Image encoding / decoding method, recording medium storing bitstream, and method of transmitting bitstream

Abstract

An image decoding method according to the present disclosure may comprise the steps of: obtaining a neural-network post-filter (NNPF) supplemental enhancement information (SEI) message, the NNPF SEI message including an NNPF characteristics (NNPFC) SEI message and an NNPF activation (NNPFA) SEI message, and determining a neural network that can be used as a post-processing filter on the basis of the NNPFC SEI message; and determining whether to activate a target NNPF applicable to a current picture on the basis of the NNPFA SEI message, wherein, until a picture of a current layer related to an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output after the current picture in an output order, the target NNPF is used to perform post-processing filtering for the current picture and subsequent pictures in the current layer in the output order.

Description

Video encoding / decoding method, recording medium storing bitstream, and method for transmitting bitstream

[0001] The present disclosure relates to a method for encoding / decoding a video, a recording medium storing a bitstream, and a method for transmitting a bitstream, and relates to a method for determining whether to cancel persistence of a neural network post-filter.

[0002] Recently, demand for high-resolution, high-quality images, such as HD (High Definition) and UHD (Ultra High Definition) images, has been increasing across various fields. As image data becomes higher resolution and higher quality, the amount of information transmitted, or bits, increases relative to conventional image data. This increase in information or bits transmitted leads to increased transmission and storage costs.

[0003] Accordingly, a highly efficient image compression technology is required to effectively transmit, store, and play high-resolution, high-quality image information.

[0004] The present disclosure aims to provide a video encoding / decoding method and device with improved encoding / decoding efficiency.

[0005] Additionally, the present disclosure aims to provide a method for clearly distinguishing which NNPF's persistence is to be canceled when there are two or more NNPF activations having the same identification information.

[0006] Additionally, the present disclosure aims to provide a method for preventing simultaneous activation of two or more NNPFs having the same identification information.

[0007] In addition, the present disclosure aims to provide a non-transitory computer-readable recording medium that stores a bitstream generated by an image encoding method according to the present disclosure.

[0008] In addition, the present disclosure aims to provide a method for transmitting a bitstream generated by an image encoding method according to the present disclosure.

[0009] In addition, the present disclosure aims to provide a non-transitory computer-readable recording medium that stores a bitstream received and decoded by an image decoding device according to the present disclosure and used for restoring an image.

[0010] The technical problems to be achieved in the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by a person having ordinary skill in the technical field to which the present disclosure belongs from the description below.

[0011] An image decoding method according to one aspect of the present disclosure is an image decoding method performed by an image decoding device, comprising: a step of obtaining a neural-network post-filter (NNPF) SEI (supplemental enhancement information) message, wherein the NNPF SEI message includes a neural-network post-filter characteristics (NNPFC) SEI message and a neural-network post-filter activation (NNPFA) SEI message, and determining a neural network that can be used as a post-processing filter based on the NNPFC SEI message; And, based on the NNPFA SEI message, a step of determining whether to activate a target NNPF applicable to the current picture, wherein the target NNPF is used to perform post-processing filtering on the current picture and subsequent pictures in the current layer in the output order until a picture of the current layer related to an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output next to the current picture in the output order.

[0012] According to another aspect of the present disclosure, a video encoding method is performed by a video encoding device, and includes: a step of encoding a neural network that can be used as a post-processing filter into a neural-network post-filter characteristics (NNPF) SEI (supplemental enhancement information) message; and a step of encoding whether a target NNPF applicable to a current picture is activated into a neural-network post-filter activation (NNPF) SEI message, wherein the target NNPF is used to perform post-processing filtering on the current picture and subsequent pictures within the current layer in the output order until a picture of the current layer related to an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output next to the current picture in the output order.

[0013] A computer-readable recording medium according to another aspect of the present disclosure can store a bitstream generated by an image encoding method or device of the present disclosure.

[0014] A transmission method according to another aspect of the present disclosure can transmit a bitstream generated by an image encoding method or device of the present disclosure.

[0015] The features briefly summarized above regarding the present disclosure are merely exemplary aspects of the detailed description of the present disclosure that follows and do not limit the scope of the present disclosure.

[0016] According to the present disclosure, a video encoding / decoding method and device with improved encoding / decoding efficiency can be provided.

[0017] Additionally, according to the present disclosure, when there are two or more NNPF activations having the same identification information, it is possible to clearly identify the NNPF whose persistence is to be canceled.

[0018] Additionally, according to the present disclosure, it is possible to prevent two or more NNPFs having the same identification information from being activated simultaneously.

[0019] In addition, according to the present disclosure, a non-transitory computer-readable recording medium for storing a bitstream generated by an image encoding method according to the present disclosure can be provided.

[0020] In addition, according to the present disclosure, a non-transitory computer-readable recording medium can be provided that stores a bitstream received and decoded by an image decoding device according to the present disclosure and used for restoring an image.

[0021] Additionally, according to the present disclosure, a method for transmitting a bitstream generated by an image encoding method can be provided.

[0022] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from the description below.

[0023] FIG. 1 is a diagram schematically illustrating a video coding system to which an embodiment according to the present disclosure can be applied.

[0024] FIG. 2 is a schematic diagram of an image encoding device to which an embodiment according to the present disclosure can be applied.

[0025] FIG. 3 is a schematic diagram illustrating an image decoding device to which an embodiment according to the present disclosure can be applied.

[0026] Figure 4 illustrates an example of a hierarchical structure for coded video / images.

[0027] Figure 5 is a diagram for explaining an interleaved method for deriving a luma channel.

[0028] Figure 6 is a drawing for explaining an image encoding method of an image encoding device.

[0029] Figure 7 is a drawing for explaining an image decoding method of an image decoding device.

[0030] FIG. 8 is a diagram for explaining an image decoding method for an embodiment of determining whether a target NNPF is activated.

[0031] Figures 9 to 11 are drawings for explaining various embodiments of whether to cancel the persistence of the target NNPF.

[0032] FIG. 12 is a diagram exemplifying a content streaming system to which an embodiment according to the present disclosure can be applied.

[0033] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein.

[0034] In describing embodiments of the present disclosure, detailed descriptions of known configurations or functions will be omitted if they are deemed to obscure the gist of the present disclosure. Furthermore, portions unrelated to the description of the present disclosure in the drawings have been omitted, and similar portions have been designated with similar reference numerals.

[0035] In the present disclosure, when a component is said to be "connected," "coupled," or "connected" to another component, this may include not only a direct connection, but also an indirect connection in which another component exists in between. Furthermore, when a component is said to "include" or "have" another component, unless otherwise specifically stated, this does not exclude the other component, but rather implies that the other component may be included.

[0036] 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 components unless specifically stated otherwise. Accordingly, 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.

[0037] In this disclosure, distinct components are used to clearly illustrate their respective characteristics, and do not necessarily imply that the components are separated. That is, multiple components may be integrated into a single hardware or software unit, or a single component may be distributed into multiple hardware or software units. Therefore, even if not specifically mentioned, such integrated or distributed embodiments are also included within the scope of this disclosure.

[0038] In the present disclosure, the components described in various embodiments are not necessarily essential components, and some may be optional components. Therefore, embodiments comprising a subset of the components described in one embodiment are also within the scope of the present disclosure. Furthermore, embodiments including other components in addition to the components described in various embodiments are also within the scope of the present disclosure.

[0039] The present disclosure relates to encoding and decoding of video. For example, the methods and embodiments disclosed in this document can be applied to methods disclosed in the versatile video coding (VVC) standard, the essential video coding (EVC) standard, the AOMedia Video 1 (AV1) standard, the second generation of audio video coding standard (AVS2), or the next generation of video / image coding standards (e.g., H.267 or H.268).

[0040] The present disclosure presents various embodiments of video / image coding, and unless otherwise stated, the embodiments may be performed in combination with each other.

[0041] Terms used in this disclosure may have their usual meanings commonly used in the technical field to which this disclosure belongs, unless newly defined in this disclosure.

[0042] In the present disclosure, a "picture" generally means a unit representing one image of a specific time period, and a slice / tile is a coding unit constituting a part of a picture, and one picture may be composed of one or more slices / tiles. In addition, a slice / tile may include one or more CTUs (coding tree units). One picture may be composed of one or more tile groups. One tile group may include one or more tiles. A brick may represent a rectangular area of ​​CTU rows of tiles in a picture. In this document, tile group and slice may be used interchangeably. For example, in this document, a tile group / tile group header may be called a slice / slice header.

[0043] In the present disclosure, "pixel" or "pel" may refer to the smallest unit that constitutes a picture (or image). Additionally, "sample" may be used as a term corresponding to a pixel. A sample may generally represent a pixel or a pixel value, and may represent only a pixel / pixel value of a luma component or only a pixel / pixel value of a chroma component.

[0044] In the present disclosure, a "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 related to the region. One unit may include one luma block and two chroma (e.g., cb, cr) blocks. In some cases, the term "unit" may be used interchangeably with terms such as "sample array," "block," or "area." In general, an M×N block may include a set (or array) of samples (or sample array) or transform coefficients consisting of M columns and N rows.

[0045] In the present disclosure, the "current block" may mean one of the following: a "current coding block," a "current coding unit," a "block to be encoded," a "block to be decoded," or a "block to be processed." When prediction is performed, the "current block" may mean a "current prediction block" or a "block to be predicted." When transformation (inverse transformation) / quantization (inverse quantization) is performed, the "current block" may mean a "current transformation block" or a "block to be transformed." When filtering is performed, the "current block" may mean a "block to be filtered."

[0046] In the present disclosure, a "current block" may mean a block that includes both a luma component block and a chroma component block, or a "luma block of the current block," unless explicitly described as a chroma block. The luma component block of the current block may be explicitly expressed by including an explicit description of the luma component block, such as "luma block" or "current luma block." Additionally, the chroma component block of the current block may be explicitly expressed by including an explicit description of the chroma component block, such as "chroma block" or "current chroma block."

[0047] In this disclosure, " / " and "," can be interpreted as "and / or". For example, "A / B" and "A, B" can be interpreted as "A and / or B". Additionally, "A / B / C" and "A, B, C" can mean "at least one of A, B, and / or C."

[0048] 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, "or" in this disclosure may mean "additionally or alternatively."

[0049] Video Coding System Overview

[0050] FIG. 1 is a diagram schematically illustrating a video coding system to which an embodiment according to the present disclosure can be applied.

[0051] A video coding system according to one embodiment may include an encoding device (10) and a decoding device (20). The encoding device (10) may transmit encoded video and / or image information or data to the decoding device (20) in the form of a file or streaming through a digital storage medium or a network.

[0052] 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 reception unit (21), a decoding unit (22), and a rendering unit (23). The encoding unit (12) may be referred to as a video / image encoding unit, and the decoding unit (22) may be referred to as a video / image decoding unit. The transmission unit (13) may be included in the encoding unit (12). The reception 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 configured as a separate device or an external component.

[0053] The video source generation unit (11) can obtain video / images through a process of capturing, synthesizing, or generating video / images. The video source generation unit (11) can include a video / image capture device and / or a video / image generation device. The video / image capture device can include, for example, one or more cameras, a video / image archive including previously captured video / images, etc. The video / image generation device can include, for example, a computer, a tablet, a smartphone, etc., and can (electronically) generate video / images. For example, a virtual video / image can be generated through a computer, etc., in which case the video / image capture process can be replaced with a process of generating related data.

[0054] The encoding unit (12) can encode input video / images. The encoding unit (12) can perform a series of procedures such as prediction, transformation, and quantization to improve compression and encoding efficiency. The encoding unit (12) can output encoded data (encoded video / image information) in the form of a bitstream.

[0055] The transmission unit (13) can obtain encoded video / image information or data output in the form of a bitstream, and transmit it to the reception unit (21) of the decoding device (20) or another external object through a digital storage medium or a network in the form of a file or streaming. The digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, SSD, etc. The transmission unit (13) may include an element for generating a media file through a predetermined file format, and may include an element for transmission through a broadcasting / communication network. The transmission unit (13) may be provided as a separate transmission device from the encoding device (12), and in this case, the transmission device may include at least one processor for obtaining encoded video / image information or data output in the form of a bitstream, and a transmission unit for transmitting it in the form of a file or streaming. The reception unit (21) can extract / receive the bitstream from the storage medium or network and transmit it to the decoding unit (22).

[0056] The decoding unit (22) can decode video / image by performing a series of procedures such as inverse quantization, inverse transformation, and prediction corresponding to the operation of the encoding unit (12).

[0057] The rendering unit (23) can render the decrypted video / image. The rendered video / image can be displayed through the display unit.

[0058] Overview of the video encoding device

[0059] FIG. 2 is a schematic diagram illustrating an image encoding device to which an embodiment according to the present disclosure can be applied.

[0060] As illustrated in FIG. 2, the image encoding device (200) may be configured to include an image partitioner (210), a prediction unit (predictor) 220, a residual processor (residual processor) 230, an entropy encoder (entropy encoder) 240, an adder (adder) 250, a filter (filter) 260, and a memory (memory) 270. The prediction unit (220) may include an inter prediction unit (221) and an intra prediction unit (222). The residual processor (230) may include a transformer (transformer) 232, a quantizer (quantizer) 233, a dequantizer (dequantizer) 234, and an inverse transformer (inverse transformer) 235. The residual processing unit (230) may further include a subtractor (231). The addition unit (250) may be called a reconstructor or a recontructed block generator. The image segmentation unit (210), the prediction unit (220), the residual processing unit (230), the entropy encoding unit (240), the addition unit (250), and the filtering unit (260) described above may be configured by one or more hardware components (e.g., an encoder chipset or a processor) depending on the embodiment. In addition, the memory (270) may include a DPB (Decoded Picture Buffer) and may be configured by a digital storage medium. The hardware component may further include the memory (270) as an internal / external component.

[0061] The image segmentation unit (210) can segment an input image (or picture, frame) input to the image encoding device (200) into one or more processing units. For example, the processing unit may be called a coding unit (CU). The coding unit may be obtained by recursively segmenting a coding tree unit (CTU) or a largest coding unit (LCU) according to a QT / BT / TT (Quad-tree / binary-tree / ternary-tree) structure. For example, one coding unit may be segmented into a plurality of coding units of deeper depth based on a quad-tree structure, a binary-tree structure, and / or a ternary-tree structure. For segmenting the coding unit, the quad-tree structure may be applied first, and the binary-tree structure and / or the ternary-tree structure may be applied later. The coding procedure according to the present disclosure may be performed based on the final coding unit that is no longer segmented. In this case, based on coding efficiency according to image characteristics, etc., the maximum coding unit may be used as the final coding unit, or, if necessary, the maximum coding unit may be recursively divided into coding units of lower depths, and the coding unit of the optimal size 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 each be divided or partitioned from the final coding unit.The above prediction unit may be a unit of sample prediction, and the above transformation unit may be a unit for deriving a transformation coefficient and / or a unit for deriving a residual signal from a transformation coefficient.

