IMAGE ENCODING / DECODING METHOD, BITSTREAM TRANSMISSION METHOD, AND RECORDING MEDIUM THAT STORES THE BITSTREAM

Abstract

An image encoding / decoding method, a bitstream transmission method, and a computer-readable recording medium for storing a bitstream are provided. The image decoding method according to the present invention is an image decoding method carried out by an image decoding device and may be an image decoding method comprising the steps of: obtaining size information from a Supplementary Enhancement Information (SEI) message of neural network post-filter features (NNPFC); and determining the size of an output image based on the size information, wherein the size information comprises information about the numerator value of the ratio between the size of the output image and the size of an input image and information about the denominator value of the ratio.

Description

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

[0001] The present disclosure relates to a video encoding / decoding method, a method for transmitting a bitstream, and a recording medium storing a bitstream, and relates to a method for processing information about the size of a picture.

[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 signaling size information.

[0006] Additionally, the present disclosure aims to provide a method for determining the size of a picture based on signaled size information.

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

[0008] 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.

[0009] 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.

[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 size information from a neural-network post-filter characteristics (NNPFC) SEI (supplemental enhancement information) message; and a step of determining a size of an output picture based on the size information, wherein the size information includes information on a numerator value of a ratio between a size of the output picture and a size of an input picture and information on a denominator value of the ratio.

[0012] According to another aspect of the present disclosure, a video encoding method is performed by a video encoding device, the video encoding method comprising: a step of determining a ratio between a size of an output picture and a size of an input picture; and a step of encoding size information about the ratio into a neural-network post-filter characteristics (NNPFC) supplemental enhancement information (SEI) message, wherein the size information includes information about a numerator value of the ratio and information about a denominator value of the ratio.

[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, size information can be signaled efficiently.

[0018] Additionally, according to the present disclosure, the size of an output picture can be adaptively determined in response to a change in the size of an input picture.

[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 is a drawing for explaining an interleaved method for deriving a luma channel.

[0027] FIG. 5 is a flowchart for explaining an image encoding method according to one embodiment of the present disclosure.

[0028] FIG. 6 is a diagram for explaining an image decoding method according to one embodiment of the present disclosure.

[0029] FIG. 7 is a flowchart for explaining an image encoding method according to another embodiment of the present disclosure.

[0030] FIG. 8 is a diagram for explaining an image decoding method according to another embodiment of the present disclosure.

[0031] FIG. 9 is a flowchart illustrating an image encoding method according to another embodiment of the present disclosure.

[0032] FIG. 10 is a diagram for explaining an image decoding method according to another embodiment of the present disclosure.

[0033] FIG. 11 is a diagram exemplifying a content streaming system to which an embodiment according to the present disclosure can be applied.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] The present disclosure relates to encoding and decoding of images, and terms used in the present disclosure may have their usual meanings commonly used in the technical field to which the present disclosure belongs, unless newly defined in the present disclosure.

[0041] In the present disclosure, a "picture" generally refers to a unit representing one image of a specific time period, and a slice / tile is a coding unit that constitutes a part of a picture, and a single picture may be composed of one or more slices / tiles. In addition, a slice / tile may include one or more coding tree units (CTUs).

[0042] 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.

[0043] 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. In some cases, the term "unit" may be used interchangeably with terms such as "sample array," "block," or "area." In general, an MxN block may include a set (or array) of samples (or sample array) or transform coefficients consisting of M columns and N rows.

[0044] 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."

[0045] 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."

[0046] 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."

[0047] 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."

[0048] Video Coding System Overview

[0049] FIG. 1 is a diagram schematically illustrating a video coding system to which an embodiment according to the present disclosure can be applied.

[0050] 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 via a digital storage medium or a network.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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).

[0055] 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).

[0056] The rendering unit (23) can render the decrypted video / image. The rendered video / image can be displayed through the display unit.

[0057] Overview of the video encoding device

[0058] FIG. 2 is a schematic diagram illustrating an image encoding device to which an embodiment according to the present disclosure can be applied.

[0059] As illustrated in FIG. 2, the image encoding device (100) may include an image segmentation unit (110), a subtraction unit (115), a transformation unit (120), a quantization unit (130), an inverse quantization unit (140), an inverse transformation unit (150), an addition unit (155), a filtering unit (160), a memory (170), an inter prediction unit (180), an intra prediction unit (185), and an entropy encoding unit (190). The inter prediction unit (180) and the intra prediction unit (185) may be collectively referred to as a “prediction unit.” The transformation unit (120), the quantization unit (130), the inverse quantization unit (140), and the inverse transformation unit (150) may be included in a residual processing unit. The residual processing unit may further include a subtraction unit (115).

[0060] All or at least some of the plurality of components constituting the video encoding device (100) may be implemented as a single hardware component (e.g., an encoder or a processor) according to an embodiment. In addition, the memory (170) may include a decoded picture buffer (DPB) and may be implemented by a digital storage medium.

[0061] The image segmentation unit (110) can segment an input image (or picture, frame) input to the image encoding device (100) 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. The maximum coding unit can be used directly as the final coding unit, and the coding unit of the lower depth obtained by dividing the maximum coding unit can be used as the final coding unit. Here, the coding procedure may include procedures such as prediction, transformation, and / or restoration described below. 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 prediction unit may be a unit of sample prediction, and the transformation unit may be a unit for deriving a transform coefficient and / or a unit for deriving a residual signal from a transform coefficient.

[0062] The prediction unit (inter-prediction unit (180) or intra-prediction unit (185)) 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 can determine whether intra-prediction or inter-prediction is applied to the current block or CU unit. The prediction unit can generate various information regarding the prediction of the current block and transmit the information to the entropy encoding unit (190). The information regarding the prediction can be encoded by the entropy encoding unit (190) and output in the form of a bitstream.

[0063] The intra prediction unit (185) 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 (185) 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 (180) 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 from each other. 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 (180) 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 (180) 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 can generate a prediction signal based on various prediction methods and / or prediction techniques described below. For example, the prediction unit 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 may perform intra block copy (IBC) to predict the current block. Intra block copy can be used for video / image coding of content 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 can 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 can be used to generate a restoration signal or a residual signal. The subtraction unit (115) 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 from the input image signal (original block, original sample array). The generated residual signal can be transmitted to the conversion unit (120).

[0067] The transform unit (120) 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 (130) can quantize the transform coefficients and transmit them to the entropy encoding unit (190). The entropy encoding unit (190) 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 (130) can rearrange the quantized transform coefficients in a block form into a one-dimensional vector form based on a 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 (190) can perform various encoding methods, such as, for example, exponential Golomb, context-adaptive variable length coding (CAVLC), and context-adaptive binary arithmetic coding (CABAC). The entropy encoding unit (190) can also encode, together or separately, information necessary for video / image restoration (e.g., values ​​of syntax elements) 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 signaling information, transmitted information and / or syntax elements mentioned in the present disclosure 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 (190) and / or a storage unit (not shown) for storing the signal may be provided as an internal / external element of the video encoding device (100), or the transmission unit may be provided as a component of the entropy encoding unit (190).

[0071] The quantized transform coefficients output from the quantization unit (130) 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 (140) and inverse transformation unit (150), a residual signal (residual block or residual samples) can be restored.

[0072] The addition unit (155) 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 (180) or the intra prediction unit (185). When there is no residual for the block to be processed, such as when skip mode is applied, the predicted block can be used as the reconstructed block. The addition unit (155) can be called a reconstructor 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 (160) can improve subjective / objective picture quality by applying filtering to the restoration signal. For example, the filtering unit (160) can apply various filtering methods to the restoration picture to generate a modified restoration picture, and store the modified restoration picture in the memory (170), specifically, in the DPB of the memory (170). The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, etc. The filtering unit (160) can generate various information regarding filtering and transmit the information to the entropy encoding unit (190), as described later in the description of each filtering method. The information regarding filtering may be encoded by the entropy encoding unit (190) and output in the form of a bitstream.

