particular nnpfc_id value in the current CLVS in decoding order, the value of nnpfc_formatting_and_purpose_flag must be 0.

[0251] -----Snippet end-----

[0252] The above constraints can specify that signaling of syntax elements for describing formatting, purpose, and complexity is only allowed for the base neural-network post-processing filter, i.e., the base neural-network post-filter, in the SEI, while the same way of signaling is not allowed for the update filter. However, since there can be at least two possibilities as follows, problems can occur in the meaning of the above-described constraints itself when there is no signaling for formatting, purpose, and complexity:

[0253] 1. In the case of a NNPFC message without formatting, purpose, and complexity information, the information is inferred from the NNPFC SEI message including the base neural network post - processing filter.

[0254] 2. In the case of a NNPFC message without formatting, purpose, and complexity information, the information is not known.

[0255] When the flag (i.e., nnpfc_formatting_and_purpose_flag) is 0, the meaning of the message needs to be specified in the NNPFC SEI message semantics.

[0256] 〔Embodiment〕

[0257] Examples In the present disclosure, embodiments that can solve the above - mentioned problems are proposed.

[0258] On the other hand, when explaining the present disclosure, the post - processing filter, the post - filter, and the post - treatment filter may be used in the same meaning. Also, the following embodiments may be used individually or in combination of two or more.

[0259] Hereinafter, NNPFC has the NNPFC syntax structure in Tables 1 and 2 and may be signaled in the form of an SEI message. In this case, NNPFC may be a NNPFC SEI message. NNPFA has the NNPFA syntax structure in Table 17 and may be signaled in the form of an SEI message. In this case, NNPFA may be a NNPFA SEI message. The post - filter hint has the post - filter hint syntax structure in Table 18 and may be signaled in the form of an SEI message. In this case, the post - filter hint may be a post - filter hint SEI message.

[0260] 1. Ensure that formatting and signaling of target information are present only in NNPFC SEI messages that include base neural network post-processing filters.

[0261] 2. In updated NNPFC SEI messages containing a neural network post-processing filter, formatting and target information should be inferred to be the same as the information signaled in the associated NNPFC SEI message containing the base neural network post-processing filter (i.e., an NNPFC SEI message with the same nnpfc_id).

[0262] 3. Alternatively, if formatting and purpose information does not exist, specify that information regarding such information will not be provided or will be provided from an external source.

[0263] 4. Alternatively, the following may apply:

[0264] a. For NNPFC SEI messages that include a base neural network post-processing filter, specify that formatting and signaling of target information are present.

[0265] b. For NNPFC SEI messages that include an updated neural network post-processing filter, formatting and target information signaling may be present. That is, such signaling may be optional, but if such signaling is absent, it is specified that it be inferred to be the same as that signaled in the message associated with the base filter.

[0266] Example 1

[0267] This embodiment will provide a detailed explanation of the table of contents 1 and 2 of the previously described embodiment. This embodiment can be based on a standard (e.g., VVC) document.

[0268] This disclosure proposes the following updates:

[0269] Neural-network post-filter characteristics SEI

[0270] The following Table 20 is an example of a change to some of the elements of the NNPFC SEI syntax.

[0271]

Table 20

[0272] Next is an example of a change in semantics related to the above example of change.

[0273] The neural-network post-filter characteristics (NNPFC) SEI message can identify a neural network that can be used as a post-processing filter. The use of the post-processing filter specified for a particular filter may be indicated by the neural-network post-filter activation SEI message.

[0274] When a particular SEI message is not the first NNPFC SEI message having a particular nnpfc_id value within the current CLVS in decoding order, the PostProcessingFilter( ) post-processing filter may be obtained by applying the update information defined by that SEI message to the base post-processing filter.

[0275] Here, the update information is not cumulative; each update may be applied to a base post-processing filter, which is a post-processing filter specified by the first NNPFC SEI message currently having a specific nnpfc_id value in the CLVS in the decoding order.