[0062] The video encoding device (200) can generate a residual signal (residual block, residual sample array) by subtracting a prediction signal (predicted block, prediction sample array) output from an inter prediction unit (221) or an intra prediction unit (222) from an input video signal (original block, original sample array), and the generated residual signal is transmitted to a conversion unit (232). In this case, as illustrated, a unit that subtracts a prediction signal (prediction block, prediction sample array) from an input video signal (original block, original sample array) within the video encoding device (200) may be called a subtraction unit (231). The prediction unit (220) can perform prediction on a block to be processed (current block) and generate a predicted block including prediction samples for the current block. The prediction unit (220) can determine whether intra prediction or inter prediction is applied on a current block or CU basis. The prediction unit (220) can generate various information regarding the prediction of the current block and transmit it to the entropy encoding unit (240). The information regarding the prediction can be encoded in the entropy encoding unit (240) and output in the form of a bitstream.

[0063] The intra prediction unit (222) can predict the current block by referring to samples within the current picture. The referenced samples may be located in the neighborhood of the current block or may be located away from it, depending on the intra prediction mode and / or intra prediction technique. The intra prediction modes 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 degree of detail in the prediction direction. However, this is merely an example, and a greater or lesser number of directional prediction modes may be used depending on the settings. The intra prediction unit (222) may also determine the prediction mode applied to the current block by using the prediction mode applied to the neighboring blocks.

[0064] The inter prediction unit (221) can derive a predicted block for the current block based on a reference block (reference sample array) specified by a motion vector on a reference picture. At this time, in order to reduce the amount of motion information transmitted in the inter prediction mode, the motion information can be predicted in units of blocks, sub-blocks, or samples based on the correlation of the motion information between the neighboring blocks and the current block. The motion information can include a motion vector and a reference picture index. The motion information can further include information on the inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.). In the case of inter prediction, the neighboring block can include a spatial neighboring block existing in the current picture and a temporal neighboring block existing in the reference picture. The reference picture including the reference block and the reference picture including the temporal neighboring block may be the same or different. The temporal neighboring block may be called a collocated reference block, a collocated CU (colCU), etc. A reference picture including the above temporal neighboring blocks may be called a collocated picture (colPic). For example, the inter prediction unit (221) may construct a motion information candidate list based on neighboring blocks and generate information indicating which candidate is used to derive the motion vector and / or reference picture index of the current block. Inter prediction may be performed based on various prediction modes, and for example, in the case of skip mode and merge mode, the inter prediction unit (221) may use the motion information of neighboring blocks as the motion information of the current block. In the case of skip mode, unlike the merge mode, a residual signal may not be transmitted.In the motion vector prediction (MVP) mode, the motion vector of the current block can be signaled by using the motion vector of the surrounding blocks as the motion vector predictor and encoding the motion vector difference and an indicator for the motion vector predictor. The motion vector difference can mean the difference between the motion vector of the current block and the motion vector predictor.

[0065] The prediction unit (220) can generate a prediction signal based on various prediction methods and / or prediction techniques described below. For example, the prediction unit (220) can apply intra prediction or inter prediction to predict the current block, and can also apply intra prediction and inter prediction simultaneously. A prediction method that simultaneously applies intra prediction and inter prediction to predict the current block may be called combined inter and intra prediction (CIIP). In addition, the prediction unit (220) may perform intra block copy (IBC) to predict the current block. Intra block copy may be used for content image / video coding such as games, such as screen content coding (SCC). IBC is a method of predicting the current block using a previously restored reference block within the current picture located at a predetermined distance from the current block. When IBC is applied, the location of the reference block within 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 can be performed similarly to inter prediction in that it derives reference blocks within the current picture. That is, IBC can utilize at least one of the inter prediction techniques described in the present disclosure.

[0066] The prediction signal generated through the prediction unit (220) can be used to generate a restoration signal or a residual signal. The subtraction unit (231) can generate a residual signal (residual block, residual sample array) by subtracting the prediction signal (predicted block, predicted sample array) output from the prediction unit (220) from the input image signal (original block, original sample array). The generated residual signal can be transmitted to the conversion unit (232).

[0067] The transform unit (232) can apply a transform technique to the residual signal to generate transform coefficients. For example, the transform technique can include at least one of a Discrete Cosine Transform (DCT), a Discrete Sine Transform (DST), a Karhunen-Loeve Transform (KLT), a Graph-Based Transform (GBT), or a Conditionally Non-linear Transform (CNT). Here, GBT refers to a transform obtained from a graph when the relationship information between pixels is expressed as a graph. CNT refers to a transform obtained based on generating a prediction signal using all previously reconstructed pixels. The transform process can be applied to a pixel block having a square equal size, or can be applied to a block of a non-square variable size.

[0068] The quantization unit (233) can quantize the transform coefficients and transmit them to the entropy encoding unit (240). The entropy encoding unit (240) can encode the quantized signal (information about the quantized transform coefficients) and output it as a bitstream. The information about the quantized transform coefficients can be called residual information. The quantization unit (233) can rearrange the quantized transform coefficients in a block form into a one-dimensional vector form based on the coefficient scan order, and can also generate information about the quantized transform coefficients based on the quantized transform coefficients in the one-dimensional vector form.

[0069] The entropy encoding unit (240) can perform various encoding methods such as, for example, exponential Golomb, context-adaptive variable length coding (CAVLC), context-adaptive binary arithmetic coding (CABAC), etc. The entropy encoding unit (190) can also encode, together or separately, information necessary for video / image restoration (e.g., values ​​of syntax elements, etc.) in addition to quantized transform coefficients. The encoded information (e.g., encoded video / image information) can be transmitted or stored in the form of a bitstream in the form of a network abstraction layer (NAL) unit. The video / image information may further include information on 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). In addition, the video / image information may further include general constraint information. The signaled information, transmitted information, and / or syntax elements mentioned in the present disclosure may be included in video / image information. The video / image information may be encoded through the encoding procedure described above and included in the bitstream.

[0070] The above bitstream may be transmitted via a network or stored in a digital storage medium. Here, the network may include a broadcasting network and / or a communication network, and the digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, SSD, etc. A transmission unit (not shown) for transmitting the signal output from the entropy encoding unit (240) and / or a storage unit (not shown) for storing the signal may be provided as an internal / external element of the video encoding device (200), or the transmission unit may be provided as a component of the entropy encoding unit (240).

[0071] The quantized transform coefficients output from the quantization unit (233) can be used to generate a residual signal. For example, by applying inverse quantization and inverse transformation to the quantized transform coefficients through the inverse quantization unit (234) and inverse transformation unit (235), a residual signal (residual block or residual samples) can be restored.

[0072] The addition unit (250) can generate a reconstructed signal (reconstructed picture, reconstructed block, reconstructed sample array) by adding the reconstructed residual signal to the prediction signal output from the inter prediction unit (221) or the intra prediction unit (222). When there is no residual for the block to be processed, such as when skip mode is applied, the predicted block can be used as the reconstructed block. The addition unit (250) can be called a reconstructed unit or a reconstructed block generation unit. The generated reconstructed signal can be used for intra prediction of the next block to be processed within the current picture, and can also be used for inter prediction of the next picture after filtering as described below.

[0073] The filtering unit (260) can improve subjective / objective picture quality by applying filtering to the restoration signal. For example, the filtering unit (260) can apply various filtering methods to the restoration picture to generate a modified restoration picture, and store the modified restoration picture in the memory (270), specifically, the DPB of the memory (170). The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, etc. The filtering unit (260) can generate various information regarding filtering and transmit the information to the entropy encoding unit (240), as described later in the description of each filtering method. The information regarding filtering may be encoded by the entropy encoding unit (240) and output in the form of a bitstream.

[0074] The modified restored picture transmitted to the memory (270) can be used as a reference picture in the inter prediction unit (221). Through this, when inter prediction is applied, the image encoding device (200) can avoid prediction mismatch between the image encoding device (200) and the image decoding device, and can also improve encoding efficiency.

[0075] The DPB in the memory (270) can store a modified reconstructed picture to be used as a reference picture in the inter prediction unit (221). The memory (270) can store motion information of a block from which motion information in the current picture is derived (or encoded) and / or motion information of blocks in a picture that has already been reconstructed. The stored motion information can be transferred to the inter prediction unit (221) to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory (270) can store reconstructed samples of reconstructed blocks in the current picture and transfer them to the intra prediction unit (222).

[0076] Video Decoding Device Overview

[0077] FIG. 3 is a schematic diagram illustrating an image decoding device to which an embodiment according to the present disclosure can be applied.

[0078] As illustrated in FIG. 3, the image decoding device (300) may be configured to include an entropy decoder (310), a residual processor (320), a predictor (330), an adder (340), a filter (350), and a memory (360). The predictor (330) may include an inter-prediction unit (332) and an intra-prediction unit (331). The residual processor (320) may include a dequantizer (321) and an inverse transformer (321). The entropy decoding unit (310), residual processing unit (320), prediction unit (330), addition unit (340), and filtering unit (350) described above may be configured by one hardware component (e.g., decoder chipset or processor) according to an embodiment. In addition, the memory (360) may include a decoded picture buffer (DPB) and may be configured by a digital storage medium. The hardware component may further include the memory (360) as an internal / external component. When a bitstream including video / image information is input, the image decoding device (300) may perform a process corresponding to the process performed in the image encoding device (200) of FIG. 2 to restore the image. For example, the image decoding device (300) may perform decoding using a processing unit applied in the image encoding device (200). Therefore, the processing unit for decoding may be, for example, a coding unit. The coding unit may be a coding tree unit or may be obtained by dividing the maximum coding unit into quad tree structures, binary tree structures, and / or ternary tree structures. Then, the restored video signal decoded and output by the video decoding device (300) may be reproduced by a reproduction device (not shown).

[0079] The video decoding device (300) can receive a signal output from the video encoding device (200) of FIG. 2 in the form of a bitstream. The received signal can be decoded through the entropy decoding unit (310). For example, the entropy decoding unit (310) can parse the bitstream to derive information (e.g., video / image information) necessary for image restoration (or picture restoration). The video / image information may further include information on 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). In addition, the video / image information may further include general constraint information. The video decoding device (300) can additionally use the information on the parameter set and / or the general constraint information to decode the image. The signaling information, received information, and / or syntax elements mentioned in the present disclosure can be obtained from the bitstream by being decoded through the decoding procedure. For example, the entropy decoding unit (310) 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 required for image restoration and the quantized values ​​of transform coefficients for residuals. More specifically, the CABAC entropy decoding method receives a bin corresponding to each syntax element in the bitstream, determines a context model using information of the syntax element to be decoded and the decoding information of the surrounding block and the decoding target block or the information of the symbol / bin decoded in the previous step, and predicts the occurrence probability of the bin according to the determined context model to perform arithmetic decoding of the bin to generate a symbol corresponding to the value of each syntax element.At this time, the CABAC entropy decoding method can update the context model using the information of the decoded symbol / bin for the context model of the next symbol / bin after determining the context model. Information regarding prediction among the information decoded by the entropy decoding unit (310) is provided to the prediction unit (330) (inter-prediction unit (332) and intra-prediction unit (331)), and residual values ​​on which entropy decoding is performed by the entropy decoding unit (310), i.e., quantized transform coefficients and related parameter information, can be input to the residual processing unit (320). In addition, information regarding filtering among the information decoded by the entropy decoding unit (310) can be provided to the filtering unit (350). Meanwhile, a receiving unit (not shown) that receives a signal output from an image encoding device (200) may be additionally provided as an internal / external element of an image decoding device (300), or the receiving unit may be provided as a component of an entropy decoding unit (310).

[0080] Meanwhile, the video decoding device (300) according to the present disclosure may be referred to as a video / video / picture decoding device. The video decoding device (300) may include an information decoder (video / video / picture information decoder) and / or a sample decoder (video / video / picture sample decoder). The information decoder may include an entropy decoding unit (310), and the sample decoder may include at least one of an inverse quantization unit (321), an inverse transformation unit (322), an addition unit (340), a filtering unit (350), a memory (360), an inter prediction unit (332), and an intra prediction unit (331).

[0081] The inverse quantization unit (321) can inverse quantize the quantized transform coefficients and output the transform coefficients. The inverse quantization unit (321) can rearrange the quantized transform coefficients into a two-dimensional block form. In this case, the rearrangement can be performed based on the coefficient scanning order performed in the image encoding device (200). The inverse quantization unit (321) can perform inverse quantization on the quantized transform coefficients using quantization parameters (e.g., quantization step size information) and obtain transform coefficients.

[0082] In the inverse transform unit (322), the transform coefficients can be inversely transformed to obtain a residual signal (residual block, residual sample array).

[0083] The prediction unit (330) can perform a prediction on the current block and generate a predicted block including prediction samples for the current block. The prediction unit (330) can determine whether intra-prediction or inter-prediction is applied to the current block based on the information regarding the prediction output from the entropy decoding unit (310), and can determine a specific intra / inter-prediction mode (prediction technique).

[0084] The fact that the prediction unit (330) can generate a prediction signal based on various prediction methods (techniques) described below is the same as that mentioned in the description of the prediction unit (220) of the image encoding device (200).

[0085] The intra prediction unit (331) can predict the current block by referring to samples within the current picture. The description of the intra prediction unit (222) can be equally applied to the intra prediction unit (331). The referenced samples may be located in the neighborhood of the current block or may be located away from it, depending on the prediction mode. In intra prediction, the prediction modes may include multiple non-directional modes and multiple directional modes. The intra prediction unit (331) can also determine the prediction mode applied to the current block by using the prediction mode applied to the neighboring blocks.

[0086] The inter prediction unit (332) can derive a predicted block for the current block based on a reference block (reference sample array) specified by a motion vector on a reference picture. At this time, in order to reduce the amount of motion information transmitted in the inter prediction mode, the motion information can be predicted in units of blocks, sub-blocks, or samples based on the correlation of the motion information between the neighboring blocks and the current block. The motion information can include a motion vector and a reference picture index. The motion information can further include information on the inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.). In the case of inter prediction, the neighboring blocks can include spatial neighboring blocks existing in the current picture and temporal neighboring blocks existing in the reference picture. For example, the inter prediction unit (332) can construct a motion information candidate list based on the neighboring blocks, and derive the motion vector and / or reference picture index of the current block based on the received candidate selection information. Inter prediction can be performed based on various prediction modes (techniques), and the information about the prediction can include information indicating the mode (technique) of inter prediction for the current block.