[0074] The modified restored picture transmitted to the memory (170) can be used as a reference picture in the inter prediction unit (180). Through this, when inter prediction is applied, the image encoding device (100) can avoid prediction mismatch between the image encoding device (100) and the image decoding device, and can also improve encoding efficiency.

[0075] The DPB in the memory (170) can store a modified reconstructed picture to be used as a reference picture in the inter prediction unit (180). The memory (170) 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 (180) to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory (170) can store reconstructed samples of reconstructed blocks in the current picture and transfer them to the intra prediction unit (185).

[0076] Video Decryption 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 (200) may be configured to include an entropy decoding unit (210), an inverse quantization unit (220), an inverse transformation unit (230), an addition unit (235), a filtering unit (240), a memory (250), an inter prediction unit (260), and an intra prediction unit (265). The inter prediction unit (260) and the intra prediction unit (265) may be collectively referred to as a “prediction unit.” The inverse quantization unit (220) and the inverse transformation unit (230) may be included in a residual processing unit.

[0079] All or at least some of the plurality of components constituting the video decoding device (200) may be implemented as a single hardware component (e.g., a decoder or processor) depending on the embodiment. In addition, the memory (170) may include a DPB and may be implemented by a digital storage medium.

[0080] The video decoding device (200) that receives a bitstream including video / image information can restore the image by performing a process corresponding to the process performed in the video encoding device (100) of FIG. 2. For example, the video decoding device (200) can perform decoding using a processing unit applied in the video encoding device. 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 a maximum coding unit. In addition, the restored image signal decoded and output by the video decoding device (200) can be reproduced through a reproduction device (not shown).

[0081] The video decoding device (200) can receive a signal output from the video encoding device of FIG. 2 in the form of a bitstream. The received signal can be decoded through the entropy decoding unit (210). For example, the entropy decoding unit (210) 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 may additionally use 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 (210) can decode information in the bitstream based on a coding method such as exponential Golomb coding, CAVLC, or CABAC, and output the values ​​of syntax elements 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 (210) is provided to the prediction unit (inter prediction unit (260) and intra prediction unit (265)), and the residual value on which entropy decoding is performed by the entropy decoding unit (210), i.e., quantized transform coefficients and related parameter information, can be input to the inverse quantization unit (220). In addition, information regarding filtering among the information decoded by the entropy decoding unit (210) can be provided to the filtering unit (240). Meanwhile, a receiving unit (not shown) that receives a signal output from an image encoding device may be additionally provided as an internal / external element of the image decoding device (200), or the receiving unit may be provided as a component of an entropy decoding unit (210).

[0082] Meanwhile, the video decoding device according to the present disclosure may be referred to as a video / video / picture decoding device. The video decoding device 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 (210), and the sample decoder may include at least one of an inverse quantization unit (220), an inverse transformation unit (230), an addition unit (235), a filtering unit (240), a memory (250), an inter prediction unit (260), and an intra prediction unit (265).

[0083] The inverse quantization unit (220) can inverse quantize the quantized transform coefficients and output the transform coefficients. The inverse quantization unit (220) 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. The inverse quantization unit (220) can perform inverse quantization on the quantized transform coefficients using quantization parameters (e.g., quantization step size information) and obtain transform coefficients.

[0084] In the inverse transform unit (230), the transform coefficients can be inversely transformed to obtain a residual signal (residual block, residual sample array).

[0085] The prediction unit can perform a prediction on the current block and generate a predicted block containing prediction samples for the current block. The prediction unit can determine whether intra-prediction or inter-prediction is applied to the current block based on the prediction information output from the entropy decoding unit (210), and can determine a specific intra / inter-prediction mode (prediction technique).

[0086] The fact that the prediction unit can generate a prediction signal based on various prediction methods (techniques) described later is the same as that mentioned in the description of the prediction unit of the image encoding device (100).

[0087] The intra prediction unit (265) can predict the current block by referring to samples within the current picture. The description of the intra prediction unit (185) can be equally applied to the intra prediction unit (265).

[0088] The inter prediction unit (260) 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 (260) 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.

[0089] The addition unit (235) 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 (including the inter prediction unit (260) and / or the intra prediction unit (265)). 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 (155) can be equally applied to the addition unit (235). The addition unit (235) 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.

[0090] The filtering unit (240) can improve subjective / objective image quality by applying filtering to the restored signal. For example, the filtering unit (240) can apply various filtering methods to the restored picture to generate a modified restored picture, and store the modified restored picture in the memory (250), specifically, in the DPB of the memory (250). The various filtering methods can include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, etc.

[0091] The (modified) reconstructed picture stored in the DPB of the memory (250) can be used as a reference picture in the inter prediction unit (260). The memory (250) 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 transferred to the inter prediction unit (260) to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory (250) can store reconstructed samples of reconstructed blocks within the current picture and transfer them to the intra prediction unit (265).

[0092] In this specification, the embodiments described in the filtering unit (160), the inter prediction unit (180), and the intra prediction unit (185) of the image encoding device (100) can be applied to the filtering unit (240), the inter prediction unit (260), and the intra prediction unit (265) of the image decoding device (200) in the same or corresponding manner, respectively.

[0093] Neural-network post-filter characteristics (NNPFC)

[0094] The combinations in Tables 1 to 3 represent the NNPFC syntax structure.

[0095]

[0096]

[0097]

[0098] The NNPFC syntax structures of Tables 1 to 3 can be signaled in the form of supplemental enhancement information (SEI) messages. An SEI message signaling the NNPFC syntax structures of Tables 1 to 2 may be referred to as an NNPFC SEI message.

[0099] 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 for specific pictures can be indicated using the neural-network post-filter activation (NNPFA) SEI message. Here, "post-processing filter" and "post-filter" can have the same meaning.

[0100] Using these SEI messages may require defining the following variables:

[0101] - The width and height of the input picture can be cropped in luma sample units, and this width and height can be expressed as CroppedWidth and CroppedHeight, respectively.

[0102] - CroppedYPic[idx], which is a luma sample array of input pictures, and CroppedCbPic[idx] and CroppedCrPic[idx], which are chroma sample arrays, can be used as inputs to NNPF if they exist, and the index idx can have a range from 0 to numInputPics-1.

[0103] - BitDepth Y can represent the bit depth for the luma sample array of input pictures.

[0104] - BitDepth C may represent the bit depth of the chroma sample arrays (if any) of the input pictures.

[0105] - ChromaFormatIdc can represent a chroma format identifier.

[0106] - If the value of nnpfc_auxiliary_inp_idc is 1, the filtering strength control value StrengthControlVal must be a real number in the range of 0 to 1.

[0107] An input picture with 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 whose index i is in the range of 1 to numInputPics - 1 may have precedence over an input picture with index i-1 in the output order.

[0108] If nnpfc_purpose & 0x08 is not equal to 0 and the input picture with index 0 is associated with a frame packing array SEI message with fp_arrangement_type equal to 5, then all input pictures may be associated with frame packing array SEI messages with fp_arrangement_type equal to 5 and have the same value as fp_current_frame_is_frame0_flag.

[0109] 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 active for the same picture, the two or more NNPFC SEI messages can have the same or different nnpfc_purpose and nnpfc_mode_idc values.

[0110] nnpfc_purpose may indicate the purpose of the NNPF as shown in Table 4. The value of nnpfc_purpose may be restricted to exist in the range of 0 to 63 in the bitstream. The value of nnpfc_purpose in the range of 64 to 65 535 may be reserved for future use. Decoders shall ignore NNPFC SEI messages with nnpfc_purpose in the range of 64 to 65 535. If the value of nnpfc_purpose is reserved for future use, the syntax elements of this SEI message may be extended with syntax elements that exist provided that nnpfc_purpose is equal to that value. If ChromaFormatIdc is equal to 3, nnpfc_purpose & 0x02 shall be equal to 0. If ChromaFormatIdc or nnpfc_purpose & 0x02 is not equal to 0, then nnpfc_purpose & 0x20 must be equal to 0.