[0276] In the bitstream according to this revised document, nnpfc_reserved_zero_bit_a may have a value of 0. decrypt The decoder may ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0277] nnpfc_tag_uri may include a tag URI for syntax and semantics specified in IETF RFC 4151 that identifies neural network-related information used as an update applied to a format and base post-processing filter or a base post-processing filter having the same nnpfc_id value as identified by nnpfc_uri.

[0278] Here, nnpfc_tag_uri can uniquely identify the format of the neural network data specified by nnrpf_uri, even without the necessary central registration authority.

[0279] If nnpfc_tag_uri is "tag:iso.org,2023:15938-17", it indicates that the neural network data identified by nnpfc_uri conforms to ISO / IEC 15938-17.

[0280] nnpfc_uri may include a URI for syntax and semantics identified by IETF Internet Standard 66 that identifies a neural network used as an update to a base post-processing filter or a base post-processing filter having the same nnpfc_id value.

[0281] If the value of formatting_and_purpose_flag is 1, it may be determined that syntax elements related to the filter's purpose, input formatting, output formatting, and complexity exist. If the value of nnpfc_formatting_and_purpose_flag is 0, it may be determined that syntax related to the filter's purpose, input formatting, output formatting, and complexity does not exist.

[0282] The value of nnpfc_formatting_and_purpose_flag must be 1 if the SEI message is the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order. On the other hand, if the SEI message is not the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the value of nnpfc_formatting_and_purpose_flag must be 0. If the value of nnpfc_formatting_and_purpose_flag is 0, the values ​​of the syntax elements related to the filter's purpose, input formatting, output formatting, and complexity may be inferred from the values ​​of the corresponding syntax elements in the NNPFC SEI message containing the same nnpfc_id neural network post-processing filter.

[0283] Example 2

[0284] This embodiment will provide a detailed explanation of the table of contents 1 and 2 of the previously described embodiment. This embodiment can be based on a standard (e.g., VVC) document.

[0285] This disclosure proposes the following updates:

[0286] Neural network post-filter characteristics SEI

[0287] An example of a change to some elements of the NNPFC SEI syntax is shown in Table 20 above.

[0288] Next are examples of changes in Table 20 and related semantic changes.

[0289] The neural-network post-filter characteristics (NNPFC) SEI message can identify neural networks that can be used as post-processing filters. The use of a post-processing filter identified for a particular filter may be indicated by a neural-network post-filter activation SEI message.

[0290] If a particular SEI message is not the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the PostProcessingFilter() may be obtained by applying the update information defined by the SEI message to the base postprocessing filter.

[0291] Here, the update information is not cumulative; each update may be applied to a base post-processing filter, which is a post-processing filter specified by the first NNPFC SEI message currently having a specific nnpfc_id value in the CLVS in the decoding order.

[0292] nnpfc_reserved_zero_bit_a must have a value of 0 in the bitstream according to this revised document. decrypt The decoder may ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0293] nnpfc_tag_uri may include a tag URI for syntax and semantics specified in IETF RFC 4151 that identifies neural network-related information used as an update applied to a format and base post-processing filter or a base post-processing filter having the same nnpfc_id value as identified by nnpfc_uri.

[0294] Here, nnpfc_tag_uri can uniquely identify the format of the neural network data specified by nnrpf_uri, even without the necessary central registration authority.

[0295] If nnpfc_tag_uri is "tag:iso.org,2023:15938-17", it indicates that the neural network data identified by nnpfc_uri conforms to ISO / IEC 15938-17.

[0296] nnpfc_uri may include a URI for syntax and semantics identified by IETF Internet Standard 66 that identifies a neural network used as an update to a base post-processing filter or a base post-processing filter having the same nnpfc_id value.

[0297] If the value of formatting_and_purpose_flag is 1, it may be determined that syntax elements related to the filter's purpose, input formatting, output formatting, and complexity exist. If the value of nnpfc_formatting_and_purpose_flag is 0, it may be determined that syntax related to the filter's purpose, input formatting, output formatting, and complexity does not exist.