[0087] The addition unit (340) can generate a restoration signal (restored picture, restoration block, restoration sample array) by adding the acquired residual signal to the prediction signal (predicted block, prediction sample array) output from the prediction unit (330) (including the inter prediction unit (332) and / or the intra prediction unit (331)). When there is no residual for the block to be processed, such as when the skip mode is applied, the predicted block can be used as the restoration block. The description of the addition unit (250) can be equally applied to the addition unit (340). The addition unit (340) can be called a restoration unit or a restoration block generation unit. The generated restoration signal can be used for intra prediction of the next block to be processed within the current picture, and can also be used for inter prediction of the next picture after going through filtering as described below.

[0088] The filtering unit (350) can improve subjective / objective image quality by applying filtering to the restored signal. For example, the filtering unit (350) can apply various filtering methods to the restored picture to generate a modified restored picture, and store the modified restored picture in the memory (360), specifically, in the DPB of the memory (360). The various filtering methods can include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, etc.

[0089] The (modified) reconstructed picture stored in the DPB of the memory (360) can be used as a reference picture in the inter prediction unit (332). The memory (360) can store motion information of a block from which motion information is derived (or decoded) within the current picture and / or motion information of blocks within a picture that has already been reconstructed. The stored motion information can be transmitted to the inter prediction unit (332) to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory (360) can store reconstructed samples of reconstructed blocks within the current picture and transmit them to the intra prediction unit (331).

[0090] In this specification, the embodiments described in the filtering unit (260), the inter prediction unit (221), and the intra prediction unit (222) of the image encoding device (200) can be applied to the filtering unit (350), the inter prediction unit (332), and the intra prediction unit (331) of the image decoding device (300) in the same or corresponding manner, respectively.

[0091] Figure 4 illustrates an example of a hierarchical structure for coded video / images.

[0092] Referring to FIG. 4, the coded video / image is divided into a VCL (Video Coding Layer) that handles decoding processing of the video / image and the video itself, a subsystem that transmits and stores the coded information, and a NAL (Network Abstraction Layer) that exists between the VCL and the subsystem and is responsible for network adaptation functions.

[0093] In VCL, VCL data containing compressed image data (slice data) can be generated, or a parameter set containing information such as a picture parameter set (PPS), a sequence parameter set (SPS), a video parameter set (VPS), etc., or an SEI (Supplemental Enhancement Information) message additionally required for the image decoding process can be generated.

[0094] In NAL, a NAL unit can be created by adding header information (NAL unit header) to an RBSP (Raw Byte Sequence Payload) generated from a VCL. At this time, RBSP refers to slice data, parameter sets, SEI messages, etc. generated from a VCL. The NAL unit header can include NAL unit type information that is specific to the RBSP data included in the NAL unit.

[0095] As illustrated in Fig. 4, NAL units can be divided into VCL NAL units and non-VCL NAL units according to the RBSP generated from VCL. A VCL NAL unit can refer to a NAL unit that contains information about a video (slice data), and a non-VCL NAL unit can refer to a NAL unit that contains information necessary for decoding a video (parameter set or SEI message).

[0096] The above-described VCL NAL units and non-VCL NAL units can be transmitted over a network by attaching header information according to the data specifications of the lower system. For example, NAL units can be transformed into data formats of a certain standard, such as the H.266 / VVC file format, RTP (Real-time Transport Protocol), TS (Transport Stream), etc., and transmitted over various networks.

[0097] As described above, a NAL unit can be specified as a NAL unit type according to the RBSP data structure included in the NAL unit, and information about the NAL unit type can be stored and signaled in the NAL unit header.

[0098] For example, depending on whether a NAL unit contains information about a picture (slice data), it can be broadly classified into VCL NAL unit types and Non-VCL NAL unit types. The VCL NAL unit type can be classified according to the nature and type of the picture contained in the VCL NAL unit, and the Non-VCL NAL unit type can be classified according to the type of parameter set, etc.

[0099] Below are examples of NAL unit types, specified by the type of parameter set included in the Non-VCL NAL unit type.

[0100] - APS (Adaptation Parameter Set) NAL unit: Type for NAL units containing APS

[0101] - DPS (Decoding Parameter Set) NAL unit: Type for NAL unit containing DPS

[0102] - VPS (Video Parameter Set) NAL unit: Type for NAL units containing VPS

[0103] - SPS (Sequence Parameter Set) NAL unit: Type for NAL units containing SPS

[0104] - PPS (Picture Parameter Set) NAL unit: Type for NAL units containing PPS

[0105] The above-described NAL unit types have syntax information for the NAL unit type, and the syntax information can be stored and signaled in the NAL unit header. For example, the syntax information can be nal_unit_type, and NAL unit types can be specified by the nal_unit_type value.

[0106] The slice header (slice header syntax, slice header information) may include information / parameters that are commonly applicable to the slices. The APS (APS syntax) or PPS (PPS syntax) may include information / parameters that are commonly applicable to one or more slices or pictures. The SPS (SPS syntax) may include information / parameters that are commonly applicable to one or more sequences. The VPS (VPS syntax) may include information / parameters that are commonly applicable to multiple layers. The DPS (DPS syntax) may include information / parameters that are commonly applicable to the entire video. The DPS may include information / parameters related to the concatenation of CVS (coded video sequence). In the present disclosure, the High Level Syntax (HLS) may include at least one of the APS syntax, PPS syntax, SPS syntax, VPS syntax, DPS syntax, or slice header syntax.

[0107] In the present disclosure, image / video information encoded in an image encoding device and signaled in the form of a bitstream may include information related to partitioning within a picture, intra / inter prediction information, residual information, in-loop filtering information, etc., and may also include information included in the slice header, information included in the APS, information included in the PPS, information included in the SPS, information included in the VPS, and / or information included in the DPS.

[0108] A common post-processing filtering procedure using a neural network post-filter.

[0109] The input to this procedure is a bitstream BitstreamToFilter, and the output is a list of NNPF output pictures ListNnpfOutputPics. First, BitstreamToFilter is decoded, and the list CroppedDecodedPictures is set to a list of cropped and decoded pictures in the output order resulting from decoding BitstreamToFilter. Second, the filtering process for one picture exists in CroppedDecodedPictures, and is applied recursively in the output order for each cropped and decoded picture for which one or more NNPFs are enabled. The order of the pictures in ListNnpfOutputPics is the output order.

[0110] A picture associated with a particular time instance must not be present in more than one ListNnpfOutputPics . If multiple NNPFs are active for a particular picture in CroppedDecodedPictures and any of the NNPFs can be selected, but only one is allowed to be applied, the above constraint may be applied regardless of which NNPF is selected to be applied to the particular picture.

[0111] The filtering procedure described below can be applied to each cropped and decoded picture (referred to as the current picture) present in CroppedDecodedPictures and for which one or more NNPFs are enabled. When applying NNPF to the current picture, filtered and / or interpolated pictures are generated by the NNPF by applying the NNPF procedure specified in the semantics of the NNPFC SEI message to the current picture on a patch-by-patch basis.

[0112] When applying NNPF to the current picture, the order of the pictures generated by NNPF by applying the NNPF stored in the output tensor of NNPF is the output order. If the applied NNPF is the last NNPF applied to the current picture, the pictures generated by NNPF and output by the NNPF procedure can be included in ListNnpfOutputPics in the same order in which the pictures are stored in the output tensor of NNPF.

[0113] Neural-network post-filter characteristics (NNPFC)

[0114] The combinations in Tables 1 to 3 represent the NNPFC syntax structure.

[0115]

[0116]

[0117]

[0118] The NNPFC syntax structures of Tables 1 to 3 may be signaled in the form of supplemental enhancement information (SEI) messages. An SEI message signaling the NNPFC syntax structures of Tables 1 to 3 may be referred to as an NNPFC SEI message.

[0119] The NNPFC SEI message can specify a neural network that can be used as a post-processing filter. The use of specific post-processing filters (NNPFs) for specific pictures can be indicated using neural-network post-filter activation SEI messages. Here, "post-processing filter" and "post-filter" can have the same meaning.

[0120] Using these SEI messages may require defining the following variables:

[0121] - The input picture width and height in luma sample units can be represented as CroppedWidth and CroppedHeight, respectively.

[0122] - CroppedYPic[idx], which is a luma sample array of input pictures with indices idx in the range of 0 to numInputPics-1, and CroppedCbPic[idx] and CroppedCrPic[idx], which are chroma sample arrays, can be used as inputs to NNPF if they exist.

[0123] - BitDepth Y can represent the bit depth for the luma sample array of input pictures.

[0124] - BitDepth C may represent the bit depth of the chroma sample arrays (if any) of the input pictures.

[0125] - ChromaFormatIdc can represent a chroma format identifier.

[0126] - If the value of nnpfc_auxiliary_inp_idc is 1, the filtering strength control value array StrengthControlVal[idx] must contain real numbers in the range 0 to 1 for input pictures with indices idx in the range 0 to numInputPics-1.

[0127] An input picture having index 0 may correspond to a picture whose NNPF defined by the NNPFC SEI message is activated by the NNPFA SEI message. An input picture having an index i in the range of 0 to numInputPics-1 may precede an input picture having an index i-1 in the output order.

[0128] The variables SubWidthC and SubHeightC can be derived from ChromaFormatIdc. There can be more than one NNPFC SEI message for the same picture. If more than one NNPFC SEI message with different nnpfc_id values ​​exists or is enabled for the same picture, the two or more NNPFC SEI messages can have the same or different nnpfc_purpose and nnpfc_mode_idx values.

[0129] nnpfc_purpose can represent the purpose of NNPF as specified in Table 3. Here, (nnpfc_purpose & bitMask) being non-zero can indicate that NNPF has a purpose associated with the bitMask value in Table 3. If nnpfc_purpose is greater than 0 and (nnpfc_purpose & bitMask) is 0, the purpose associated with the bitMask value may not be applied to NNPF. If nnpfc_purpose is 0, NNPF can be used.

[0130] The nnpfc_purpose value must be in the range 0 to 63 inclusive in the bitstream. The values ​​64 to 65535 for nnpfc_purpose are reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages containing npfc_purpose in the range 64 to 65535.

[0131]

[0132] The variables chromaUpsamplingFlag, resolutionResamplingFlag, pictureRateUpsamplingFlag, bitDepthUpsamplingFlag, and colorizationFlag, which specify whether nnpfc_purpose indicates the purpose of NNPF, which includes chroma upsampling, resolution resampling, pictureRateUpsamplingFlag, bitDepthUpsamplingFlag, and colorizationFlag, can be derived as shown in Table 5 below.

[0133]

[0134] If the reserved value of nnpfc_purpose is used in the future, the syntax of the above SEI message may be extended with a syntax element whose presence is determined by nnpfc_purpose matching that value.

[0135] If ChromaFormatIdc is 3, chromaUpsamplingFlag must be equal to 0.

[0136] If ChromaFormatIdc or chromaUpsamplingFlag is non-zero, colorizationFlag must be equal to 0.

[0137] If pictureRateUpsamplingFlag is 1 and the input picture at index 0 is associated with a frame packing arrangement SEI message with fp_arrangement_type equal to 5, then all input pictures may be associated with a frame packing arrangement SEI message with fp_arrangement_type equal to 5 and fp_current_frame_is_frame0_flag of the same value.

[0138] nnpfc_id can contain an identifier number that can be used to identify the post-processing filter. The nnpfc_id value can be between 0 and 2. 32 - Must be in the range of 2. 256 to 511 and 2 31 Inland 2 32 - nnpfc_id values ​​in the range 256 to 511 may be reserved for future use. Decoders may use values ​​in the range 256 to 511 or 2 31 Inland 2 32 - NNPFC SEI messages with nnpfc_id in the range 2 must be ignored.

[0139] If the NNPFC SEI message is the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current Coded Layer Video Sequence (CLVS), the following may apply.

[0140] - The above SEI message may represent a base post-processing filter (NNPF).

[0141] - The above SEI message may be associated with the current decoded picture and all subsequent decoded pictures of the current layer until the current CLVS ends, in output order.

[0142] A value of 1 for nnpfc_base_flag can indicate that the SEI message specifies the base NNPF. A value of 0 for nnpfc_base_flag can indicate that the SEI message specifies updates related to the base NNPF.

[0143] The following constraints may apply to the nnpfc_base_flag value:

[0144] - If the NNPFC SEI message is the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS, the nnpfc_base_flag value must be equal to 1.

[0145] - If NNPFC SEI message nnpfcB is not the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS and the nnpfc_base_flag value is equal to 1, then the NNPFC SEI message must be a repetition of the first NNPFC SEI message nnpfcA with the same nnpfc_id value in decoding order. That is, the payload content of nnpfcB must be identical to the payload content of nnpfcA.

[0146] If nnpfc_base_flag is 0, the following may apply:

[0147] - The above SEI message may define updates relative to a base NNPF preceding in decoding order with the same nnpfc_id value. The updates are not cumulative, but rather each update may be applied to the base NNPF, which is the NNPF specified by the first NNPFC SEI message in decoding order with a specific nnpfc_id value within the current CLVS. The NNPF defined by the above SEI message may be obtained by applying the updates defined by the above SEI message to a base NNPF with the same nnpfc_id value.

[0148] - The above SEI message is associated with the current decoded picture and all subsequent decoded pictures of the current layer in output order until the current CLVS ends or until the decoded picture following the current decoded picture in output order within the current CLVS is excluded, and may be associated with subsequent NNPFC SEI messages in decoding order that have nnpfc_base_flag equal to 0 and have a specific nnpfc_id value earlier in the current CLVS.

[0149] A value of nnpfc_mode_idc of 0 may indicate that the SEI message contains a bitstream compliant with ISO / IEC 15938-17 that specifies a base NNPF (if nnpfc_base_flag is 1) or is an update associated with a base NNPF with the same nnpfc_id value (if nnpfc_base_flag is 0).

[0150] When nnpfc_mode_idc is 1, a value of nnpfc_mode_idc may indicate that the underlying NNPF associated with the nnpfc_id value is a neural network, and the neural network may be a neural network identified by a URI denoted by nnpfc_uri using a format identified by a tag URI nnpfc_tag_uri. When nnpfc_mode_idc is 0, a value of nnpfc_mode_idc may indicate that updates to the underlying NNPF with the same nnpfc_id value are defined by a URI denoted by nnpfc_uri using a format identified by a tag URI nnpfc_tag_uri.

[0151] The value of nnpfc_mode_idc must be in the range 0 to 1 in the bitstream. Values ​​in the range 2 to 255 for nnpfc_mode_idc are reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_mode_idc in the range 2 to 255. Values ​​of nnpfc_mode_idc greater than 255 are not present in the bitstream and may not be reserved for future use.