[0111]

[0112] nnpfc_id may contain an identification number that can be used to identify the NNPF. The nnpfc_id value is 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.

[0113] 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 following may apply:

[0114] - The above SEI message may represent a base NNPF.

[0115] - 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.

[0116] An NNPFC SEI message may be a repetition of a previous NNPFC SEI message within the current CLVS in decoding order, and subsequent semantics may apply as if this SEI message were the only NNPFC SEI message with the same content within the current CLVS.

[0117] A value of nnpfc_mode_idc of 0 indicates that the SEI message may contain a bitstream representing the default NNPF or may represent an update relative to the default NNPF with the same nnpfc_id value.

[0118] If the NNPFC SEI message is the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS, a value of 1 in 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.

[0119] If the NNPFC SEI message is neither the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS nor is it a repeat of the first NNPFC SEI message, a value of 1 in nnpfc_mode_idc may indicate that updates related to the underlying NNPF with the same nnpfc_id value are defined by a URI denoted by nnpfc_uri using the format identified by the tag URI nnpfc_tag_uri.

[0120] The value of nnpfc_mode_idc may be constrained to range from 0 to 1 in the bitstream. Values ​​of nnpfc_mode_idc in the range 2 to 255 may be 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 may not be present in the bitstream and may not be reserved for future use.

[0121] If the above SEI message is the first NNPFC SEI message in decoding order with a specific nnpfc_id value within the current CLVS, the NNPF PostProcessingFilter() may be assigned the same as the default NNPF.

[0122] If the above SEI message is not the first NNPFC SEI message in decoding order with a specific nnpfc_id value within the current CLVS and is not a repeat of the first NNPFC SEI message, the NNPF PostProcessingFilter() may be obtained by applying the update defined by the above SEI message to the base NNPF.

[0123] Updates are not cumulative; rather, each update may be applied to the default NNPF, which is the NNPF specified by the first NNPFC SEI message in decoding order with a particular nnpfc_id value within the current CLVS.

[0124] nnpfc_reserved_zero_bit_a may be restricted to have a value equal to 0 due to bitstream restrictions. Decoders may be restricted to ignore NNPFC SEI messages where the value of nnpfc_reserved_zero_bit_a is not 0.

[0125] The nnpfc_tag_uri may contain a tag URI with syntax and semantics specified in IETF RFC 4151 that identifies a neural network used as the primary NNPF or an update to the primary NNPF using the nnpfc_id value specified by the nnpfc_uri. The nnpfc_tag_uri allows for uniquely identifying the format of the neural network data specified by the nnrpf_uri without the need for a central registry. An nnpfc_tag_uri equal to "tag:iso.org,2023:15938-17" may indicate that the neural network data identified by the nnpfc_uri is ISO / IEC 15938-17 compliant.

[0126] nnpfc_uri may contain a URI with syntax and semantics specified in IETF Internet Standard 66 that identifies the neural network used as the default NNPF or an update related to the default NNPF using the same nnpfc_id value.

[0127] A value of nnpfc_property_present_flag of 1 may indicate the presence of syntax elements related to filter purpose, input formatting, output formatting, and complexity. A value of nnpfc_property_present_flag of 0 may indicate the absence of syntax elements related to filter purpose, input formatting, output formatting, and complexity. The value of nnpfc_property_present_flag may be constrained to be equal to 1 if the SEI message is the first NNPFC SEI message in decoding order and has a particular nnpfc_id value within the current CLVS. When the value of nnpfc_property_present_flag is equal to 0, the values ​​of all syntax elements that are present only when the value of nnpfc_property_present_flag is 1 and for which no inferred value has been specified may be inferred to be equal to the corresponding syntax elements in the NNPFC SEI message that contains the underlying NNPF for which the SEI provides updates.

[0128] A value of 1 for nnpfc_base_flag can indicate that the SEI message refers to the base NNPF. A value of 0 for nnpfc_base_flag can indicate that the SEI message refers to an update related to the base NNPF. If nnpfc_base_flag does not exist, the value of 0 for nnpfc_base_flag can be inferred.

[0129] The following restrictions may apply to the value of nnpfc_base_flag:

[0130] - If the NNPFC SEI message is the first NNPFC SEI message with a particular nnpfc_id value within the current CLVS in decoding order, the value of nnpfc_base_flag may be equal to 1.

[0131] - If NNPFC SEI message nnpfcB is not the first NNPFC SEI message with a particular nnpfc_id value within the current CLVS in decoding order and the value of nnpfc_base_flag is equal to 1, then the NNPFC SEI message may correspond to a repetition of the first NNPFC SEI message nnpfcA with the same nnpfc_id in decoding order. That is, the payload content of nnpfcB may be identical to the payload content of nnpfcA.

[0132] If the NNPFC SEI message is not the first NNPFC SEI message with a particular nnpfc_id value within the current CLVS in decoding order and is not a repeat of the first NNPFC SEI message with a particular nnpfc_id value, the following may apply:

[0133] - SEI messages can define updates relative to the underlying NNPF that has the same nnpfc_id value and precedes it in decoding order.

[0134] - The SEI message is associated only with the current restored picture of the current layer and all subsequent restored pictures in output order, up to the end of the current CLVS or the restored picture following the current restored picture within the current CLVS, and is associated with subsequent NNPFC SEI messages with a specific nnpfc_id value within the current CLVS, whichever is earlier in decoding order.

[0135] If the NNPFC SEI message nnpfcCurr is not the first NNPFC SEI message with a particular nnpfc_id value within the current CLVS in decoding order, is not a repeat of the first NNPFC SEI message with a particular nnpfc_id value (i.e., nnpfc_base_flag has a value of 0), and nnpfc_property_present_flag has a value of 1, the following restrictions may apply:

[0136] - The value of nnpfc_purpose in an NNPFC SEI message must be identical to the value of nnpfc_purpose in the first NNPFC SEI message with a specific nnpfc_id value within the current CLVS in decoding order.

[0137] - The values ​​of the syntax elements nnpfc_base_flag and preceding nnpfc_complexity_info_present_flag in the NNPFC SEI message must be identical to the values ​​of the corresponding syntax elements in the first NNPFC SEI message with a specific nnpfc_id value in the current CLVS in decoding order.

[0138] - In decoding order, the nnpfc_complexity_info_present_flag in the first NNPFC SEI message with a specific nnpfc_id value within the current CLVS must be equal to 0 or all 1s, and the following may apply:

[0139] (1) nnpfc_parameter_parameter_type_idc in nnpfcCurr must be the same as nnpfc_parameter_parameter_type_idc in nnpfcBase.

[0140] (2) If nnpfc_log2_parameter_bit_length_minus3 exists in nnpfcCurr, nnpfc_log2_parameter_bit_length_minus3 in nnpfcCurr must be less than or equal to nnpfc_log2_parameter_bit_length_minus3 in nnpfcBase.

[0141] (3) If nnpfc_num_parameters_idc in nnpfcBase is equal to 0, nnpfc_num_parameters_idc in nnpfcCurr must be equal to 0.

[0142] (4) Otherwise (nnpfc_num_parameters_idc in nnpfcBase is greater than 0), nnpfc_num_parameters_idc in nnpfcCurr must be greater than 0 or less than or equal to nnpfc_num_parameters_idc in nnpfcBase.

[0143] (5) If nnpfc_num_kmac_operations_idc in nnpfcBase is equal to 0, nnpfc_num_kmac_operations_idc in nnpfcCurr must be equal to 0.