[0298] The value of nnpfc_formatting_and_purpose_flag must be 1 if the SEI message currently has a specific nnpfc_id value in the CLVS and is an NNPFC SEI message containing a base neural network post-processing filter. On the other hand, if the SEI message currently has a specific nnpfc_id value in the CLVS and is not an NNPFC SEI message containing a base neural network post-processing filter, the value of nnpfc_formatting_and_purpose_flag must be 0. If the value of nnpfc_formatting_and_purpose_flag is 0, the values ​​of the syntax elements related to the filter's purpose, input formatting, output formatting, and complexity may be inferred from the values ​​of the corresponding syntax elements in an NNPFC SEI message containing a neural network post-processing filter with the same nnpfc_id.

[0299] Example 3

[0300] This embodiment will provide a detailed explanation of the table of contents 1 and 2 of the previously described embodiment. This embodiment can be based on a standard (e.g., VVC) document.

[0301] This disclosure proposes the following updates:

[0302] Neural network post-filter characteristics SEI

[0303] An example of a change to some elements of the NNPFC SEI syntax is shown in Table 20 above.

[0304] Next are examples of changes in Table 20 and related semantic changes.

[0305] The neural-network post-filter characteristics (NNPFC) SEI message can identify neural networks that can be used as post-processing filters. The use of a post-processing filter identified for a particular filter may be indicated by a neural-network post-filter activation SEI message.

[0306] If a particular SEI message is not the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the PostProcessingFilter() may be obtained by applying the update information defined by the SEI message to the base postprocessing filter.

[0307] Here, the update information is not cumulative; each update may be applied to a base post-processing filter, which is a post-processing filter specified by the first NNPFC SEI message currently having a specific nnpfc_id value in the CLVS in the decoding order.

[0308] nnpfc_reserved_zero_bit_a must have a value of 0 in the bitstream according to this revised document. decrypt The decoder may ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0309] nnpfc_tag_uri may include a tag URI for syntax and semantics specified in IETF RFC 4151 that identifies neural network-related information used as an update applied to a format and base post-processing filter or a base post-processing filter having the same nnpfc_id value as identified by nnpfc_uri.

[0310] Here, nnpfc_tag_uri can uniquely identify the format of the neural network data specified by nnrpf_uri, even without the necessary central registration authority.

[0311] If nnpfc_tag_uri is "tag:iso.org,2023:15938-17", it indicates that the neural network data identified by nnpfc_uri conforms to ISO / IEC 15938-17.

[0312] nnpfc_uri may include a URI for syntax and semantics identified by IETF Internet Standard 66 that identifies a neural network used as an update to a base post-processing filter or a base post-processing filter having the same nnpfc_id value.

[0313] If the value of formatting_and_purpose_flag is 1, it may be determined that syntax elements related to the filter's purpose, input formatting, output formatting, and complexity exist. If the value of nnpfc_formatting_and_purpose_flag is 0, it may be determined that syntax related to the filter's purpose, input formatting, output formatting, and complexity does not exist.

[0314] The value of nnpfc_formatting_and_purpose_flag must be 1 if the SEI message currently has a specific nnpfc_id value in CLVS and is an NNPFC SEI message containing a base neural network post-processing filter. On the other hand, if the SEI message does not currently have a specific nnpfc_id value in CLVS and is not an NNPFC SEI message containing a base neural network post-processing filter, the value of nnpfc_formatting_and_purpose_flag must be 0. If the value of nnpfc_formatting_and_purpose_flag is 0, the values ​​of the syntax elements related to the filter's purpose, input formatting, output formatting, and complexity may not be known or may be provided by other external means.

[0315] Example 4

[0316] This embodiment will provide a detailed explanation of the table of contents 1 and 2 of the previously described embodiment. This embodiment can be based on a standard (e.g., VVC) document.

[0317] This disclosure proposes the following updates:

[0318] Neural network post-filter characteristics SEI

[0319] An example of a change to some elements of the NNPFC SEI syntax is shown in Table 20 above.

[0320] Next are examples of changes in Table 20 and related semantic changes.

[0321] The neural-network post-filter characteristics (NNPFC) SEI message can identify neural networks that can be used as post-processing filters. The use of a post-processing filter identified for a particular filter may be indicated by a neural-network post-filter activation SEI message.