[0152] nnpfc_reserved_zero_bit_a must be equal to 0 in the bitstream. Decoders must ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0153] nnpfc_tag_uri may contain a tag URI with syntax and semantics specified in IETF RFC 4151 that identifies the format and related information for updates regarding the neural network used as the base NNPF or the base NNPF having the same nnpfc_id value specified by nnpfc_uri.

[0154] nnpfc_tag_uri can uniquely identify the format of neural network data specified by nnrpf_uri without a central registration authority.

[0155] An nnpfc_tag_uri equal to "tag:iso.org,2023:15938-17" may indicate that the neural network data identified by nnpfc_uri is compliant with ISO / IEC 15938-17.

[0156] nnpfc_uri may contain a URI with the syntax and semantics specified in IETF Internet Standard 66 that identifies the neural network used as the default NNPF or an update to the default NNPF with the same nnpfc_id value.

[0157] A value of 1 for nnpfc_formatting_and_purpose_flag may indicate the presence of syntax elements related to filter purpose, input formatting, output formatting, and complexity. A value of 0 for nnpfc_formatting_and_purpose_flag may indicate the absence of syntax elements related to filter purpose, input formatting, output formatting, and complexity.

[0158] If nnpfc_base_flag is 1, nnpfc_property_present_flag must be equal to 1.

[0159] If nnpfc_property_present_flag is 0, the values ​​of all syntax elements that can only be present if nnpfc_property_present_flag is 1 can be inferred to be identical to their respective syntax elements in the NNPFC SEI message containing the base NNPF to which the above SEI message provides updates.

[0160] If the NNPFC SEI message nnpfcCurr is not the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS, is not a repeat of the first NNPFC SEI message with the particular nnpfc_id value (i.e., the nnpfc_base_flag value is equal to 0), and the nnpfc_property_present_flag value is equal to 1, the following constraints may apply.

[0161] - The nnpfc_purpose value of an NNPFC SEI message must be identical to the nnpfc_purpose value of the first NNPFC SEI message in decoding order with a specific nnpfc_id value within the current CLVS.

[0162] - The values ​​of the syntax elements that come before nnpfc_complexity_info_present_flag and after nnpfc_property_present_flag in decoding order in the NNPFC SEI message must be identical to the values ​​of the corresponding syntax elements of the first NNPFC SEI message in decoding order with a specific nnpfc_id value within the current CLVS.

[0163] In the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS (denoted by nnpfcBase below), nnpfc_complexity_info_present_flag shall be equal to 0 or both nnpfc_complexity_info_present_flag shall be equal to 1, and all of the following may apply:

[0164] - nnpfc_parameter_type_idc of nnpfcCurr must be the same as nnpfc_parameter_type_idc of nnpfcBase.

[0165] - nnpfc_log2_parameter_bit_length_minus3 of nnpfcCurr must be less than or equal to nnpfc_log2_parameter_bit_length_minus3 of nnpfcBase, if present.

[0166] - If nnpfc_num_parameters_idc of nnpfcBase is 0, nnpfc_num_parameters_idc of nnpfcCurr must be equal to 0.

[0167] - Otherwise (nnpfc_num_parameters_idc of nnpfcBase is greater than 0), nnpfc_num_parameters_idc of nnpfcCurr must be greater than 0 and less than or equal to nnpfc_num_parameters_idc of nnpfcBase.

[0168] - If nnpfc_num_kmac_operations_idc of nnpfcBase is 0, nnpfc_num_kmac_operations_idc of nnpfcCurr must be equal to 0.

[0169] - Otherwise (nnpfc_num_kmac_operations_idc of nnpfcBase is greater than 0), nnpfc_num_kmac_operations_idc of nnpfcCurr must be greater than 0 and less than or equal to nnpfc_num_kmac_operations_idc of nnpfcBase.

[0170] - If nnpfc_total_kilobyte_size of nnpfcBase is 0, nnpfc_total_kilobyte_size of nnpfcCurr must be equal to 0.

[0171] - Otherwise (nnpfc_total_kilobyte_size of nnpfcBase is greater than 0), nnpfc_total_kilobyte_size of nnpfcCurr must be greater than 0 and less than or equal to nnpfc_total_kilobyte_size of nnpfcBase.

[0172] nnpfc_num_input_pics_minus1 +_1 can represent the number of pictures used as input to NNPF. The value of nnpfc_num_input_pics_minus1 must be in the range of 0 to 63. If pictureRateUpsamplingFlag is equal to 1, the value of nnpfc_num_input_pics_minus1 must be greater than 0.

[0173] The variable numInputPics, which represents the number of pictures used as input to NNPF, can be derived as shown in Equation 1 below.

[0174] [Formula 1]

[0175]

[0176] A value of 1 in nnpfc_input_pic_output_flag[i] may indicate that NNPF generates the corresponding output picture for the i-th input picture. A value of 0 in nnpfc_input_pic_output_flag[i] may indicate that NNPF does not generate the corresponding output picture for the i-th input picture. If nnpfc_num_input_pics_minus1 is equal to 0, nnpfc_input_pic_output_flag[0] may be inferred to be 1. If pictureRateUpsamplingFlag is equal to 0 and nnpfc_num_input_pics_minus1 is greater than 0, nnpfc_input_pic_output_flag[i] shall be equal to 1 for at least one value of i in the range of 0 to nnpfc_num_input_pics_minus1.

[0177] A value of 1 for nnpfc_absent_input_pic_zero_flag may indicate that NNPF expects that input pictures that are not present in the bitstream will be represented by sample arrays with sample values ​​of 0. A value of 0 for nnpfc_absent_input_pic_zero_flag may indicate that NNPF expects that input pictures that are not present in the bitstream will be represented by the closest input picture in output order in the bitstream. nnpfc_out_sub_c_flag may indicate the values ​​of variables outSubWidthC and outSubHeightC when chromaUpsamplingFlag is 1. A value of 1 for nnpfc_out_sub_c_flag may indicate that the value of outSubWidthC is 1 and the value of outSubHeightC is 1. A value of 0 for nnpfc_out_sub_c_flag can indicate that the value of outSubWidthC is 2 and the value of outSubHeightC is 1. If the value of ChromaFormatIdc is 2 and nnpfc_out_sub_c_flag is present, the value of nnpfc_out_sub_c_flag must be equal to 1.

[0178] nnpfc_out_colour_format_idc can represent the colour format of NNPF and consequently the values ​​of variables outSubWidthC and outSubHeightC when colourizationFlag is 1. A value of 1 for nnpfc_out_colour_format_idc can indicate that the colour format of the NNPF output is 4:2:0, and both outSubWidthC and outSubHeightC are 2. A value of 2 for nnpfc_out_colour_format_idc can indicate that the colour format of the NNPF output is 4:2:2, outSubWidthC is 2, and outSubHeightC is 1. A value of 3 for nnpfc_out_colour_format_idc can indicate that the colour format of the NNPF output is 4:4:4, and both outSubWidthC and outSubHeightC are 1. The value of nnpfc_out_colour_format_idc must not be 0.

[0179] If both chromaUpsamplingFlag and colorizationFlag are 0, outSubWidthC and outSubHeightC can be inferred to be equal to SubWidthC and SubHeightC, respectively. nnpfc_pic_width_num_minus1 + 1 and nnpfc_pic_width_denom_minus1 + 1 can represent the numerator and denominator, respectively, for the resampling ratio of the NNPF output picture width with respect to CroppedWidth. The value of (nnpfc_pic_width_num_minus1 +1) ÷ (nnpfc_pic_width_denom_minus1 +1) must be in the range of 1 ÷ 16 to 16. If nnpfc_pic_width_num_minus1 and nnpfc_pic_width_denom_minus1 do not exist, the values ​​of nnpfc_pic_width_num_minus1 and nnpfc_pic_width_denom_minus1 can both be inferred to be equal to 0.

[0180] The variable nnpfcOutputPicWidth, which represents the width of the luma sample arrays of the picture(s) resulting from applying the NNPF identified by nnpfc_id to the input picture(s), can be derived as in Equation 2 below.

[0181] [Formula 2]

[0182]

[0183] It is a bitstream conformance requirement that the value of nnpfcOutputPicWidth % outSubWidthC must be equal to 0.

[0184] nnpfc_pic_height_num_minus1 + 1 and nnpfc_pic_height_denom_minus1 + 1 may represent the numerator and denominator, respectively, for the resampling ratio of the NNPF output picture height with respect to CroppedHeight. The value of (nnpfc_pic_height_num_minus1 + 1) ÷ (nnpfc_pic_height_denom_minus1 + 1) must be in the range of 1 ÷ 16 to 16. If nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denom_minus1 do not exist, the values ​​of nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denom_minus1 can be inferred to be both equal to 0.

[0185] The variable nnpfcOutputPicHeight, which represents the height of the luma sample arrays of the picture(s) resulting from applying the NNPF identified by nnpfc_id to the input picture(s), can be derived as in Equation 3 below.

[0186] [Formula 3]

[0187]

[0188] It is a bitstream conformance requirement that the value of nnpfcOutputPicHeight % outSubHeightC must be equal to 0.

[0189] If nnpfc_pic_width_num_minus1, nnpfc_pic_width_denom_minus1, nnpfc_pic_height_num_minus1, and nnpfc_pic_height_denom_minus1 exist, then at least one of the following must be true:

[0190] - The value of nnpfcOutputPicWidth is not equal to CroppedWidth.

[0191] - The value of nnpfcOutputPicHeight is not equal to CroppedHeight.

[0192] nnpfc_interpolated_pics[i] can represent the number of interpolated pictures generated by NNPF between the i-th picture used as input to NNPF and the (i + 1)-th picture.

[0193] The value of nnpfc_interpolated_pics[i] must be in the range 0 to 63, inclusive. The value of nnpfc_interpolated_pics[i] must be greater than 0 for at least one value of i in the range 0 to nnpfc_num_input_pics_minus1 - 1.

[0194] The variables NumInpPicsInOutputTensor, which represents the number of pictures existing in the output tensor of NNPF with the corresponding input picture, InpIdx[idx], which represents the input picture index of the idx-th picture existing in the output tensor of NNPF with the corresponding input picture, and numOutputPics, which represents the total number of pictures existing in the output tensor of NNPF, can be derived as shown in Table 6 below.

[0195]

[0196] The value 1 of nnpfc_component_last_flag can indicate that the last dimension of the input tensor inputTensor for NNPF and the output tensor outputTensor resulting from NNPF are used for the current channel. The value 0 of nnpfc_component_last_flag can indicate that the third dimension of the input tensor inputTensor for NNPF and the output tensor outputTensor resulting from NNPF are used for the current channel.

[0197] The first dimension of the input and output tensors can be used as batch indices, as used in some neural network frameworks. The semantics of this SEI message use a batch size corresponding to a batch index equal to 0, but the batch size used as input for neural network inference can be determined by the implementation of postprocessing.

[0198] For example, when the value of nnpfc_inp_order_idc is equal to 3 and the value of nnpfc_auxiliary_inp_idc is equal to 1, the input tensor can have 7 channels, including 4 luma matrices, 2 chroma matrices, and 1 auxiliary input matrix. In this case, the DeriveInputTensors() process can derive one for each of the 7 channels of the input tensor, and when a specific channel among these channels is processed, that channel can be referred to as the current channel during the process.

[0199] nnpfc_inp_format_idc can indicate how to convert the sample values ​​of the input picture into the input values ​​of NNPF. If nnpfc_inp_format_idc is 0, the input values ​​to NNPF are real numbers, and the functions InpY() and InpC() can be specified as in the following equation 4.

[0200] [Formula 4]

[0201]

[0202] If the value of nnpfc_inp_format_idc is 1, the input values ​​of NNPF are unsigned integer numbers, and the functions InpY() and InpC() can be derived as shown in Table 7.

[0203]

[0204] Variable inpTensorBitDepth ycan be derived from the syntax element nnpfc_inp_tensor_bitlength_minus8 described below. inpTensorBitDepth C can be derived from the syntax element nnpfc_inp_tensor_chroma_bitdepth_minus8 described below.

[0205] Values ​​of nnpfc_inp_format_idc greater than 1 may be reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages containing reserved values ​​of nnpfc_inp_format_idc.

[0206] A value of nnpfc_auxiliary_inp_idc greater than 0 may indicate that auxiliary input data exists in the input tensor of NNPF. A value of 0 for nnpfc_auxiliary_inp_idc may indicate that auxiliary input data does not exist in the input tensor. A value of 1 for nnpfc_auxiliary_inp_idc may indicate that auxiliary input data is derived as described in Equation 5 below.

[0207] The value of nnpfc_auxiliary_inp_idc must be in the range 0 to 1 in the bitstream. Values ​​of nnpfc_auxiliary_inp_idc in the range 2 to 255 are reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages containing nnpfc_auxiliary_inp_idc in the range 2 to 255. Values ​​of nnpfc_auxiliary_inp_idc greater than 255 are not present in the bitstream and are not reserved for future use.

[0208] nnpfc_inp_order_idc can indicate how to order the sample array of input pictures to form the input tensor for NNPF.

[0209] The value of nnpfc_inp_order_idc must be in the range 0 to 3 in the bitstream. Values ​​of 4 to 255 for nnpfc_inp_order_idc are reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_inp_order_idc in the range 4 to 255. Values ​​of nnpfc_inp_order_idc greater than 255 are not present in the bitstream and are not reserved for future use.

[0210] If the value of ChromaFormatIdc is not 1, the value of nnpfc_inp_order_idc must not be 3.

[0211] If ChromaFormatIdc is 0, nnpfc_inp_order_idc must be equal to 0.

[0212] If chromaUpsamplingFlag is 1, nnpfc_inp_order_idc must not be 0.

[0213] Table 8 contains a description of the nnpfc_inp_order_idc values.

[0214]

[0215] nnpfc_inp_tensor_bitlength_minus8 + 8 can represent the bit depth of luma sample values ​​in the input integer tensor. inpTensorBitDepth Y The value of can be derived as in Equation 5.

[0216] [Formula 5]

[0217]

[0218] It is a bitstream conformance requirement that the value of nnpfc_inp_tensor_luma_bitdepth_minus8 be in the range 0 to 24.

[0219] nnpfc_inp_tensor_chroma_bitdepth_minus8 + 8 can represent the bit depth of chroma sample values ​​in the input integer tensor. inpTensorBitDepth C The value of can be derived as in Equation 6.

[0220] [Formula 6]

[0221]

[0222] It is a bitstream conformance requirement that the value of nnpfc_inp_tensor_chroma_bitdepth_minus8 be in the range 0 to 24.