[0144] (6) Otherwise (nnpfc_num_kmac_operations_idc in nnpfcBase is greater than 0), nnpfc_num_kmac_operations_idc in nnpfcCurr must be greater than 0 and less than or equal to nnpfc_num_kmac_operations_idc in nnpfcBase.

[0145] (7) If nnpfc_total_kilobyte_size in nnpfcBase is equal to 0, nnpfc_total_kilobyte_size in nnpfcCurr must be equal to 0.

[0146] (8) Otherwise (nnpfc_total_kilobyte_size in nnpfcBase is greater than 0), nnpfc_total_kilobyte_size in nnpfcCurr must be greater than 0 or less than or equal to nnpfc_total_kilobyte_size in nnpfcBase.

[0147] nnpfc_out_sub_c_flag can represent the values ​​of variables outSubWidthC and outSubHeightC when nnpfc_purpose & 0x02 are not equal to 0. A value of 1 for nnpfc_out_sub_c_flag can represent 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 represent 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.

[0148] nnpfc_out_colour_format_idc can indicate the color format of the NNPFC output and the values ​​of the variables outSubWidthC and outSubHeightC accordingly when nnpfc_purpose & 0x20 are not equal to 0. A value of 1 in nnpfc_out_colour_format_idc can indicate that the color format of the NNPFC output is a 4:2:0 format, and both outSubWidthC and outSubHeightC are equal to 2. A value of 2 in nnpfc_out_colour_format_idc can indicate that the color format of the NNPFC output is a 4:2:2 format, outSubWidthC is 2, and outSubHeightC is 1. A value of 3 in nnpfc_out_colour_format_idc can indicate that the color format of the NNPFC output is a 4:2:4 format, and both outSubWidthC and outSubHeightC are 1. The value of nnpfc_out_colour_format_idc may be restricted to not be equal to 0.

[0149] If both nnpfc_purpose & 0x02 and nnpfc_purpose & 0x20 are equal to 0, then outSubWidthC and outSubHeightC can be inferred to be equal to SubWidthC and SubHeightC, respectively.

[0150] nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples may represent the width and height, respectively, of the luma sample array of the picture resulting from applying the NNPF identified by nnpfc_id to the cropped decoded output picture. If nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples do not exist, they may be inferred to be equal to CroppedWidth and CroppedHeight, respectively. The value of nnpfc_pic_width_in_luma_samples must be in the range CroppedWidth through CroppedWidth * 16 - 1. The value of nnpfc_pic_height_in_luma_samples must be in the range of CroppedHeight to CroppedHeight * 16 - 1.

[0151] nnpfc_num_input_pics_minus1 + 1 may represent the number of decoded output pictures used as input to NNPF. The value of nnpfc_num_input_pics_minus1 may be constrained to be in the range of 0 to 63.

[0152] nnpfc_interpolated_pics[ i ] may 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. The value of nnpfc_interpolated_pics[ i ] may be constrained to be within the range of 0 to 63. The value of nnpfc_interpolated_pics[ i ] may be constrained to be greater than 0 for at least one i within the range of 0 to nnpfc_num_input_pics_minus1 - 1.

[0153] A value of 1 in nnpfc_input_pic_output_flag[ i ] may indicate that NNPF generates a 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 a corresponding output picture for the i-th input picture.

[0154] The variable numInputPics, which represents the number of pictures used as input to NNPF, and the variable numOutputPics, which represents the total number of pictures generated as a result of NNPF, can be derived as shown in Table 5.

[0155]

[0156] A value of 1 for 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. A value of 0 for 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.

[0157] 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.

[0158] 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.

[0159] nnpfc_inp_format_idc can indicate how to convert the sample values ​​of the cropped decoded output picture into the input values ​​of NNPF. If nnpfc_inp_format_idc is 0, the input values ​​to NNPF are real numbers, and the InpY() and InpC() functions can be specified as in Equation 1.

[0160]

[0161] If the value of nnpfc_inp_format_idc is 1, the input values ​​of NNPF are unsigned integer numbers, and the InpY() and InpC() functions can be derived as shown in Table 6.

[0162]

[0163] Variable inpTensorBitDepth Ycan be derived from the syntax element nnpfc_inp_tensor_luma_bitdepth_minus8 described below. inpTensorBitDepth C can be derived from the syntax element nnpfc_inp_tensor_chroma_bitdepth_minus8 described below.

[0164] 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.

[0165] nnpfc_inp_tensor_luma_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 2.

[0166]

[0167] The value of nnpfc_inp_tensor_luma_bitlength_minus8 may be constrained to be in the range 0 to 24.

[0168] 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 3.

[0169]

[0170] The value of nnpfc_inp_tensor_chroma_bitdepth_minus8 may be constrained to be in the range 0 to 24.

[0171] nnpfc_inp_order_idc may indicate how to align the sample array of the cropped decoded output picture to one of the input pictures for NNPF.

[0172] The value of nnpfc_inp_order_idc must be in the range 0 to 3 in the bitstream. Values ​​of nnpfc_inp_order_idc between 4 and 255 are not 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.

[0173] If the value of ChromaFormatIdc is not 1, the value of nnpfc_inp_order_idc must not be 3.

[0174] Table 7 contains a description of the nnpfc_inp_order_idc values.

[0175]

[0176] A patch may be a rectangular array of samples from a component of a picture (e.g., a luma or chroma component).

[0177] 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 the auxiliary input data is derived through the methods shown in Tables 8 to 10.

[0178] The value of nnpfc_auxiliary_inp_idc must be in the range 0 to 1 in the bitstream. Values ​​of nnpfc_inp_order_idc in the range 2 to 255 are not present in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_inp_order_idc in the range 2 to 255. Values ​​of nnpfc_inp_order_idc greater than 255 are not present in the bitstream and are not reserved for future use.

[0179] If the value of nnpfc_auxiliary_inp_idc is equal to 1, the variable strengthControlScaledVal can be derived as in Equation 4.

[0180]

[0181] The process DeriveInputTensors() for deriving an input tensor inputTensor for given vertical sample coordinates cTop and horizontal sample coordinates cLeft specifying the upper left sample location of the sample patch contained in the input tensor can be represented as a combination of Tables 8 to 10.

[0182]

[0183]

[0184]

[0185] A value of 1 for nnpfc_separate_colour_description_present_flag may indicate that a unique combination of colour primaries, transform properties and matrix coefficients for a picture due to NNPF is specified in the SEI message syntax structure. A value of 0 for nnfpc_separate_colour_description_present_flag may indicate that the combination of colour primaries, transform properties and matrix coefficients for a picture due to NNPF is the same as that indicated in the VUI parameters of CLVS.

[0186] nnpfc_colour_primaries may have the same semantics as defined for the vui_colour_primaries syntax element, except that:

[0187] - 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.

[0188] - 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.

[0189] nnpfc_transfer_characteristics can have the same semantics as those defined for the vui_transfer_characteristics syntax element, except that:

[0190] - 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.

[0191] - 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.

[0192] nnpfc_matrix_coeffs may have the same semantics as specified for the vui_matrix_coeffs syntax element, except that:

[0193] - nnpfc_matrix_coeffs may represent the matrix coefficients of the picture resulting from applying the NNPF specified in the SEI message, rather than the matrix coefficients used in CLVS.

[0194] - 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.

[0195] - The allowed values ​​for nnpfc_matrix_coeffs may not be restricted by the chroma format of the decoded video pictures, as indicated by the ChromaFormatIdc value for the semantics of the VUI parameters.

[0196] - If the value of nnpfc_matrix_coeffs is equal to 0, the value of nnpfc_out_order_idc cannot be equal to 1 or 3.