[0322] If a particular SEI message is not the first NNPFC SEI message in the CLVS that currently has a specific nnpfc_id value in the decoding order, the PostProcessingFilter() may be obtained by applying the update information defined by the SEI message to the base postprocessing filter.

[0323] Here, the update information is not cumulative; each update may be applied to a base post-processing filter, which is a post-processing filter specified by the first NNPFC SEI message currently having a specific nnpfc_id value in the CLVS in the decoding order.

[0324] nnpfc_reserved_zero_bit_a must have a value of 0 in the bitstream according to this revised document. decrypt The decoder may ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0325] nnpfc_tag_uri may include a tag URI for syntax and semantics specified in IETF RFC 4151 that identifies neural network-related information used as an update applied to a format and base post-processing filter or a base post-processing filter having the same nnpfc_id value as identified by nnpfc_uri.

[0326] Here, nnpfc_tag_uri can uniquely identify the format of the neural network data specified by nnrpf_uri, even without the necessary central registration authority.

[0327] If nnpfc_tag_uri is "tag:iso.org,2023:15938-17", it indicates that the neural network data identified by nnpfc_uri conforms to ISO / IEC 15938-17.

[0328] nnpfc_uri may include a URI for syntax and semantics identified by IETF Internet Standard 66 that identifies a neural network used as an update to a base post-processing filter or a base post-processing filter having the same nnpfc_id value.

[0329] If the value of formatting_and_purpose_flag is 1, it may be determined that syntax elements related to the filter's purpose, input formatting, output formatting, and complexity exist. If the value of nnpfc_formatting_and_purpose_flag is 0, it may be determined that syntax related to the filter's purpose, input formatting, output formatting, and complexity does not exist.

[0330] If an SEI message currently has a specific nnpfc_id value in the CLVS and is an NNPFC SEI message containing a base neural network post-processing filter, the value of nnpfc_formatting_and_purpose_flag must be 1. On the other hand, if an SEI message currently has a specific nnpfc_id value in the CLVS and is not an NNPFC SEI message containing a base neural network post-processing filter, the value of nnpfc_formatting_and_purpose_flag may be 0. If the value of nnpfc_formatting_and_purpose_flag is 0, the values ​​of the syntax elements related to the filter's purpose, input formatting, output formatting, and complexity may be inferred from the values ​​of the corresponding syntax elements in NNPFC SEI messages with the same nnpfc_id that precede the SEI message in the decoding order.

[0331] The following describes video encoding and video decoding methods according to various embodiments of the present application. The video encoding method in Figure 5 may be performed by the video encoding device 100, and the video decoding method in Figure 6 may be performed by the video decoding device 200. Furthermore, the video encoding and decoding methods in Figures 5 and 6 can be based on the embodiments described above.

[0332] Referring to Figure 5, at least one neural network that can be used as a post-processing filter may be determined, and information about the determined neural network may be encoded as at least one NNPFC SEI message (S510).

[0333] It may be determined whether or not the target neural network post-processing filter applicable to the picture is activated, and information regarding the determined target neural network post-processing filter may be encoded as an NNPFA SEI message (S520). The S520 process for determining whether or not the target neural network post-processing filter is activated may include a process for determining the target neural network post-processing filter, a process for determining whether or not to cancel the persistence of the target neural network post-processing filter, and a process for determining whether or not the target neural network post-processing filter has persistence.

[0334] Post-processing filter coefficients or correlation information for the design of the post-processing filter may be encoded as a post-filter hint SEI message (S530). NNPFC SEI messages, NNPFA SEI messages, and / or post-filter hint SEI messages may be included in the SEI message for the neural network post-filter (NNFP).

[0335] The target neural network post-processing filter may be determined or specified by various embodiments of the present invention when the SEI message to the NNPF is currently applied to the picture in the video decoding device.