[0223] If nnpfc_auxiliary_inp_idc is 1, the variable strengthControlScaledVal can be derived as shown in Table 9 below.

[0224]

[0225] A patch may be a rectangular array of samples from a component of a picture (e.g., a luma or chroma component).

[0226] The process DeriveInputTensors( ) for deriving an input tensor inputTensor for a given vertical sample coordinate cTop and a horizontal sample coordinate cLeft specifying the top-left sample location for a patch of samples contained in the input tensor can be represented as a combination of Tables 10 to 12.

[0227]

[0228]

[0229]

[0230] A value of 0 in nnpfc_out_format_id may indicate that the sample values ​​output to the NNPF are real numbers that are linearly mapped to an unsigned integer value range of 0 to (1 << bitDepth) - 1 for the desired bit depth bitDepth for subsequent post-processing or display, where the real numbers may be in the value range of 0 to 1.

[0231] A value of nnpfc_out_format_flag of 1 means that the luma sample values ​​output by NNPF are between 0 and ( 1 << outTensorBitDepth Y ) - 1 is an unsigned integer in the range ( 1 << outTensorBitDepth C ) - can represent an unsigned integer in the range 1.

[0232] Values ​​of nnpfc_out_format_idc greater than 1 may be reserved for future specifications and are not present in the bitstream. Decoders must ignore NNPFC SEI messages containing reserved values ​​of nnpfc_out_format_idc.

[0233] nnpfc_out_order_idc can indicate the output order of samples due to NNPF.

[0234] The value of nnpfc_out_order_idc must be in the range 0 to 3 in the bitstream. Values ​​of 4 to 255 for nnpfc_out_order_idc may be reserved for future use and are not present in the bitstream. Decoders must ignore NNPFC SEI messages containing nnpfc_out_order_idc in the range 4 to 255. Values ​​of nnpfc_out_order_idc greater than 255 are not present in the bitstream and are not reserved for future use.

[0235] If chromaUpsamplingFlag is 1, nnpfc_out_order_idc must not be 0 or 3.

[0236] If colorizationFlag is 1, nnpfc_out_order_idc must not be 0.

[0237] Table 13 contains a description of the nnpfc_out_order_idc values.

[0238]

[0239] nnpfc_out_tensor_luma_bitdepth_minus8 + 8 can represent the bit depth of the luma sample values ​​of the output integer tensor. The value of nnpfc_out_tensor_luma_bitdepth_minus8 must be in the range of 0 to 24. outTensorBitDepth Y The value of can be derived as in Equation 7.

[0240] [Formula 7]

[0241]

[0242] nnpfc_out_tensor_chroma_bitdepth_minus8 + 8 can represent the bit depth of the chroma sample values ​​of the output integer tensor. The value of nnpfc_out_tensor_chroma_bitdepth_minus8 must be in the range of 0 to 24. outTensorBitDepth C The value of can be derived as in Equation 8.

[0243] [Formula 8]

[0244]

[0245] If bitDepthUpsamplingFlag is 1, the value of nnpfc_out_format_idc must be equal to 1, and at least one of the following conditions must be true:

[0246] - nnpfc_out_tensor_luma_bitdepth_minus8 exists and outTensorBitDepth Y BitDepth Y Bigger than.

[0247] - nnpfc_out_tensor_chroma_bitdepth_minus8 exists and outTensorBitDepth C BitDepth C Bigger than.

[0248] nnpfc_inp_tensor_luma_bitdepth_minus8, nnpfc_inp_tensor_chroma_bitdepth_minus8, nnpfc_out_tensor_luma_bitdepth_minus8, and nnpfc_out_tensor_chroma_bitdepth_minus8 exist and outTensorBitDepth Y inpTensorBitDepth Y If greater than outTensorBitDepth C is inpTensorBitDepth C It should be smaller than that.

[0249] nnpfc_inp_tensor_luma_bitdepth_minus8, nnpfc_inp_tensor_chroma_bitdepth_minus8, nnpfc_out_tensor_luma_bitdepth_minus8, and nnpfc_out_tensor_chroma_bitdepth_minus8 exist and outTensorBitDepth C inpTensorBitDepth C If greater than outTensorBitDepth Y is inpTensorBitDepth Y It should be smaller than that.

[0250] The process StoreOutputTensors( ) for deriving sample values ​​in the filtered output sample arrays FilteredYPic, FilteredCbPic and FilteredCrPic from the output tensor outputTensor for the given vertical sample coordinates cTop and horizontal sample coordinates cLeft indicating the top-left sample location for the patch of samples contained in the input tensor can be expressed as a combination of Tables 14 and 15.

[0251]

[0252]

[0253] A value of 1 for nnpfc_separate_colour_description_present_flag may indicate that a unique combination of colour primaries, transformation properties, matrix coefficients, and scaling and offset values ​​applied with respect to matrix coefficients for a picture due to NNPF is specified in the SEI message syntax structure. A value of 0 for nnpfc_separate_colour_description_present_flag may indicate that a combination of colour primaries, transformation properties, matrix coefficients, and scaling and offset values ​​applied with respect to matrix coefficients for a picture due to post-processing filter is the same as indicated in the VUI parameters of CLVS.

[0254] nnpfc_colour_primaries may have the same semantics as defined for the vui_colour_primaries syntax element, except that:

[0255] - nnpfc_colour_primaries can represent the primary colors of a picture that result from applying NNPF specified in the SEI message, rather than the primary colors used in CLVS.

[0256] - If nnpfc_colour_primaries does not exist in the NNPFC SEI message, the value of nnpfc_colour_primaries can be inferred to be the same as the value of vui_colour_primaries.

[0257] nnpfc_transfer_characteristics can have the same semantics as those defined for the vui_transfer_characteristics syntax element, except that:

[0258] - nnpfc_transfer_characteristics can indicate the transfer characteristics of the picture that result from applying the NNPF specified in the SEI message, rather than the transfer characteristics used in CLVS.

[0259] - If nnpfc_transfer_characteristics does not exist in the NNPFC SEI message, the value of nnpfc_transfer_characteristics can be inferred to be the same as the value of vui_transfer_characteristics.

[0260] nnpfc_matrix_coeffs can describe the formulas used to derive luma and chroma signals from green, blue, red or Y, Z, X primaries. Its semantics are applied to the resulting picture by applying the NNPF specified in the SEI message, outTensorBitDepth Y and outTensorBitDepth C outTensorBitDepth equal to each C and BitDepth C It may be the same as specified for MatrixCoefficients including .

[0261] If nnpfc_matrix_coeffs does not exist in the NNPFC SEI message, the value of nnpfc_matrix_coeffs can be inferred to be equal to the value of vui_matrix_coeffs.

[0262] nnpfc_matrix_coeffs cannot be equal to 0 unless all of the following conditions are true:

[0263] - nnpfc_out_tensor_chroma_bitdepth_minus8 is the same as nnpfc_out_tensor_luma_bitdepth_minus8.

[0264] - nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0265] nnpfc_matrix_coeffs cannot be equal to 8 unless one of the following conditions is true:

[0266] - nnpfc_out_tensor_chroma_bitdepth_minus8 is the same as nnpfc_out_tensor_luma_bitdepth_minus8.

[0267] - nnpfc_out_tensor_chroma_bitdepth_minus8 is equal to nnpfc_out_tensor_luma_bitdepth_minus8 + 1, nnpfc_out_order_idc is equal to 2, outSubHeightC is equal to 1, and outSubWidthC is equal to 1.

[0268] nnpfc_full_range_flag can indicate scaling and offset values ​​applied to matrix coefficients as specified by nnpfc_matrix_coeffs. Its semantics can be identical to those specified for the VideoFullRangeFlag parameter. If it is not present, the value of nnpfc_full_range_flag can be inferred to be equal to 0.

[0269] A value of 1 for nnpfc_chroma_loc_info_present_flag may indicate the presence of the nnpfc_chroma_sample_loc_type_frame syntax element in the NNPFC SEI message. A value of 0 for nnpfc_chroma_loc_info_present_flag may indicate the absence of the nnpfc_chroma_sample_loc_type_frame syntax element in the NNPFC SEI message. The value of nnpfc_chroma_loc_info_present_flag shall be equal to 0 if colorizationFlag is 0 or nnpfc_out_colour_format_idc is not 1.

[0270] nnpfc_chroma_sample_loc_type_frame may indicate the locations of chroma samples of output pictures if nnpfc_chroma_sample_loc_type_frame is not 6 and nnpfc_out_colour_format_idc is equal to 1. If nnpfc_chroma_sample_loc_type_frame is 6 and nnpfc_out_colour_format_idc is equal to 1, it may indicate that the locations of chroma samples are unknown, unspecified, or specified by other means. The value of nnpfc_chroma_sample_loc_type_frame must be in the range 0 to 6, inclusive.

[0271] nnpfc_overlap can indicate the number of overlapping horizontal and vertical samples of adjacent input tensors of NNPF. The value of nnpfc_overlap must be in the range of 0 to 16383. A value of nnpfc_constant_patch_size_flag of 1 can indicate that NNPF accepts as input exactly the patch sizes indicated by nnpfc_patch_width_minus1 and nnpfc_patch_height_minus1. A value of nnpfc_constant_patch_size_flag of 0 can indicate that NNPF accepts as input any patch size with width inpPatchWidth and height inpPatchHeight. This can be done so that the width of the extended patch (i.e., patch + overlapping area) equal to inpPatchWidth + 2 * nnpfc_overlap becomes a positive integer multiple of nnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap, and the height of the extended patch equal to inpPatchHeight + 2 * nnpfc_overlap becomes a positive integer multiple of nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap.

[0272] npfc_patch_width_minus1 + 1 can indicate the number of horizontal samples of the patch size required for the input of NNPF 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).

[0273] npfc_patch_height_minus1 + 1 can represent the number of vertical samples of the patch size required for the input of NNPF 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).

[0274] nnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap can represent the common divisor of all allowed values ​​of the width of the extended patch required as input to NNPF when nnpfc_constant_patch_size_flag is 0. The value of nnpfc_extended_patch_width_cd_delta_minus1 must be in the range 0 to Min(32766, CroppedWidth - 1).

[0275] nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap can represent the common divisor of all allowed values ​​of extended patch heights required as input to NNPF when nnpfc_constant_patch_size_flag is 0. The value of nnpfc_extended_patch_height_cd_delta_minus1 must be in the range 0 to Min(32766, CroppedHeight - 1).

[0276] The variables inpPatchWidth and inpPatchHeight can be set to the patch size width and patch size height, respectively.

[0277] If the value of nnpfc_constant_patch_size_flag is 0, the following can be applied:

[0278] - The values ​​of inpPatchWidth and inpPatchHeight can be provided by external means or set by the post-processor itself.

[0279] - The value of inpPatchWidth + 2 * nnpfc_overlap must be a positive integer multiple of ofnnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap, and inpPatchWidth must be less than or equal to CroppedWidth. The value of inpPatchHeight + 2 * nnpfc_overlap must be a positive integer multiple of ofnnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap, and inpPatchHeight must be less than or equal to CroppedHeight.

[0280] Otherwise (the value of nnpfc_constant_patch_size_flag is equal to 1), the value of inpPatchWidth may be set equal to nnpfc_patch_width_minus1 + 1, and the value of inpPatchHeight may be set equal to nnpfc_patch_height_minus1 + 1.

[0281] The variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, outPatchCHeight, and overlapSize can be derived as shown in Table 16.

[0282]

[0283] It is a bitstream conformance requirement that outPatchWidth * CroppedWidth must equal nnpfc_pic_width_in_luma_samples * inpPatchWidth, and outPatchHeight * CroppedHeight must equal nnpfc_pic_height_in_luma_samples * inpPatchHeight.

[0284] nnpfc_padding_type may indicate a padding process when referencing sample positions outside the boundaries of the input picture, as described in Table 17. The value of nnpfc_padding_type must be in the range 0 to 4 in the bitstream. Values ​​of nnpfc_padding_type in the range 5 to 15 are reserved for future use and may not be present in the bitstream. Decoders must ignore NNPFC SEI messages containing nnpfc_padding_type in the range 5 to 15. Values ​​of nnpfc_padding_type greater than 15 are not present in the bitstream and are not reserved for future use.

[0285]

[0286] nnpfc_luma_padding_val can indicate the luma value to be used for padding when the value of nnpfc_padding_type is 4. The value of nnpfc_luma_padding_val is 0 to (1 << BitDepth Y ) - must exist in the range of 1.

[0287] nnpfc_cb_padding_val can indicate the Cb value to be used for padding when the value of nnpfc_padding_type is 4. The value of nnpfc_cb_padding_val is 0 to (1 << BitDepth C ) - must exist in the range of 1.

[0288] nnpfc_cr_padding_val can indicate the Cr value to use for padding when the value of nnpfc_padding_type is 4. The value of nnpfc_cr_padding_val must be in the range of 0 to (1 << BitDepthC) - 1.

[0289] The function InpSampleVal(y, x, picHeight, picWidth, CroppedPic) with inputs vertical sample position y, horizontal sample position x, picture height picHeight, picture width picWidth, sample array CroppedPic, and component index cIdx (equal to 0 for luma, 1 for Cb, and 2 for Cr) can return the value of SampleVal derived as shown in Table 18.

[0290] For input to the function InpSampleVal() , vertical positions may be listed before horizontal positions for compatibility with the input tensor conventions of some inference engines.

[0291]

[0292] NNPF PostProcessingFilter( ) may be a target NNPF derived from the semantics of the NNPFA SEI message. The following example process may be used to generate filtered and / or interpolated picture(s) in a patch-wise manner. The filtered and / or interpolated picture(s) may include a Y sample array FilteredYPic, a Cb sample array FilteredCbPic, and a Cr sample array FilteredCrPic, as specified by nnpfc_out_order_idc.

[0293]

[0294] An NNPF-generated picture containing index i may contain sample arrays FilteredYPic[i], FilteredCbPic[i], and FilteredCrPic[i] derived by Table 19, if any. An NNPF-generated picture may not contain overlapping regions.

[0295] The NNPF process can output NNPF-generated pictures in their increasing index order, forming a process defined by Table 19. Here, all NNPF-generated pictures interpolated by the NNPF are output, and NNPF-generated pictures corresponding to all input pictures to the NNPF can be output as specified in the semantics of the NNPFA SEI message.

[0296] A value of 1 for nnpfc_complexity_info_present_flag may indicate the presence of one or more syntax elements indicating the complexity of the NNPF associated with the nnpfc_id. A value of 0 for nnpfc_complexity_info_present_flag may indicate the absence of syntax elements indicating the complexity of the NNPF associated with the nnpfc_id.