[0197] A value of 0 for nnpfc_out_format_idc may indicate that the sample values ​​output by the NNPF are real numbers whose value range from 0 to 1 is linearly mapped to an unsigned integer value range from 0 to (1 << bitDepth) - 1, for the bit depth bitDepth required for subsequent post-processing or display. A value of 1 for nnpfc_out_format_idc may indicate that the luma sample values ​​output by the NNPF are unsigned integers in the range from 0 to ( 1 << ( nnpfc_out_tensor_luma_bitlength_minus8 + 8 ) ) - 1, and that the chroma sample values ​​output by the NNPF are unsigned integers in the range from 0 to ( 1 << ( nnpfc_out_tensor_chroma_bitlength_minus8 + 8 ) ) - 1.

[0198] Values ​​of nnpfc_out_format_idc greater than 1 may be reserved for future use and are not present in the bitstream. Decoders must ignore NNPFC SEI messages containing reserved values ​​of nnpfc_out_format_idc.

[0199] nnpfc_out_tensor_luma_bitdepth_minus8 + 8 can represent the bit depth of the luma sample values ​​in the output integer tensor. The value of nnpfc_out_tensor_luma_bitdepth_minus8 must be in the range of 0 to 24.

[0200] nnpfc_out_tensor_chroma_bitdepth_minus8 + 8 can represent the bit depth of the chroma sample values ​​in the output integer tensor. The value of nnpfc_out_tensor_chroma_bitdepth_minus8 must be in the range of 0 to 24.

[0201] If nnpfc_purpose & 0x10 are not equal to 0, the value of nnpfc_out_format_idc must be equal to 1, and at least one of the following restrictions must be true:

[0202] - nnpfc_out_tensor_luma_bitdepth_minus8 + 8 is BitDepth Y greater than

[0203] -nnpfc_out_tensor_chroma_bitdepth_minus8 + 8 BitDepth C greater than

[0204] nnpfc_out_order_idc can indicate the output order of samples output from the NNPF. The value of nnpfc_out_order_idc must be in the range of 0 to 3 in the bitstream. Values ​​of 4 to 255 for nnpfc_out_order_idc must not be present in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_out_order_idc in the range of 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. If the value of nnpfc_purpose & 0x02 is 0, the value of nnpfc_out_order_idc must not be equal to 3.

[0205] Table 11 describes the values ​​of nnpfc_out_order_idc.

[0206]

[0207] 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 12 and 13.

[0208]

[0209]

[0210] 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 16,383.

[0211] A value of 1 for nnpfc_constant_patch_size_flag 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 0 for nnpfc_constant_patch_size_flag can indicate that NNPF accepts as input any arbitrary patch size with width inpPatchWidth and height inpPatchHeight. Here, the width of the extended patch (i.e., the patch plus the overlapping area) equal to inpPatchWidth + 2 * nnpfc_overlap is 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 is a positive integer multiple of nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap.

[0212] 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(32 766, CroppedWidth - 1).

[0213] 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(32 766, CroppedHeight - 1).

[0214] nnpfc_extended_patch_width_cd_delta_minus1 + 1 + 2 * nnpfc_overlap can represent the common divisor of the allowed values ​​of the width of the extended patch required to be input to NNPF when the value of 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(32 766, CroppedWidth - 1).

[0215] nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap can represent the common divisor of the allowed values ​​of extended patch heights required to input to NNPF when the value of 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(32 766, CroppedHeight - 1).

[0216] The inpPatchWidth and inpPatchHeight variables can be set to the patch size width and patch size height, respectively.

[0217] If the value of nnpfc_constant_patch_size_flag is 0, the following can be applied:

[0218] - The values ​​of inpPatchWidth and inpPatchHeight can be provided by external means or set by the post-processor itself.

[0219] - The value of inpPatchWidth + 2 * nnpfc_overlap must be a positive integer multiple of nnpfc_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 nnpfc_extended_patch_height_cd_delta_minus1 + 1 + 2 * nnpfc_overlap, and inpPatchHeight must be less than or equal to CroppedHeight.

[0220] Otherwise (if the value of nnpfc_constant_patch_size_flag is 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.

[0221] The variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, and outPatchCHeight can be derived as shown in Table 14.

[0222]

[0223] 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.

[0224] nnpfc_padding_type can indicate the padding process when referencing sample locations outside the boundaries of a cropped decoded output picture, as described in Table 15. The value of nnpfc_padding_type must be in the range of 0 to 15.

[0225]

[0226] nnpfc_luma_padding_val can indicate the luma value to use for padding when the value of nnpfc_padding_type is 4.

[0227] nnpfc_cb_padding_val can indicate the Cb value to use for padding when the value of nnpfc_padding_type is 4.

[0228] nnpfc_cr_padding_val can indicate the Cr value to use for padding when the value of nnpfc_padding_type is 4.

[0229] The InpSampleVal(y, x, picHeight, picWidth, CroppedPic) function, whose inputs are vertical sample position y, horizontal sample position x, picture height picHeight, picture width picWidth, and sample array CroppedPic, can return the value of SampleVal derived as shown in Table 16.

[0230] For input to the InpSampleVal() function, vertical positions may be listed before horizontal positions for compatibility with the input tensor conventions of some inference engines.

[0231]

[0232] The process in Table 17 can be used to generate filtered and / or interpolated pictures by filtering them patch-wise using NNPF PostProcessingFilter(), where the filtered and / or interpolated pictures can include a Y sample array FilteredYPic, a Cb sample array FilteredCbPic, and a Cr sample array FilteredCrPic, as indicated by nnpfc_out_order_idc.

[0233]

[0234] The order of the pictures in the saved output tensor can be the output order, and the output order generated by applying NNPF to the output order can be interpreted as an output order that does not conflict with the output order of the input pictures.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] nnpfc_num_parameters_idc can represent the maximum number of neural network parameters for NNPF in units of 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. A value of nnpfc_num_parameters_idc greater than 52 must not be present in the bitstream. Decoders must ignore NNPFC SEI messages with nnpfc_num_parameters_idc greater than 52.

[0239] If the value of nnpfc_num_parameters_idc is greater than 0, the maxNumParameters variable can be derived as in Equation 5.

[0240]

[0241] The number of neural network parameters in NNPF can be limited to be less than or equal to maxNumParameters.

[0242] 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 * 1 000. 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.

[0243] 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 8,000, 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.

[0244] 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.

[0245] 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.

[0246] Neural-network post-filter activation (NNFPA)

[0247] The syntax structure for NNFPA is shown in Table 18.

[0248]

[0249] The NNPFA syntax structure of Table 18 can be signaled in the form of an SEI message. An SEI message signaling the NNPFA syntax structure of Table 18 may be referred to as an NNPFA SEI message.

[0250] The NNPFA SEI message may enable or disable the possible use of a target neural network post-processing filter (NNPF) identified by nnpfa_target_id for post-processing filtering of a set of pictures. For a particular picture with an NNPF enabled, the target NNPF may be the NNPF specified by the last NNPFC SEI message with an nnpfc_id equal to nnpfa_target_id. Here, the last NNPFC SEI message may precede the first VCL NAL unit of the current picture in decoding order and may not correspond to a repeat of the NNPFC SEI message containing the base NNPF.

[0251] Multiple NNPFA SEI messages may exist for the same picture if NNPF is used for different purposes or filters different color components.

[0252] 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 nnfpa_target_id.

[0253] 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.

[0254] An NNPFA SEI message with a specific value of nnpfa_target_id must not exist in the current PU unless one or both of the following conditions are true:

[0255] - 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.

[0256] - There is an NNPFC SEI message with an nnpfc_id equal to the specific value of the current PU's nnpfa_target_id.

[0257] 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.