[0336] For example, when an NNPFC SEI message exists, the information that can be present in that message may be determined based on whether or not it contains the NNPFC SEI base network post-processing filter. The information present in an NNPFC SEI message may be determined based on whether or not it has the same value as nnpfc_id. In this case, the NNPFC SEI message containing the base network post-processing filter may be the first NNPFC SEI message in the decoding order and may currently have a specific nnpfc_id value in CLVS. Furthermore, the information that may be included in an NNPFC SEI message may include at least one of the following: the purpose of the filter, input formatting, output formatting (collectively referred to as formatting information), and complexity information. Also, for example, specific information (e.g., formatting information or purpose information) may be encoded and signaled only if the NNPFC SEI message contains the base network post-processing filter. On the other hand, if an NNPFC SEI message includes information for updating the neural network post-processing filter, i.e., an updated neural network post-processing filter, then the formatting and target information are not encoded and are treated as the same as specific information (e.g., formatting information or target information) included in the NNPFC SEI message containing the base neural network post-processing filter. decrypt It may be inferred by the processor or encoded in a specific way so that it is inferred as the same thing. Another example is when specific information (e.g., formatting information or target information) does not exist. decryptIt does not need to be communicated to the processor or other devices. That is, it does not need to be explicitly encoded and may be provided by external means. For example, the absence of specific information may include cases where information indicating the existence or non-existence of specific information (e.g., nnpfc_formatting_and_purpose_flag) is determined to a specific value (e.g., 0). Another example is when an NNPFC SEI message includes a base neural network post-processing filter, in which case specific information (e.g., formatting information or purpose information) may always be signaled, while in other cases (e.g., when an NNPFC SEI message includes information for updating the neural network post-processing filter), it may not be encoded and may be inferred to be the same as the information included in the NNPFC SEI message including the base neural network post-processing filter, or may be encoded in such a way that it can be inferred to be the same. For example, if information indicating the presence or absence of specific information (e.g., nnpfc_formatting_and_purpose_flag) is a specific value (e.g., 0), the specific information may precede the SEI message in the decoding order and not be encoded with the corresponding syntax element in an NNPFC SEI message having the same nnpfc_id value, but may be inferred to be the same value, or encoded in such a way that it is inferred to be the same value.

[0337] Referring to Figure 6, SEI messages for the NNPF currently applied to the picture may be obtained from the bitstream. SEI messages for the NNPF may include NNPFC SEI messages, NNPFA SEI messages, and / or post-filter hint SEI messages.

[0338] When an SEI message for an NNPF is currently applied to a picture, at least one neural network available as a post-processing filter may be determined based on at least one NNPFC SEI message included in the SEI message for the NNPF (S610).

[0339] Based on at least one NNPFA SEI message obtained from the bitstream, it may be determined whether or not the target neural network post-processing filter currently applicable to the picture is activated (S620). The S620 process for determining whether or not the target neural network post-processing filter is activated may include a process for determining the target neural network post-processing filter, a process for determining whether or not to cancel the persistence of the target neural network post-processing filter, and a process for determining whether or not the target neural network post-processing filter has persistence.

[0340] If the target neural network post-processing filter is activated, the target neural network post-processing filter may be applied to the current picture (S630).

[0341] Various embodiments of this application may be used to determine or specify the target neural network post-processing filter.

[0342] For example, when an NNPFC SEI message exists, the information that can be present in that message may be determined based on whether or not it includes the NNPFC SEI base network post-processing filter. That is, the information present in an NNPFC SEI message may be determined based on whether or not it has the same value as nnpfc_id. In this case, the NNPFC SEI message that includes the base network post-processing filter may be the first NNPFC SEI message in the decoding order and may currently have a specific nnpfc_id value in CLVS. Furthermore, the information that may be included in an NNPFC SEI message may include at least one of the following: the purpose of the filter, input formatting, output formatting (collectively referred to as formatting information), and complexity information. Also, for example, specific information (e.g., formatting information or purpose information) may be signaled only if the NNPFC SEI message includes the base network post-processing filter. On the other hand, if an NNPFC SEI message includes information for updating the neural network post-processing filter, i.e., an updated neural network post-processing filter, then the formatting and purpose information may be inferred to be the same as the specific information (e.g., formatting information or purpose information) included in the NNPFC SEI message containing the base neural network post-processing filter. As another example, if the specific information (e.g., formatting information or purpose information) is not present, then such information is not disclosed, does not need to be decoded, and may be provided by external means. For example, the absence of specific information may include cases where the information indicating the presence or absence of specific information (e.g., nnpfc_formatting_and_purpose_flag) is a specific value (e.g., 0).Furthermore, as another example, if an NNPFC SEI message includes a base neural network post-processing filter, specific information (e.g., formatting information or purpose information) may always be signaled, and in other cases (e.g., if an NNPFC SEI message includes information for updating the neural network post-processing filter), it may be inferred to be the same as the information included in the NNPFC SEI message that includes the base neural network post-processing filter. For example, if information indicating the presence or absence of specific information (e.g., nnpfc_formatting_and_purpose_flag) is a specific value (e.g., 0), the specific information may be inferred to be the same value as the corresponding syntax element in an NNPFC SEI message that precedes the SEI message in the decoding order and has the same nnpfc_id value.