[0297] A value of 0 for nnpfc_parameter_type_idc may indicate that the neural network uses only integer parameters. A value of 1 for nnpfc_parameter_type_flag may indicate that the neural network can use either floating-point or integer parameters. A value of 2 for nnpfc_parameter_type_idc may 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. Decoders should ignore NNPFC SEI messages with a value of 3 for nnpfc_parameter_type_idc.

[0298] The values ​​0, 1, 2, and 3 of nnpfc_log2_parameter_bit_length_minus3 can indicate that the network does 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 network may not use parameters with bit lengths greater than 1.

[0299] nnpfc_num_parameters_idc can represent the maximum number of neural network parameters for NNPF in powers of 2048. A value of 0 for nnpfc_num_parameters_idc can indicate 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 may be reserved for future use and shall not be present in the bitstream. Decoders should ignore NNPFC SEI messages with nnpfc_num_parameters_idc greater than 52.

[0300] If the value of nnpfc_num_parameters_idc is greater than 0, the variable maxNumParameters can be derived as in Equation 9.

[0301] [Formula 9]

[0302]

[0303] It is a requirement of bitstream conformance that the number of neural network parameters of NNPF must be less than or equal to maxNumParameters.

[0304] A value of nnpfc_num_kmac_operations_idc greater than 0 may indicate that the maximum number of multiply-accumulate operations per sample in NNPF is less than or equal to nnpfc_num_kmac_operations_idc * 1000. A value of nnpfc_num_kmac_operations_idc of 0 may indicate that the maximum number of multiply-accumulate operations in the network is unknown. The value of nnpfc_num_kmac_operations_idc can be between 0 and 2. 32 - Must be within the range of 2.

[0305] A value of nnpfc_total_kilobyte_size greater than 0 may indicate the total size (in 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 total size (in bits) divided by 8000, rounded up. A value of 0 for nnpfc_total_kilobyte_size may indicate that the total size required to store the parameters for the neural network is unknown. The value of nnpfc_total_kilobyte_size may be between 0 and 2. 32 - Must be within the range of 2.

[0306] A value of nnpfc_metadata_extension_num_bits of 0 may indicate that nnpfc_reserved_metadata_extension does not exist. An nnpfc_metadata_extension_num_bits greater than 0 may indicate the length of nnpfc_reserved_metadata_extension in bits. nnpfc_metadata_extension_num_bits must be equal to 0. Values ​​in the range 1 to 2048 for nnpfc_metadata_extension_num_bits may be reserved for future use and may not be present in the bitstream. Decoders should accept all values ​​of nnpfc_metadata_extension_num_bits in the range 0 to 2048, inclusive. Values ​​of nnpfc_metadata_extension_num_bits greater than 2048 are not present in the bitstream and are not reserved for future use.

[0307] nnpfc_reserved_metadata_extension is not present in the bitstream. However, decoders must ignore the presence and values ​​of nnpfc_reserved_metadata_extension. If present, the length in bits of nnpfc_reserved_metadata_extension can be equal to nnpfc_metadata_extension_num_bits.

[0308] nnpfc_reserved_zero_bit_b must be equal to 0 in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_reserved_zero_bit_b not equal to 0.

[0309] nnpfc_payload_byte[i] may contain the ith byte of the bitstream. For all existing values ​​of i, the byte sequence nnpfc_payload_byte[i] must be a complete bitstream conforming to ISO / IEC 15938-17.

[0310] Neural-network post-filter activation (NNPFA)

[0311] The syntax structure for NNPFA is shown in Table 20.

[0312]

[0313] The NNPFA syntax structure of Table 20 can be signaled in the form of an SEI message. An SEI message signaling the NNPFA syntax structure of Table 20 may be referred to as an NNPFA SEI message.

[0314] The NNPFA SEI message can enable or disable the possible use of a target neural network post-processing filter, identified by nnpfa_target_id and nnpfc_base_flag, for post-processing filtering of a picture set. For a given picture with NNPF enabled, the target NNPF can be derived as follows:

[0315] - If nnpfa_target_base_flag is 1, the target NNPF is the base NNPF with the same nnpfc_id as nnpfa_target_id.

[0316] - Otherwise (nnpfa_target_base_flag is 0), the target NNPF is the NNPF specified by the last NNPFC SEI message with an nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repeat of the NNPFC SEI message containing the base NNPF.

[0317] Multiple NNPFA SEI messages may exist for the same picture if post-processing filters are used for different purposes or filter different color components.

[0318] nnpfa_target_id may indicate a target NNPF associated with the current picture and specified by one or more NNPFC SEI messages having an nnpfc_id equal to nnpfa_target_id.

[0319] The value of nnpfa_target_id is 0 to 2 32 - Must be in the range of 2. 256 to 511 and 2 31 Inland 2 32 - nnpfa_target_id values ​​in the range 2 may be reserved for future use. Decoders may use values ​​between 256 and 511 or 2 31 Inland 2 32 - NNPFA SEI messages with nnpfa_target_id in the range 2 must be ignored.

[0320] An NNPFA SEI message with a specific value of nnpfa_target_id must not exist in the current Picture Unit (PU) unless one or both of the following conditions are true:

[0321] - Currently, within the CLVS, there exists an NNPFC SEI message with an nnpfc_id that is identical to a specific value of nnpfa_target_id that exists in the PU preceding the current PU in the decoding order.

[0322] - There is an NNPFC SEI message with an nnpfc_id equal to a specific value of nnpfa_target_id in the current PU.

[0323] If a PU contains both an NNPFC SEI message with a nnpfc_id of a particular value and an NNPFA SEI message with a nnpfa_target_id equal to a particular nnpfc_id, the NNPFC SEI message shall precede the NNPFA SEI message in decoding order.

[0324] A value of 1 for nnpfa_cancel_flag may indicate that the persistence of the target neural network post-processing filter set by any previous NNPFA SEI message with the same nnpfa_target_id as the current SEI message is canceled. That is, the target neural network post-processing filter is no longer used unless it is activated by another NNPFA SEI message with the same nnpfa_target_id as the current SEI message and an nnpfa_cancel_flag equal to 0. A value of 0 for nnpfa_cancel_flag may indicate that nnpfa_target_base_flag, nnpfa_persistence_flag, and nnpfa_num_output_entries follow.

[0325] A value of 1 for nnpfa_target_base_flag may indicate that the target NNPF is the base NNPF with nnpfc_id equal to nnpfa_target_id. A value of 0 for nnpfa_target_base_flag may indicate that the target NNPF is the NNPF specified by the last NNPFC SEI message with nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order.

[0326] nnpfa_persistence_flag can indicate the persistence of the target neural network post-processing filter for the current layer. A value of 0 for nnpfa_persistence_flag can indicate that the target neural network post-processing filter can only be used for post-processing filtering for the current picture. A value of 1 for nnpfa_persistence_flag can indicate that the target neural network post-processing filter can be used for post-processing filtering for the current picture and all subsequent pictures in the current layer in output order until one or more of the following conditions are true:

[0327] - A new CLVS for the current layer is started.

[0328] - Bitstream ended

[0329] - The picture in the current layer associated with the NNPFA SEI message with the same nnpfa_target_id as the current SEI message and nnpfa_cancel_flag equal to 1 is output after the current picture in the output order.

[0330] The target neural network postprocessing filter is not applied to subsequent pictures within the current layer associated with an NNPFA SEI message that has the same nnpfa_target_id as the current SEI message and an nnpfa_cancel_flag equal to 1.

[0331] Let nnpfcTargetPictures be the set of pictures associated with the last NNPFC SEI message that precedes the current NNPFA SEI message in decoding order and has an nnpfc_id equal to nnpfa_target_id. Let nnpfaTargetPictures be the set of pictures whose target NNPF is activated by the current NNPFA SEI message. It is a bitstream conformance requirement that a picture included in nnpfaTargetPictures must also be included in nnpfcTargetPictures.

[0332] nnpfa_num_output_entries can indicate the number of nnpfa_output_flag[i] syntax elements present in the NNPFA SEI message. The value of nnpfa_num_output_entries is in the range of 0 to NumInpPicsInOutputTensor.

[0333] A value of 1 in nnpfa_output_flag[i] indicates that the NNPF-generated picture corresponding to the input picture with index InpIdx[i] is output by the NNPF process activated by this NNPFA SEI message, where the NNPF process can be specified within the semantics of the NNPFC SEI message. A value of 0 in nnpfa_output_flag[i] can indicate that the NNPF-generated picture corresponding to the input picture with index InpIdx[i] is not output by the NNPF process activated by this NNPFA SEI message. If nnpfa_num_output_entries is less than NumInpPicsInOutputTensor, nnpfa_output_flag[i] can be inferred to be 1 for each value of i in the range from nnpfa_num_output_entries to NumInpPicsInOutputTensor - 1.

[0334] Post-filter hint

[0335] The syntax structure for post-filter hints is shown in Table 21.

[0336]

[0337] The post-filter hint syntax structure of Table 21 can be signaled in the form of an SEI message. An SEI message signaling the post-filter hint syntax structure of Table 21 may be referred to as a post-filter hint SEI message.

[0338] The post-filter hint SEI message can provide post-filter coefficients or correlation information for the design of a post-filter, potentially allowing the decoded and output picture set to be used in post-processing to achieve improved display quality.

[0339] A value of 1 for filter_hint_cancel_flag may indicate that the SEI message cancels the persistence of the previous post-filter hint SEI message in the output order applied to the current layer. A value of 0 for filter_hint_cancel_flag may indicate that post-filter hint information follows.

[0340] 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 can indicate that the post-filter hint applies only to the currently decoded picture. A value of 1 for filter_hint_persistence_flag can indicate that the post-filter hint SEI message applies to the currently decoded picture and persists for all subsequent pictures in the current layer in output order until one or more of the following conditions are true:

[0341] - A new CLVS for the current layer is started.

[0342] - Bitstream ended

[0343] - Pictures in the current layer of the AU associated with the post-filter hint SEI message are output after the current picture in the output order.

[0344] filter_hint_size_y can indicate the vertical size of the filter coefficients or correlation array. The value of filter_hint_size_y must be in the range of 1 to 15.

[0345] filter_hint_size_x can indicate the horizontal size of the filter coefficients or correlation array. The value of filter_hint_size_x must be in the range of 1 to 15.

[0346] 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 cannot be present in the bitstream. Decoders must ignore post-filter hint SEI messages with filter_hint_type equal to 3.

[0347]

[0348] A value of 1 for filter_hint_chroma_coeff_present_flag may indicate that filter coefficients for chroma exist. A value of 0 for filter_hint_chroma_coeff_present_flag may indicate that filter coefficients for chroma do not exist.

[0349] filter_hint_value[cIdx][cy][cx] can represent filter coefficients or cross-correlation matrix elements between the original and decoded signals with 16-bit precision. The value of filter_hint_value[cIdx][cy][cx] is -2 31 + 1 to 2 31 - Must be in the range of 1. cIdx represents the related color element, cy represents the vertical counter, and cx can represent the horizontal counter. Depending on the value of filter_hint_type, the following can be applied.

[0350] - If the value of filter_hint_type is 0, the coefficients of a two-dimensional FIR (Finite Impulse Response) filter of the size of filter_hint_size_y * filter_hint_size_x can be transmitted.

[0351] - Otherwise, if the value of filter_hint_type is 1, the filter coefficients of two one-dimensional FIR filters can be transmitted. In this case, the value of filter_hint_size_y must be 2. An index cy of 0 can represent the filter coefficients of the horizontal filter, and a cy of 1 can represent the filter coefficients of the vertical filter. In the filtering process, the horizontal filter is applied first, and the result can be filtered by the vertical filter.

[0352] - Otherwise (if the value of filter_hint_type is 2), the transmitted hint may represent a cross-correlation matrix between the original signal s and the decoded signal s'.

[0353] The normalized cross-correlation matrix for the relevant color components identified by cIdx of size filter_hint_size_y * filter_hint_size_x can be defined as in Equation 10.

[0354] [Formula 10]

[0355]

[0356] In Equation 10, s represents a sample array of the color component cIdx of the original picture, s' represents an array of the corresponding decoded picture, h represents the vertical height of the corresponding color component, w represents the horizontal width of the corresponding color component, and bitDepth represents the bit depth of the color component. In addition, OffsetY is equal to ( filter_hint_size_y >> 1 ), OffsetX is equal to ( filter_hint_size_x >> 1 ), cy is in the range of 0 <= cy < filter_hint_size_y, and cx is in the range of 0 <= cx < filter_hint_size_x.

[0357] The decoder can derive a Wiener post-filter from the cross-correlation matrix of the original signal and the decoded signal and the auto-cross-correlation matrix of the decoded signal.

[0358] Problems with prior art

[0359] In the current configuration of NNPFC and NNPFA SEI messages, an NNPFA SEI message can activate a base filter (i.e., an NNPFA SEI message with nnpfc_base_flag equal to 1) or an update filter (i.e., an NNPFA SEI message with nnpfc_base_flag equal to 0) based on the value of nnpfa_target_base_flag.

[0360] nnpfa_target_base_flag can only be signaled when nnpfa_cancel_flag has a value of 0. This can cause problems in identifying which NNPF activation should be canceled if there are two NNPF activations with the same nnpfa_target_id but different values ​​of nnpfa_target_base_flag.

[0361] In other words, if both a base NNPF and an updated NNPF with the same nnpfc_id are active for the same picture, it is not clear how to distinguish which of the two persistences will be canceled when a new NNPFA SEI message containing the same nnpfa_target_id with an nnpfa_cancel_flag equal to 1 later exists, unless such a case is allowed.

[0362] Example

[0363] The present invention provides solutions to the problems described above. Each embodiment may be performed individually or in combination with two or more embodiments.

[0364] The embodiments proposed by the present invention are summarized as follows.

[0365] 1. nnpfa_target_base_flag can be signaled without any condition on the nnpfa_cancel_flag value.

[0366] 2. If the nnpfa_cancel_flag value is equal to 1, the persistence of a previously activated target NNPF with the same nnpfa_target_id and nnpfa_target_base_flag values ​​can be canceled.

[0367] 3. Alternatively, if there is an NNPFA with a specific nnpfa_target_id and nnpfa_target_base_flag, the persistence of previous NNPFA SEI messages with the same values ​​of nnpfa_target_id and nnpfa_target_base_flag can be canceled according to the output order.

[0368] 4. Alternatively, one could constrain that there are no two (or more) NNPFA SEI messages active for the same picture (i.e., containing nnpfa_cancel_flag equal to 0), regardless of the value of nnpfa_target_base_flag.

[0369] In other words, regardless of the value of nnpfa_target_base_flag, two NNPFA SEI messages with the same nnpfa_target_id and nnpfa_cancel_flag set to 0 are not activated.