[0258] A value of 1 for nnpfa_cancel_flag may indicate that the persistence of the target NNPF established by any previous NNPFA SEI message with the same nnpfa_target_id as the current SEI message is canceled. That is, the target NNPF is no longer used unless it is activated by another NNPFA SEI message with the same nnpfa_target_id as the current SEI message and an nnpfa_cancel_flag equal to 0. A value of 0 for nnpfa_cancel_flag may indicate that nnpfa_persistence_flag follows.

[0259] nnpfa_persistence_flag can indicate the persistence of the target NNPF for the current layer. A value of 0 for nnpfa_persistence_flag can indicate that the target NNPF 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 NNPF 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:

[0260] - A new CLVS for the current layer is started.

[0261] - Bitstream ended

[0262] - 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.

[0263] The target NNPF does not apply 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.

[0264] nnpfcTargetPictures may be a 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. nnpfaTargetPictures may be a set of pictures whose target NNPF is activated by the current NNPFA SEI message. Any picture included in nnpfaTargetPictures must also be included in nnpfcTargetPictures.

[0265] Post-filter hint

[0266] The syntax structure for post-filter hints is shown in Table 19.

[0267]

[0268] The post-filter hint syntax structure of Table 19 can be signaled in the form of an SEI message. An SEI message signaling the post-filter hint syntax structure of Table 19 may be referred to as a post-filter hint SEI message.

[0269] 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.

[0270] 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.

[0271] 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:

[0272] - A new CLVS for the current layer is started.

[0273] - Bitstream ended

[0274] - 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.

[0275] 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.

[0276] 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.

[0277] filter_hint_type can indicate the type of filter hint transmitted, as shown in Table 20. 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.

[0278]

[0279] 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.

[0280] filter_hint_value[ cIdx ][ cy ][ cx ] can represent filter coefficients or cross-correlation matrix elements between the original signal and the decoded signal with 16-bit precision. The value of filter_hint_value[ cIdx ][ cy ][ cx ] is -2 31 + 1 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.

[0281] - 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.

[0282] - 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.

[0283] - 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'.

[0284] The normalized cross-correlation matrix for the relevant color components identified by cIdx of the size filter_hint_size_y * filter_hint_size_x can be defined as in Equation 6.

[0285]

[0286]

[0287] In Equation 6, 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.

[0288] 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.

[0289] Problems with prior art

[0290] To control the size of the output picture, the following design is currently being applied.

[0291] - If the purpose of NNPF does not include spatial upsampling, the size of the output picture is inferred to be the same as the size of the input picture.

[0292] - Otherwise, the size of the output picture is signaled.

[0293] Considering that an NNPF carrying an NNPFC SEI message can be activated by one or more NNPFA SEI messages in different pictures, the size of the input picture can vary depending on the activation time, but currently the size of the output picture is fixed to be the same when the NNPF includes a spatial upsampling purpose.

[0294] Example

[0295] The present invention proposes various embodiments to address the problems described above. The embodiments proposed by the present invention may be implemented individually or in combination with one another.

[0296] Through this disclosure, the following possible and suitable embodiments are proposed.

[0297] 1. The bitstream can contain various picture sizes, and NNPF can be used to upsample the resolution of all pictures to the same size.

[0298] 2. The bitstream can contain various picture sizes, and NNPF can be used to upsample the resolution of all pictures while maintaining the ratio of the picture resolution of the input bitstream.

[0299] The embodiments proposed through this disclosure are summarized as follows.

[0300] 1. When signaling the output picture size, a flag (i.e., nnpfc_output_pic_size_flag) can be added to indicate whether the output picture size is a fixed size (i.e., given width and height) or a relative ratio to the input picture size. A value of nnpfc_output_pic_size_flag of 0 can indicate that there are luma samples with width and height for the output picture size. A value of nnpfc_output_pic_size_flag of 1 can indicate that there is a ratio of the output picture to the input picture size.

[0301] 2. When the value of nnpfc_output_pic_size_flag is 1, nnpfc_pic_width_ratio_num representing the numerator of the ratio of the output picture width to the input picture width and nnpfc_pic_width_ratio_denum representing the denominator can be signaled, and nnpfc_pic_height_ratio_num representing the numerator of the ratio of the output picture height to the input picture height and nnpfc_pic_height_ratio_denum representing the denominator can be signaled.

[0302] 3. When signaling the output picture size, scale ratio values ​​for width and height can be signaled. The ratio can be signaled as a numerator and denominator value. The ratio (or ratio value) can be signaled using the term "minus1" to save bits and avoid signaling a zero value. Additionally, the ratio (or ratio value) can be encoded and signaled using 0th order Exponential Golomb (ue(v)) encoding.

[0303] 4. nnpfc_pic_width_num_minus1 can represent the numerator for the ratio between the input picture width and the output picture width, and nnpfc_pic_width_denum_minus1 can represent the denominator for the ratio between the input picture width and the output picture width. nnpfc_pic_height_num_minus1 can represent the numerator for the ratio between the input picture height and the output picture height, and nnpfc_pic_height_denum_minus1 can represent the denominator for the ratio between the input picture height and the output picture height.

[0304] 5. The output picture width can be derived by rounding the value obtained by multiplying the input picture width by a non-integer ratio. Similarly, the output picture height can be derived by rounding the value obtained by multiplying the input picture height by a non-integer ratio.

[0305] 6. If nnpfc_pic_width_num_minus1, nnpfc_pic_width_denum_minus1, nnpfc_pic_height_num_minus1, and nnpfc_pic_height_denum_minus1 exist, the value of (nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1) may be constrained to have a non-1 value, or the value of (nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1) may be constrained to have a non-1 value.

[0306] 7. Alternatively, if nnpfc_pic_width_num_minus1, nnpfc_pic_width_denum_minus1, nnpfc_pic_height_num_minus1, and nnpfc_pic_height_denum_minus1 exist, the value of (nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1) may be constrained to be greater than 1, or the value of (nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1) may be constrained to be greater than 1.

[0307] Hereinafter, embodiments of the present disclosure will be described in detail.

[0308] Example 1

[0309] Example 1 relates to 1 and 2 of the summaries described above.

[0310] According to Example 1, the NNPFC SEI message can be configured as shown in Table 21.

[0311]

[0312] A value of 0 for nnpfc_output_pic_size_flag may indicate the presence of nnpfc_pic_width_in_luma_samples and nnpfc_pic_width_in_luma_samples. A value of 1 for nnpfc_output_pic_size_flag may indicate the presence of nnpfc_pic_width_ratio_num, nnpfc_pic_width_ratio_denum, nnpfc_pic_height_ratio_num, and nnpfc_pic_height_ratio_denum.

[0313] nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples may represent the width and height, respectively, of the luma sample array of the picture resulting from applying the NNPF identified by nnpfc_id to the cropped decoded output picture. The value of nnpfc_pic_width_in_luma_samples may be in the range of CroppedWidth to CroppedWidth * 16 - 1, and the value of nnpfc_pic_height_in_luma_samples may be in the range of CroppedHeight to CroppedHeight * 16 - 1. CroppedWidth may represent the width of the input picture, and CroppedHeight may represent the height of the input picture.

[0314] nnpfc_pic_width_ratio_num and nnpfc_pic_width_ratio_denum can represent the numerator and denominator, respectively, of the ratio of the output picture width to CroppedWidth. The values ​​of nnpfc_pic_width_ratio_num and nnpfc_pic_width_ratio_denum can be in the range of 1 to 16-1.

[0315] The variable PicWidthInLumaSamples, which represents the width of the output picture, can be derived as follows.

[0316] - If nnpfc_output_pic_size_flag does not exist, the value of PicWidthInLumaSamples can be set equal to CroppedWidth.

[0317] - Otherwise, if nnpfc_output_pic_size_flag is 0, the value of PicWidthInLumaSamples can be set equal to nnpfc_pic_width_in_luma_samples.