[0343] According to this invention, the meaning of NNPFC SEI messages can be clearly defined, thereby improving coding efficiency.

[0344] Figure 7 illustrates a content streaming system to which the embodiments of this disclosure can be applied.

[0345] As shown in Figure 7, a content streaming system to which an embodiment of the present disclosure is applied may broadly include an encoding server, a streaming server, a web server, media storage, user equipment, and multimedia input devices.

[0346] The encoding server is responsible for compressing content input from multimedia input devices such as smartphones, cameras, and camcorders into digital data to generate a bitstream, and transmitting this bitstream to the streaming server. As another example, if a multimedia input device such as a smartphone, camera, or camcorder directly generates the bitstream, the encoding server may be omitted.

[0347] The bitstream may be generated by a video encoding method and / or video encoding apparatus to which an embodiment of the present disclosure is applied, and the streaming server may temporarily store the bitstream in the process of transmitting or receiving the bitstream.

[0348] The streaming server transmits multimedia data to user devices based on user requests via a web server, and the web server can act as an intermediary to inform users of available services. When a user requests a desired service from the web server, the web server transmits it to the streaming server, and the streaming server can transmit multimedia data to the user. In this case, the content streaming system may include a separate control server, in which case the control server can play a role in controlling commands and responses between the devices within the content streaming system.

[0349] The streaming server can receive content from media storage and / or encoding servers. For example, when receiving content from the encoding server, the content can be received in real time. In this case, in order to provide a smooth streaming service, the streaming server can store the bitstream for a certain period of time.

[0350] Examples of user devices include mobile phones, smartphones, laptop computers, digital broadcasting terminals, PDAs (personal digital assistants), PMPs (portable multimedia players), navigation systems, slate PCs, tablet PCs, ultrabooks, wearable devices (such as smartwatches, smart glasses, and HMDs), digital TVs, desktop computers, and digital signage.

[0351] Each server within the aforementioned content streaming system may be operated as a distributed server, in which case the data received by each server may be processed in a distributed manner.

[0352] The scope of this disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that enable the operation of various embodiments to be performed on a device or computer, and non-transitory computer-readable medium on which such software or instructions are stored and executable on a device or computer.

[0353] [Industrial applicability] The embodiments described herein can be used for encoding / decoding video.