[0370] Example 1

[0371] Example 1 provides a description of Summary 1 and Summary 2 described above. The table can be updated as follows.

[0372]

[0373] The NNPFA SEI message can enable or disable the possible use of a target NNPF identified by nnpfa_target_id and nnpfa_target_base_flag for post-processing filtering of a set of pictures. nnpfa_target_base_flag can be parsed without the condition of the nnpfa_cancel_flag value, as shown in Table 23. Therefore, for a particular picture where NNPF is enabled, the target NNPF can be derived as follows.

[0374] - If nnpfa_target_base_flag is equal to 1, the target NNPF can be a base NNPF whose nnpfc_id is equal to nnpfa_target_id.

[0375] - Otherwise (nnpfa_target_base_flag is equal to 0), the target NNPF is the NNPF specified by the last NNPF SEI message with nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order, and may not be a repeat of the NNPFC SEI message containing the base NNPF.

[0376] For example, there may be several NNPFA SEI messages for the same picture if NNPF is meant for different purposes or for filtering different color components.

[0377] nnpfa_target_id may indicate a target NNPF that is associated with the current picture and is specified by one or more NNPFC SEI messages having an nnpfc_id equal to nnpfa_target_id. The nnpfa_target_id value is between 0 and 2. 32 - Must be within the range of 2.

[0378] An NNPFA SEI message with a specific value of nnpfa_target_id shall not be present in the current PU unless one or both of the following conditions are true:

[0379] - Currently, within the CLVS, there may be an NNPFC SEI message having an nnpfc_id that is identical to a specific value of nnpfa_target_id that exists in the PU preceding the current PU in decoding order.

[0380] - There may be an NNPFC SEI message with an nnpfc_id equal to a specific value of nnpfa_target_id in the current PU.

[0381] If a PU includes an NNPFC SEI message having a specific value of nnpfc_id and an NNPFA SEI message having an nnpfa_target_id equal to the specific value of nnpfc_id, the NNPFC SEI message must precede the NNPFA SEI message in decoding order.

[0382] A value of 1 for nnpfa_target_base_flag may indicate that the target NNPF is a base NNPF with an nnpfc_id equal to nnpfa_target_id. A value of 0 for nnpfa_target_base_flag may indicate that the target NNPF is the NNPF specified by the last NNPFC SEI message with an nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repeat of the NNPFC SEI message containing the base NNPF.

[0383] A value of 1 for nnpfa_cancel_flag may indicate that the persistence of the target NNPF established by any previous NNPFA SEI message containing the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message is canceled. That is, the target NNPF may no longer be used unless it is activated by another NNPFA SEI message with the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message and with nnpfa_cancel_flag set to 0. A value of 0 for nnpfa_cancel_flag may indicate that nnpfa_persistence_flag and nnpfa_num_output_entries follow.

[0384] nnpfa_persistence_flag can indicate the persistence of the target NNPF for the current layer.

[0385] A value of 0 for nnpfa_persistence_flag can indicate that the target NNPF can be used to post-process filter only the current picture.

[0386] A value of 1 for nnpfa_persistence_flag may indicate that the target NNPF may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true:

[0387] - A new CLVS for the current layer is started.

[0388] - Bitstream ended

[0389] - The picture of the current layer related to the NNPFA SEI message with the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message and nnpfa_cancel_flag set to 1 is output after the current picture in the output order.

[0390] The target NNPF may not be applied to subsequent pictures of the current layer associated with an NNPFA SEI message that has the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message and has nnpfa_cancel_flag equal to 1. In other words, if the nnpfa_persistence_flag value is 1, the target NNPF may be used until a picture of the current layer is output after the current picture in the output order based on the nnpfa_cancel_flag value equal to 1 included in an NNPFA SEI message that has the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message.

[0391] nnpfcTargetPictures can be set to the set of pictures associated with the last NNPFC SEI message with the same nnpfc_id as the nnpfa_target_id that precedes the current NNPFA SEI message in decoding order. nnpfaTargetPictures can be set to the set of pictures whose target NNPF is activated by the current NNPFA SEI message. It is a conformance requirement of a bitstream that all pictures included in nnpfaTargetPictures must also be included in nnpfcTargetPictures.

[0392] Example 2

[0393] Example 2 provides an explanation of Summaries 1 and 3 described above. The table can be updated as follows.

[0394]

[0395] The NNPFA SEI message can enable or disable the possible use of a target NNPF identified by nnpfa_target_id and nnpfa_target_base_flag for post-processing filtering of a set of pictures. Similar to Example 1, nnpfa_target_base_flag can be parsed without the condition of the nnpfa_cancel_flag value, as shown in Table 24. Therefore, for a specific picture with NNPF enabled, the target NNPF can be derived as follows.

[0396] - If nnpfa_target_base_flag is equal to 1, the target NNPF can be a base NNPF whose nnpfc_id is equal to nnpfa_target_id.

[0397] - Otherwise (nnpfa_target_base_flag is equal to 0), the target NNPF is the NNPF specified by the last NNPF SEI message with nnpfc_id equal to nnpfa_target_id preceding the first VCL NAL unit of the current picture in decoding order, and may not be a repeat of the NNPFC SEI message containing the base NNPF.

[0398] For example, there may be several NNPFA SEI messages for the same picture if NNPF is meant for different purposes or for filtering different color components.

[0399] nnpfa_target_id may indicate a target NNPF associated with the current picture and indicated by one or more NNPFC SEI messages having an nnpfc_id equal to nnpfa_target_id. The nnpfa_target_id value is 0 to 2. 32 - Must be within the range of 2.

[0400] An NNPFA SEI message with a specific value of nnpfa_target_id shall not be present in the current PU unless one or both of the following conditions are true:

[0401] - Currently, within the CLVS, there may be an NNPFC SEI message having an nnpfc_id that is identical to a specific value of nnpfa_target_id that exists in the PU preceding the current PU in decoding order.

[0402] - There may be an NNPFC SEI message with an nnpfc_id equal to a specific value of nnpfa_target_id in the current PU.

[0403] If a PU includes an NNPFC SEI message having a specific value of nnpfc_id and an NNPFA SEI message having an nnpfa_target_id equal to the specific value of nnpfc_id, the NNPFC SEI message must precede the NNPFA SEI message in decoding order.

[0404] A value of 1 for nnpfa_target_base_flag may indicate that the target NNPF is a base NNPF with an nnpfc_id equal to nnpfa_target_id. A value of 0 for nnpfa_target_base_flag may indicate that the target NNPF is the NNPF specified by the last NNPFC SEI message with an nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repeat of the NNPFC SEI message containing the base NNPF.

[0405] A value of 1 for nnpfa_cancel_flag may indicate that the persistence of the target NNPF established by any previous NNPFA SEI message containing the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message is canceled. That is, the target NNPF may no longer be used unless it is activated by another NNPFA SEI message with the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message and with nnpfa_cancel_flag set to 0. A value of 0 for nnpfa_cancel_flag may indicate that nnpfa_persistence_flag and nnpfa_num_output_entries follow.

[0406] nnpfa_persistence_flag can indicate the persistence of the target NNPF for the current layer.

[0407] A value of 0 for nnpfa_persistence_flag can indicate that the target NNPF can be used to post-process filter only the current picture.

[0408] A value of 1 for nnpfa_persistence_flag may indicate that the target NNPF may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true:

[0409] - A new CLVS for the current layer is started.

[0410] - Bitstream ended

[0411] - The picture of the current layer related to the NNPFA SEI message that has the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message is output after the current picture in the output order.

[0412] The target NNPF may not be applied to subsequent pictures of the current layer associated with NNPFA SEI messages having the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message. In other words, if the value of nnpfa_persistence_flag is 1, the target NNPF may be used until a picture of the current layer is output after the current picture in the output order, regardless of the value of nnpfa_cancel_flag included in an NNPFA SEI message having the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message.

[0413] Let nnpfcTargetPictures be the set of pictures associated with the last NNPFC SEI message with an nnpfc_id equal to the nnpfa_target_id that precedes the current NNPFA SEI message in decoding order. Let nnpfaTargetPictures be the set of pictures whose target NNPF is activated by the current NNPFA SEI message. It is a conformance requirement of a bitstream that all pictures included in nnpfaTargetPictures are also included in nnpfcTargetPictures.

[0414] Example 3

[0415] Example 3 provides an explanation of Summary 4 described above. The table can be updated as follows.

[0416]

[0417] The NNPFA SEI message can enable or disable the possible use of a target NNPF identified by nnpfa_target_id and nnpfa_target_base_flag for post-processing filtering of a set of pictures. For a particular picture with NNPF enabled, the target NNPF can be derived as follows.

[0418] - If nnpfa_target_base_flag is equal to 1, the target NNPF can be a base NNPF whose nnpfc_id is equal to nnpfa_target_id.

[0419] - Otherwise (nnpfa_target_base_flag is equal to 0), the target NNPF is the NNPF specified by the last NNPF SEI message with nnpfc_id equal to nnpfa_target_id preceding the first VCL NAL unit of the current picture in decoding order, and may not be a repeat of the NNPFC SEI message containing the base NNPF.

[0420] For example, there may be several NNPFA SEI messages for the same picture if NNPF is meant for different purposes or for filtering different color components.

[0421] nnpfa_target_id may indicate a target NNPF that is associated with the current picture and is specified by one or more NNPFC SEI messages having an nnpfc_id equal to nnpfa_target_id. The nnpfa_target_id value is between 0 and 2. 32 - Must be within the range of 2.

[0422] An NNPFA SEI message with a specific value of nnpfa_target_id shall not be present in the current PU unless one or both of the following conditions are true:

[0423] - Currently, within the CLVS, there may be an NNPFC SEI message with an nnpfc_id that is identical to a specific value of nnpfa_target_id present in the PU preceding the current PU in decoding order.

[0424] - There may be an NNPFC SEI message with an nnpfc_id equal to a specific value of nnpfa_target_id in the current PU.

[0425] If a PU includes an NNPFC SEI message having a specific value of nnpfc_id and an NNPFA SEI message having an nnpfa_target_id equal to the specific value of nnpfc_id, the NNPFC SEI message must precede the NNPFA SEI message in decoding order.

[0426] A value of 1 for nnpfa_cancel_flag may indicate that the persistence of the target NNPF established by any previous NNPFA SEI message containing the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message is canceled. That is, the target NNPF may no longer be used unless it is activated by another NNPFA SEI message with the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message and with nnpfa_cancel_flag set to 0. A value of 0 for nnpfa_cancel_flag may indicate that nnpfa_persistence_flag, nnpfa_persistence_flag, and nnpfa_num_output_entries follow.

[0427] A value of 1 for nnpfa_target_base_flag may indicate that the target NNPF is a base NNPF with an nnpfc_id equal to nnpfa_target_id. A value of 0 for nnpfa_target_base_flag may indicate that the target NNPF is the NNPF specified by the last NNPFC SEI message with an nnpfc_id equal to nnpfa_target_id that precedes the first VCL NAL unit of the current picture in decoding order and is not a repeat of the NNPFC SEI message containing the base NNPF.

[0428] There is a constraint that there should not be two NNPFA SEI messages active for the same picture (i.e., containing nnpfa_cancel_flag equal to 0), regardless of the value of nnpfa_target_base_flag.

[0429] nnpfa_persistence_flag can indicate the persistence of the target NNPF for the current layer.

[0430] A value of 0 for nnpfa_persistence_flag can indicate that the target NNPF can be used to post-process filter only the current picture.

[0431] A value of 1 for nnpfa_persistence_flag may indicate that the target NNPF may be used for post-processing filtering for the current picture and all subsequent pictures of the current layer in output order until one or more of the following conditions are true:

[0432] - A new CLVS for the current layer is started.

[0433] - Bitstream ended

[0434] - The picture of the current layer related to the NNPFA SEI message with the same nnpfa_target_id and nnpfa_target_base_flag as the current SEI message and nnpfa_cancel_flag set to 1 is output after the current picture in the output order.

[0435] The target NNPF may not be applied to subsequent pictures of the current layer associated with an NNPFA SEI message that has the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message and has nnpfa_cancel_flag set to 1.

[0436] nnpfcTargetPictures can be set to the set of pictures associated with the last NNPFC SEI message with the same nnpfc_id as the nnpfa_target_id that precedes the current NNPFA SEI message in decoding order. nnpfaTargetPictures can be set to the set of pictures whose target NNPF is activated by the current NNPFA SEI message. It is a conformance requirement of a bitstream that all pictures included in nnpfaTargetPictures must also be included in nnpfcTargetPictures.

[0437] Image encoding method and image decoding method

[0438] Below, image encoding methods and image decoding methods according to various embodiments of the present invention will be described.

[0439] Fig. 6 is a drawing for explaining an image encoding method of an image encoding device, and Fig. 7 is a drawing for explaining an image decoding method of an image decoding device.

[0440] Referring to FIG. 6, the image encoding device (200) can encode information about at least one neural network that can be used as a post-processing filter into at least one NNPFC SEI message (S610). In other words, the image encoding device (200) can determine at least one neural network that can be used as a post-processing filter, and encode information about the determined at least one neural network into at least one NNPFC SEI message.

[0441] The video encoding device (200) can encode information about the target NNPF, which determines whether the target NNPF applicable to the current picture is activated, into an NNPFA SEI message (S620). In other words, the video encoding device (200) can determine whether the target NNPF applicable to the current picture is activated, and encode information about the determined target NNPF into an NNPFA SEI message.

[0442] The process of determining whether to activate the target NNPF may include a process of determining a target NNPF that can be applied to the current picture, a process of determining whether to cancel the persistence of the target NNPF, and a process of determining the persistence of the target NNPF. For example, the video encoding device (200) may determine a target NNPF that can be applied to the current picture, and determine whether to cancel the persistence of the target NNPF based on the presence of a previous NNPFA SEI message having the same target NNPF identification information. If a previous NNPFA SEI message having the same target NNPF identification information exists, the video encoding device (200) may determine to cancel the persistence of the target NNPF specified by the corresponding NNPFA SEI message. If it is determined not to cancel the persistence of the target NNPF, the video encoding device (200) may determine the persistence of the target NNPF. Information on the target NNPF determined in this way may be encoded in an NNPFA SEI message.

[0443] The video encoding device (200) can encode post-filter coefficients or correlation information for the design of the post-filter into a post-filter hint SEI message (S630). The NNPFC SEI message, the NNPFA SEI message, and / or the post-filter hint SEI message can be included in the NNPF SEI message.

[0444] Referring to FIG. 7, the image decoding device (300) can obtain an SEI message for an NNPF to be applied to the current picture from a bitstream. The SEI message for the NNPF can include an NNPFC SEI message, an NNPFA SEI message, and / or a post-filter hint SEI message.