[0318] - Otherwise (i.e. nnpfc_output_pic_size_flag is 1), the value of PicWidthInLumaSamples can be set equal to ( CroppedWidth * nnpfc_pic_width_ratio_num ) / nnpfc_pic_width_ratio_denum.

[0319] nnpfc_pic_height_ratio_num and nnpfc_pic_height_ratio_denum can represent the numerator and denominator, respectively, of the ratio of the output picture height to the CroppedHeight. The values ​​of nnpfc_pic_height_ratio_num and nnpfc_pic_height_ratio_denum can be in the range of 1 to 16-1.

[0320] The variable PicHeightInLumaSamples, which represents the height of the output picture, can be derived as follows.

[0321] - If nnpfc_output_pic_size_flag does not exist, the value of PicHeightInLumaSamples can be set equal to CroppedHeight.

[0322] - Otherwise, if nnpfc_output_pic_size_flag is 0, the value of PicHeightInLumaSamples can be set equal to nnpfc_pic_height_in_luma_samples.

[0323] - Otherwise (i.e. nnpfc_output_pic_size_flag is 1), the value of PicHeightInLumaSamples can be set equal to ( CroppedHeight * nnpfc_pic_height_ratio_num ) / nnpfc_pic_height_ratio_denum.

[0324] 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 coordinate cTop and horizontal sample coordinate cLeft indicating the top-left sample position for the patch of samples contained in the input tensor can be modified as a combination of Tables 22 and 23.

[0325]

[0326]

[0327] The derivation process of variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, and outPatchCHeight can also be changed as shown in Table 24.

[0328]

[0329] It may be a bitstream conformance requirement that outPatchWidth * CroppedWidth must equal PicWidthInLumaSamples * inpPatchWidth, and that outPatchHeight * CroppedHeight must equal PicHeightInLumaSamples * inpPatchHeight.

[0330] Hereinafter, an image encoding method and an image decoding method according to Example 1 will be described. The image encoding method can be performed by an image encoding device (100), and the image decoding method can be performed by an image decoding device (200).

[0331] Fig. 5 shows an example of an image encoding method, and Fig. 6 shows an example of an image decoding method.

[0332] Referring to FIG. 5, the size of an output picture can be determined (S510). In addition, the type of size information indicating the size of the output picture can be determined (S520). For example, the size information can be composed of nnpfc_pic_width_in_luma_samples indicating the width of a luma sample array of the output picture and nnpfc_pic_height_in_luma_samples indicating the height of a luma sample array of the output picture. As another example, the size information can be composed of nnpfc_pic_width_ratio_num and nnpfc_pic_width_ratio_denum indicating the ratio of the output picture width to the input picture, and nnpfc_pic_height_ratio_num and nnpfc_pic_height_ratio_denum indicating the ratio of the output picture height to the input picture. The size information composed of nnpfc_pic_width_in_luma_samples and nnpfc_pic_height_in_luma_samples may be referred to as "non-ratio information." The size information composed of nnpfc_pic_width_ratio_num, nnpfc_pic_width_ratio_denum, nnpfc_pic_height_ratio_num, and nnpfc_pic_height_ratio_denum may be referred to as "ratio information" or "size information." Here, the non-ratio information and the ratio information may correspond to the type of size information.

[0333] It can be determined whether the type of the size information is a ratio (S530). If the type of the size information is determined to be a ratio (i.e., ratio information), nnpfc_output_pic_size_flag is encoded with a first value (e.g., 1) and the ratio information can be encoded (S540). Conversely, if the type of the size information is determined not to be a ratio (i.e., non-ratio information), nnpfc_output_pic_size_flag is encoded with a second value (e.g., 0) and the ratio information can be encoded in the bitstream (NNPFC SEI message) (S540). The size information can be encoded based on 0th-order exponential Gollum encoding. nnpfc_output_pic_size_flag can be referred to as "first information."

[0334] Referring to FIG. 6, nnpfc_output_pic_size_flag is obtained from a bitstream (NNPFC SEI message) (S610), and the value of nnpfc_output_pic_size_flag can be determined (S620). If the value of nnpfc_output_pic_size_flag is a first value (e.g., 1) indicating that ratio information (or size information) exists, the ratio information can be obtained from the bitstream (S630). Conversely, if the value of nnpfc_output_pic_size_flag is a second value (e.g., 0) indicating that non-ratio information exists, the non-ratio information can be obtained from the bitstream (S650).

[0335] The size of the output picture can be determined based on the acquired ratio information or non-ratio information (S640). For example, when ratio information is acquired, the width (PicWidthInLumaSamples) of the output picture can be determined by applying the width ratio (nnpfc_pic_width_ratio_num / nnpfc_pic_width_ratio_denum) indicated by the ratio information to the width of the input picture, and the height (PicHeightInLumaSamples) of the output picture can be determined by applying the height ratio (nnpfc_pic_height_ratio_num / nnpfc_pic_height_ratio_denum) indicated by the ratio information to the height of the input picture. As another example, when non-ratio information is obtained, the width of the output picture (PicWidthInLumaSamples) can be determined as a value equal to the width indicated by the non-ratio information (nnpfc_pic_width_in_luma_samples), and the height of the output picture (PicHeightInLumaSamples) can be determined as a value equal to the height indicated by the non-ratio information (nnpfc_pic_height_in_luma_samples).

[0336] Example 2

[0337] Example 2 relates to 3 to 7 of the summaries described above.

[0338] According to Example 2, the NNPFC SEI message can be configured as shown in Table 25.

[0339]

[0340] nnpfc_pic_width_num_minus1 + 1 and nnpfc_pic_width_denum_minus1 + 1 can represent the numerator and denominator for the ratio of the output picture width to CroppedWidth. The value of (nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1) can be in the range of 1 to 16-1.

[0341] The value of the variable nnpfcOutputPicWidth can represent the width of the luma sample array of the picture resulting from applying the NNPF identified by nnpfc_id to the cropped decoded output picture, and can be derived as in Equation 7.

[0342]

[0343] nnpfc_pic_height_num_minus1 + 1 and nnpfc_pic_height_denum_minus1 + 1 may represent the numerator and denominator for the ratio of the output picture height to CroppedHeight. The value of (nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1) may be in the range of 1 to 16-1.

[0344] The value of the variable nnpfcOutputPicHeight can represent the height of the luma sample array of the picture resulting from applying the NNPF identified by nnpfc_id to the cropped decoded output picture, and can be derived as in Equation 8.

[0345]

[0346] If nnpfc_pic_width_num_minus1, nnpfc_pic_width_denum_minus1, nnpfc_pic_height_num_minus1, and nnpfc_pic_height_denum_minus1 exist, the value of (nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1) may be greater than 1, or the value of (nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1) may be greater than 1. Alternatively, if nnpfc_pic_width_num_minus1, nnpfc_pic_width_denum_minus1, nnpfc_pic_height_num_minus1 and nnpfc_pic_height_denum_minus1 exist, the value of (nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1) may have a value other than 1, or the value of (nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1) may have a value other than 1.

[0347] 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 modified as a combination of Tables 26 and 27.

[0348]

[0349]

[0350] The derivation process of variables outPatchWidth, outPatchHeight, horCScaling, verCScaling, outPatchCWidth, and outPatchCHeight can also be changed as shown in Table 28.

[0351]

[0352] It may be a bitstream conformance requirement that outPatchWidth * CroppedWidth must equal nnpfcOutputPicWidth * inpPatchWidth, and that outPatchHeight * CroppedHeight must equal nnpfcOutputPicHeight * inpPatchHeight.

[0353] Hereinafter, an image encoding method and an image decoding method according to Example 2 will be described. The image encoding method can be performed by an image encoding device (100), and the image decoding method can be performed by an image decoding device (200).

[0354] Fig. 7 shows an example of an image encoding method, and Fig. 8 shows an example of an image decoding method.