[0354] [Claims when filing an international application] [Claim 1] A video decoding method performed by a video decoding device, This is the stage where you obtain SEI (supplemental enhancement information) messages for the NNPF (neural-network post-filter) currently applied to the picture; A step in which, based on the fact that the SEI message for the NNPF is applied to the current picture, at least one neural network available as a post-processing filter is determined based on at least one NNPFC (neural-network post-filter characteristics) SEI message included in the SEI message for the NNPF; The step of determining whether the target neural network post-processing filter applicable to the current picture is activated based on at least one NNPFA (neural-network post-filter activation) SEI message included in the SEI message for the NNPF; A video decoding method in which formatting information and objective information included in the NNPFC SEI message are determined based on the fact that the NNPFC SEI message includes a base neural network post-processing filter. [Claim 2] A video encoding method performed by a video encoding device, The step of encoding at least one neural network available as a post-processing filter as at least one NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message; The process includes the step of encoding whether or not the target neural network post-processing filter applicable to the picture is activated as at least one NNPFA (neural-network post-filter activation) SEI message; A video encoding method in which, in the video decoding device, the formatting information and target information included in the NNPFC SEI message are determined based on the fact that the NNPFC SEI message includes a base neural network post-filter, on the basis that the SEI message for the NNPF (neural-network post-filter) is currently applied to the picture. [Claim 3] A method for transmitting a bitstream generated by a video encoding method, The aforementioned video encoding method is The step of encoding at least one neural network available as a post-processing filter as at least one NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message; The process includes the step of encoding whether or not the target neural network post-processing filter applicable to the picture is activated as at least one NNPFA (neural-network post-filter activation) SEI message; A method for transmitting a bitstream in a video decoding device, wherein the formatting information and target information included in the NNPFC SEI message are determined based on the fact that the NNPFC SEI message includes a base neural network post-filter, based on the fact that the SEI message for the NNPF (neural-network post-filter) is currently applied to the picture. [Claim 4] A computer-readable recording medium for storing a bitstream generated by a video encoding method, The aforementioned video encoding method is The step of encoding at least one neural network available as a post-processing filter as at least one NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message; The process includes the step of encoding whether or not the target neural network post-processing filter applicable to the picture is activated as at least one NNPFA (neural-network post-filter activation) SEI message; A recording medium in a video decoding device, wherein the formatting information and target information included in the NNPFC SEI message are determined based on the fact that the NNPFC SEI message includes a base neural network post-filter, based on the fact that the SEI message for the NNPF (neural-network post-filter) is currently applied to the picture.

Claims

1. A video decoding method performed by a video decoding device, Currently, we are in the stage of obtaining NNPFC (Neural Network Post-Filter Characteristics) SEI (Supplemental Enhancement Information) messages for the picture; The aforementioned NNPFC SEI message is, (i) NNPF identification information for identifying NNPF (neural-network post-filter), and (ii) Filter property existence information that identifies whether or not syntax elements related to the filter property exist, The steps include: obtaining an NNPFA (neutral-network post-filter activation) SEI message containing target NNPF identification information that indicates the target NNPF; and The process includes: performing post-processing filtering of the current picture using the target NNPF based on the NNPFA SEI message; A video decoding method in which the value of the syntax element is determined based on other NNPFC SEI messages, including base NNPF, based on the fact that the presence information of the filter property in the NNPFC SEI message is equal to 0, which identifies the absence of the syntax element associated with the filter property.

2. A video encoding method performed by a video encoding device, NNPFC (Neural Network Post-Filter Characteristics) SEI (Supplemental Enhancement Information) messages, (i) NNPF identification information for identifying NNPF (neural-network post-filter), and (ii) The step of encoding filter property existence information, which identifies whether or not syntax elements related to the filter property exist; NNPFA (Neural-Network Post-Filter Activation) comprises the step of encoding target NNPF identification information that indicates the target NNPF within the SEI message; A video encoding method in which the value of the syntax element is determined based on other NNPFC SEI messages, including a base NNPF, based on the fact that the presence information of the filter property in the NNPFC SEI message is equal to 0, which indicates that the syntax element associated with the filter property does not exist.

3. A method for transmitting a bitstream, NNPFC (Neural Network Post-Filter Characteristics) SEI (Supplemental Enhancement Information) messages, (i) NNPF identification information for identifying NNPF (neural-network post-filter), and (ii) The step of encoding filter property existence information, which identifies whether or not syntax elements related to the filter property exist; NNPFA (Neural-Network Post-Filter Activation): The step of encoding target NNPF identification information that indicates the target NNPF within the SEI message; and The step of transmitting the bitstream including the NNPFC SEI message and the NNPFA SEI message; A method for transmitting a bitstream, wherein the value of the syntax element is determined based on other NNPFC SEI messages, including a base NNPF, based on the fact that the presence information of the filter property in the NNPFC SEI message is equal to 0, which identifies the absence of the syntax element associated with the filter property.

Images