[0445] The image decoding device (300) can determine at least one neural network that can be used as a post-processing filter based on at least one NNPFC SEI message included in the SEI message for the NNPF when the SEI message for the NNPF is applied to the current picture (S710).

[0446] The video decoding device (300) can determine whether to activate a target NNPF that can be applied to the current picture based on at least one NNPFA SEI message obtained from the bitstream (S720).

[0447] The process of determining whether to activate the target NNPF may include a process of determining the target NNPF, a process of determining whether to cancel the persistence of the target NNPF, a process of determining the persistence of the target NNPF, etc. For example, the process of determining whether to activate the target NNPF may include a process of determining the target NNPF based on an NNPFA SEI message, a process of determining whether to cancel the persistence of the target NNPF, a process of determining the persistence of the target NNPF, etc. Here, the target NNPF identification information may include nnpfa_target_id, or may include nnpfa_target_id and nnpfa_target_base_flag.

[0448] The target NNPF may be determined based on nnpfa_target_id, which is an identifier representing the target NNPF. In various embodiments, the target NNPF may also be determined based on nnpfa_target_id and nnpfa_target_base_flag.

[0449] nnpfa_target_id may indicate a target NNPF specified by one or more NNPFC SEI messages that are related to the current picture and have filter identification information (i.e., nnpfc_id) that is identical to the target NNPF identification information.

[0450] nnpfa_target_base_flag may indicate whether the target NNPF is a base NNPF having the same filter identification information as the target NNPF identification information or an NNPF specified by the last NNPF SEI message preceding the first VCL NAL unit of the current picture in decoding order and having the same identification information. In other words, the target NNPF may be determined as the base NNPF having the same filter identification information as the target NNPF identification information based on the target filter flag. Additionally, the target NNPF may be determined as the NNPF specified by the last NNPFC SEI message preceding the first VCL NAL unit of the current picture in decoding order and having the same filter identification information as the target NNPF identification information based on the target filter flag. In this case, the target NNPF may not be a repetition of the NNPFC SEI message including the base NNPF.

[0451] The video decoding device (300) can determine whether there is a previous NNPFA SEI message having the same target NNPF identification information as the current NNPFA SEI message, and if there is a previous NNPFA SEI message having the same target NNPF identification information as the current NNPFA SEI message, determine whether to cancel the persistence of the target NNPF. In this case, the video decoding device (300) can determine whether to cancel the persistence of the target NNPF based on nnpfa_cancel_flag, which is a persistence cancellation flag indicating whether to cancel the persistence of the target NNPF.

[0452] nnpfa_cancel_flag may indicate whether to cancel the persistence of a target NNPF set by a previous NNPFA SEI message that has the same target NNPF identification as the current SEI message (e.g., the current NNPFA SEI message). For example, if the nnpfa_cancel_flag value is 1, the persistence of a target NNPF set by a previous NNPFA SEI message that includes the same target NNPF identification and target filter flag as the current SEI message may be canceled. At this time, the target NNPF may no longer be used unless it is activated by another NNPFA SEI message that has the same target NNPF identification and target filter flag as the current SEI message and has the nnpfa_cancel_flag value set to 0. For example, if the nnpfa_cancel_flag value is 0, flags indicating the persistence of the target NNPF for the current layer, nnpfa_persistence_flag and nnpfa_target_base_flag, may be derived.

[0453] Depending on various embodiments, if the nnpfa_cancel_flag value is 0, nnpfa_target_base_flag, nnpfa_persistence_flag and nnpfa_num_output_entries may also be derived.

[0454] The video decoding device (300) can determine the persistence of the target NNPF based on the nnpfa_persistence_flag value. For example, if nnpfa_persistence_flag is 0, the target NNPF can be used only for the current picture. For example, if nnpfa_persistence_flag is 1, the target NNPF can be used for the current picture and all subsequent pictures of the current layer in output order. At this time, the target NNPF can be used for the current picture and all subsequent pictures of the current layer in output order until at least one of the following is satisfied: a new CLVS of the current layer starts, a bitstream ends, or a picture of the current layer related to an NNPFA SEI message having the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message and an nnpfa_cancel_flag of 1 is output after the current picture in output order. In other words, the persistence of the target NNPF can be determined based on whether the picture of the current layer associated with the NNPFA SEI message having the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message and nnpfa_cancel_flag equal to 1 is output after the current picture in output order.

[0455] In various embodiments, if nnpfa_persistence_flag is 1, the target NNPF may be used for the current picture and all subsequent pictures of the current layer in output order until a picture of the current layer associated with an NNPFA SEI message having the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message is output after the current picture in output order. In other words, the persistence of the target NNPF may be determined based on whether a picture of the current layer associated with an NNPFA SEI message having the same nnpfa_target_id and nnpfa_target_base_flag as the current NNPFA SEI message is output after the current picture in output order, regardless of the value of nnpfa_cancel_flag included in the NNPFA SEI message associated with the picture of the current layer.

[0456] According to various embodiments, two or more NNPFA SEI messages for the same picture may not be activated regardless of the value of nnpfa_target_base_flag.

[0457] According to various embodiments, the target NNPF may not be applied to subsequent pictures of the current layer associated with an NNPFA SEI message having the same nnpfa_target_id as the current SEI message and an nnpfa_cancel_flag equal to 1.

[0458] FIG. 8 is a diagram for explaining an image decoding method for an embodiment of determining whether a target NNPF is activated.

[0459] Referring to FIG. 8, the video decoding device (300) can determine a target NNPF based on the NNPFA SEI message (S800). For example, the video decoding device (300) can determine a target NNPF based on target NNPF identification information (i.e., nnpfa_target_id) of the NNPFA SEI message. For example, the video decoding device (300) can determine a target NNPF specified by one or more NNPFC SEI messages that are related to the current picture and have an nnpfc_id value that is the same as the nnpfa_target_id value.

[0460] The video decoding device (300) can determine whether to cancel the persistence of the target NNPF (S810). For example, the video decoding device (300) can determine whether to cancel the persistence of the target NNPF based on the persistence cancellation flag (i.e., nnpfa_cancel_flag) indicating whether to cancel the persistence of the target NNPF.

[0461] For example, if the persistence cancel flag value is 1, the video decoding device (300) may determine to cancel the persistence of the target NNPF established by any previous NNPFA SEI message having the same target NNPF identification information as the current SEI message. In other words, the target NNPF may no longer be used unless it is activated by another NNPFA SEI message having the same target NNPF identification information as the current SEI message and having the persistence cancel flag value set to 0. For example, if the persistence cancel flag value is 0, the video decoding device (300) may determine not to cancel the persistence of the target NNPF.

[0462] The video decoding device (300) may determine the persistence of the target NNPF based on whether the persistence of the target NNPF is canceled (S830). For example, if the persistence of the target NNPF is not canceled, the video decoding device (300) may determine to use the target NNPF only for post-processing filtering for the current picture, or may determine to use the target NNPF for post-processing filtering for the current picture and all subsequent pictures within the current layer in output order until the above-described condition is met.

[0463] In this way, when the persistence of the target NNPF is determined, the image decoding device (300) can determine or continue the activation of the target NNPF.

[0464] Figures 9 to 11 are drawings for explaining various embodiments of whether to cancel the persistence of the target NNPF.

[0465] As shown in Fig. 9, if the nnpfa_cancel_flag value of the current NNPFA SEI message is 1, and if there is a previous NNPFA SEI message with the same target NNPF identification information as the current NNPFA SEI message (i.e., the nnpfa_target_id value is 1 and the nnpfa_target_base_flag value is 1), persistence for the target NNPF specified by the NNPFC SEI message with the nnpfc_id value is 1 and the nnpfc_base_flag value is 1 can be canceled.

[0466] As shown in FIG. 10, if there is a previous NNPFA SEI message with the same target NNPF identification information as the current NNPFA SEI message (i.e., the nnpfa_target_id value is 1 and the nnpfa_target_base_flag value is 1), persistence for the target NNPF may be canceled regardless of the nnpfa_cancel_flag value included in the current NNPFA SEI message.

[0467] As shown in Figure 11, persistence for a target NNPF may be canceled if there is a previous NNPFA SEI message with the same target NNPF identification information as the current NNPFA SEI message (i.e., the nnpfa_target_id value is 1).

[0468] FIG. 12 is a diagram illustrating an example of a content streaming system to which an embodiment according to the present disclosure can be applied.

[0469] As illustrated in FIG. 12, a content streaming system to which an embodiment of the present disclosure is applied may largely include an encoding server, a streaming server, a web server, a media storage, a user device, and a multimedia input device.

[0470] The encoding server compresses content input from multimedia input devices such as smartphones, cameras, and camcorders into digital data, generates a bitstream, and transmits it to the streaming server. Alternatively, if multimedia input devices such as smartphones, cameras, and camcorders directly generate bitstreams, the encoding server may be omitted.

[0471] The above bitstream can be generated by an image encoding method and / or an image encoding device to which an embodiment of the present disclosure is applied, and the streaming server can temporarily store the bitstream during the process of transmitting or receiving the bitstream.

[0472] The streaming server transmits multimedia data to a user device based on a user request via a web server, and the web server can act as an intermediary to inform the user of available services. When a user requests a desired service from the web server, the web server transmits the request to the streaming server, and the streaming server can transmit multimedia data to the user. At this time, the content streaming system may include a separate control server, and in this case, the control server may control commands / responses between each device within the content streaming system.

[0473] The streaming server can receive content from a media repository and / or encoding server. For example, when receiving content from the encoding server, the content can be received in real time. In this case, to provide a smooth streaming service, the streaming server can store the bitstream for a certain period of time.

[0474] Examples of the user devices may include mobile phones, smart phones, laptop computers, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), navigation devices, slate PCs, tablet PCs, ultrabooks, wearable devices (e.g., smartwatches, smart glasses, HMDs), digital TVs, desktop computers, digital signage, etc.

[0475] Each server within the above content streaming system can be operated as a distributed server, in which case data received from each server can be processed in a distributed manner.

[0476] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that cause operations according to the methods of various embodiments to be executed on a device or a computer, and a non-transitory computer-readable medium having such software or instructions stored thereon and executable on the device or computer.

[0477] Embodiments according to the present disclosure can be used to encode / decode images.

Claims

1. In a video decoding method performed by a video decoding device, Obtaining an NNPF (neural-network post-filter) SEI (supplemental enhancement information) message, wherein the NNPF SEI message includes an NNPFC (neural-network post-filter characteristics) SEI message and an NNPFA (neural-network post-filter activation) SEI message, A step of determining a neural network that can be used as a post-processing filter based on the above NNPFC SEI message; and A step of determining whether to activate a target NNPF applicable to the current picture based on the NNPFA SEI message, A video decoding method, wherein the target NNPF is used to perform post-processing filtering on the current picture and subsequent pictures of the current layer in the output order until a picture of the current layer related to an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output after the current picture in the output order.

2. In the first paragraph, the step of determining whether the target NNPF is activated is as follows: A step of determining the above target NNPF; A step of determining whether to cancel the persistence of the above target NNPF; and An image decoding method, comprising a step of determining the persistence of the target NNPF based on not canceling the persistence of the target NNPF.

3. In paragraph 1, the target NNPF is A method for decoding an image, wherein the target NNPF identification information is determined based on target NNPF identification information that indicates a target NNPF specified by one or more NNPFC SEI messages associated with the current picture and having the same NNPF identification information as the NNPFA SEI message.

4. In paragraph 2, whether the continuity of the target NNPF is cancelled or not, A video decoding method, wherein the determination is based on a persistence cancellation flag indicating whether to cancel the persistence of the target NNPF set by a previous NNPFA SEI message having the same target NNPF identification information as the current SEI message.

5. In the second paragraph, the sustainability of the target NNPF is A video decoding method, wherein the decision is made based on whether the picture of the current layer is output after the current picture in the output order, regardless of the value of the persistence cancellation flag of the NNPFA SEI message related to the picture of the current layer.

6. An image encoding method performed by an image encoding device, A step of encoding a neural network that can be used as a post-processing filter into a neural-network post-filter characteristics (NNPFC) SEI (supplemental enhancement information) message; and Including a step of encoding whether the target NNPF applicable to the current picture is activated as a NNPFA (neural-network post-filter activation) SEI message, A video encoding method, wherein the target NNPF is used to perform post-processing filtering on the current picture and subsequent pictures within the current layer in the output order until a picture of the current layer related to an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output after the current picture in the output order.

7. In paragraph 6, whether the target NNPF is activated or not is A video encoding method, wherein the method comprises determining the target NNPF, determining whether to cancel the persistence of the target NNPF, and determining the persistence of the target NNPF based on not canceling the persistence of the target NNPF.

8. In paragraph 6, the target NNPF is A method of encoding a video, wherein the target NNPF identification information is determined based on target NNPF identification information that indicates a target NNPF specified by one or more NNPFC SEI messages associated with the current picture and having the same NNPF identification information as the NNPFA SEI message.

9. In paragraph 7, whether the continuity of the target NNPF is cancelled or not, A video encoding method, wherein the determination is based on a persistence cancellation flag indicating whether to cancel the persistence of the target NNPF set by a previous NNPFA SEI message having the same target NNPF identification information as the current SEI message.

10. In paragraph 7, the sustainability of the target NNPF is A video encoding method, wherein the decision is made based on whether the picture of the current layer is output after the current picture in the output order, regardless of the value of the persistence cancellation flag of the NNPFA SEI message related to the picture of the current layer.

11. A computer-readable recording medium storing a bitstream generated by a video encoding method, wherein the bitstream comprises: At least one NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message representing a neural network that can be used as a post-processing filter, and Contains a neural-network post-filter activation (NNPFA) SEI message indicating whether a target neural network post-processing filter that can be applied to the current picture is activated, A computer-readable recording medium, wherein the target NNPF is used for post-processing filtering of the current picture and subsequent pictures within the current layer in the output order until a picture of the current layer associated with an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output after the current picture in the output order.

12. In a transmission method for transmitting data about an image, the transmission method comprises: Generate a bitstream for the above video, wherein the bitstream is: It is generated based on a step of encoding a neural network that can be used as a post-processing filter into an NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message; and a step of encoding whether a target neural network post-processing filter that can be applied to the current picture is activated into an NNPFA (neural-network post-filter activation) SEI message. A step of transmitting the data including the bitstream, A transmission method in which the target NNPF is used to perform post-processing filtering on the current picture and subsequent pictures within the current layer in the output order until a picture of the current layer associated with an NNPFA SEI message having the same target NNPF identification information as the current SEI message is output after the current picture in the output order.

Images