[0355] Referring to FIG. 7, the ratio between the size of an output picture and the size of an input picture can be determined (S710). Additionally, size information regarding the determined ratio can be encoded in a bitstream (NNPFC SEI message) (S720). The size information can be encoded based on zero-order exponential Gollum encoding.

[0356] The size information may include information about the numerator value of the determined ratio and information about the denominator value. The information about the numerator value may include information about the numerator value of the ratio between the width of the output picture and the width of the input picture (width ratio) (nnpfc_pic_width_num_minus1) and information about the numerator value of the ratio between the height of the output picture and the height of the input picture (height ratio) (nnpfc_pic_height_num_minus1). In addition, the information about the denominator value may include information about the denominator value of the width ratio (nnpfc_pic_width_denum_minus1) and information about the denominator value of the height ratio (nnpfc_pic_height_denum_minus1).

[0357] Information about the numerator value (nnpfc_pic_width_num_minus1, nnpfc_pic_height_num_minus1) may represent a value obtained by subtracting 1 from the numerator value of the width ratio, and may represent a value obtained by subtracting 1 from the numerator value of the height ratio. Therefore, the numerator value of the width ratio may be determined as a value obtained by adding 1 to the information about the numerator value, and the numerator value of the height ratio may be determined as a value obtained by adding 1 to the information about the numerator value. In addition, information about the denominator value (nnpfc_pic_width_denum_minus1, nnpfc_pic_height_denum_minus1) may represent a value obtained by subtracting 1 from the denominator value of the width ratio, and may represent a value obtained by subtracting 1 from the denominator value of the height ratio. Therefore, the denominator value of the width ratio can be determined as a value obtained by adding 1 to the information about the denominator value, and the denominator value of the height ratio can be determined as a value obtained by adding 1 to the information about the denominator value.

[0358] Referring to FIG. 8, when size information is obtained from a bitstream (NNPFC SEI message) (S810), the size of an output picture can be determined based on the obtained size information (S820). Here, the size determination of the output picture can be performed by resolution upsampling.

[0359] For example, the width of the output picture (nnpfcOutputPicWidth) can be determined by applying a width ratio ((nnpfc_pic_width_num_minus1 + 1) χ (nnpfc_pic_width_denum_minus1 + 1)) to the width value (CroppedWidth) of the input picture and rounding up the width of the input picture to which the width ratio is applied. As another example, the height of the output picture (nnpfcOutputPicHeight) can be determined by applying a height ratio ((nnpfc_pic_height_num_minus1 + 1) χ (nnpfc_pic_height_denum_minus1 + 1)) to the height value (CroppedHeight) of the input picture and rounding up the height of the input picture to which the height ratio is applied.

[0360] Fig. 9 shows an example of an image encoding method that limits the width ratio and height ratio, and Fig. 10 shows an example of an image decoding method that limits the width ratio and height ratio.

[0361] Referring to FIG. 9, it can be determined whether the size of the output picture and the size of the input picture are identical (S910). For example, it can be determined whether the width ratio is identical to 1 and whether the height ratio is identical to 1. As another example, it can be determined whether the width ratio is greater than 1 and whether the height ratio is greater than 1.

[0362] If the size of the output picture is not the same as the size of the input picture, the size information may be encoded in the bitstream (NNPFC SEI message) (S920). Conversely, if the size of the output picture is the same as the size of the input picture, the size information may not be encoded. For example, if the width ratio is not equal to 1 and the height ratio is not equal to 1, the size information may be encoded, and if the width ratio is equal to 1 and the height ratio is equal to 1, the size information may not be encoded. As another example, if the width ratio is greater than 1 and the height ratio is greater than 1, the size information may be encoded, and if the width ratio is less than or equal to 1 and the height ratio is less than or equal to 1, the size information may not be encoded.

[0363] Referring to FIG. 10, it can be determined whether size information exists (S1010). That is, it can be determined whether size information is obtained from a bitstream (NNPFC SEI message). Referring to Table 4 and Table 25, whether size information exists can have the same meaning as whether resolution upsampling is performed. That is, the presence of size information can mean that resolution upsampling is performed (( nnpfc_purpose & 0x04 ) != 0), and the absence of size information can mean that resolution upsampling is not performed (( nnpfc_purpose & 0x04 ) = = 0).

[0364] If size information exists, the size of the output picture can be constrained to have a different value than the size of the input picture. For example, the width ratio can be constrained to have a value that is not equal to 1, and the height ratio can be constrained to have a value that is not equal to 1. In another example, the width ratio can be constrained to have a value greater than 1, and the height ratio can be constrained to have a value greater than 1.

[0365] FIG. 11 is a diagram illustrating an example of a content streaming system to which an embodiment according to the present disclosure can be applied.

[0366] As illustrated in FIG. 11, 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] Embodiments according to the present disclosure can be used to encode / decode images.

Claims

1. An image decoding method performed by an image decoding device, A step of obtaining size information from a neural-network post-filter characteristics (NNPFC) SEI (supplemental enhancement information) message; and A step of determining the size of an output picture based on the size information is included, A method for decoding an image, wherein the above size information includes information on a numerator value of a ratio between the size of the output picture and the size of the input picture and information on a denominator value of the ratio.

2. In paragraph 1, A method for decoding an image, wherein the information about the above molecule value includes information about the molecule value of the ratio between the width of the output picture and the width of the input picture and information about the molecule value of the ratio between the height of the output picture and the height of the input picture.

3. In paragraph 1, A method for decoding an image, wherein the information about the denominator value includes information about the denominator value of the ratio between the width of the output picture and the width of the input picture and information about the denominator value of the ratio between the height of the output picture and the height of the input picture.

4. In paragraph 1, A method for decoding an image, wherein a value obtained by adding 1 to the information about the above molecular value represents the above molecular value.

5. In paragraph 1, A method for decoding an image, wherein the value obtained by adding 1 to the information about the above denominator value represents the above denominator value.

6. In paragraph 1, A method for decoding an image, wherein the above size information is encoded based on 0-th order Exponential Golomb encoding.

7. In paragraph 1, A video decoding method, wherein the width of the output picture is determined by rounding up the width value of the input picture to which a width ratio, which is a ratio between the width of the output picture and the width of the input picture, is applied.

8. In paragraph 1, A video decoding method, wherein the height of the output picture is determined by rounding the height value of the input picture to which a height ratio, which is the ratio between the height of the output picture and the height of the input picture, is applied.

9. In paragraph 1, A video decoding method, wherein, based on the existence of the above size information, the ratio between the width of the output picture and the width of the input picture is restricted to have a value greater than 1, and the ratio between the height of the output picture and the height of the input picture is restricted to have a value greater than 1.

10. In paragraph 1, A video decoding method, wherein, based on the existence of the above size information, the ratio between the width of the output picture and the width of the input picture is restricted to have a value other than 1, and the ratio between the height of the output picture and the height of the input picture is restricted to have a value other than 1.

11. In paragraph 10, Further comprising a step of obtaining first information from the NNPFC SEI message, The first value of the first information indicates that the size information exists, and the second value of the first information indicates that the size information of the output picture exists. An image decoding method, wherein the above size information is obtained based on the first information indicating the first value.

12. An image encoding method performed by an image encoding device, A step of determining the ratio between the size of the output picture and the size of the input picture; and Including a step of encoding size information for the above ratio into a NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message, An image encoding method, wherein the above size information includes information on the numerator value of the ratio and information on the denominator value of the ratio.

13. A computer-readable recording medium storing a bitstream generated by the image encoding method of Article 12.

14. A method for transmitting a bitstream generated by an image encoding method, wherein the image encoding method comprises: A step of determining the ratio between the size of the output picture and the size of the input picture; and Including a step of encoding size information for the above ratio into a NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message, A method wherein the above size information includes information on the numerator value of the above ratio and information on the denominator value of the above ratio.

Images