WO2026005570A1 - Image encoding/decoding method and device, and recording medium on which bitstream is stored - Google Patents

Abstract

An image encoding/decoding method and device, a recording medium on which a bitstream is stored, and a transmission method are provided. The image decoding method comprises the steps of: acquiring information indicating whether predetermined intra prediction is activated in a specific type of slice; determining a prediction mode of the current block on the basis of the information indicating whether predetermined intra prediction is activated in the specific type of slice; and generating a prediction block of the current block on the basis of the prediction mode, wherein the information indicating whether predetermined intra prediction is activated in the specific type of slice can include information indicating whether predetermined intra prediction is activated in an I slice and information indicating whether predetermined intra prediction is activated in a P slice or a B slice.

Description

Video encoding/decoding method, device, and recording medium storing bitstream

The present disclosure relates to a video encoding/decoding method, a device, and a recording medium storing a bitstream. Specifically, the present disclosure relates to a video encoding/decoding method, a device, and a recording medium storing a bitstream, including a method for signaling and obtaining intra prediction-related syntax elements.

Recently, the demand for high-resolution, high-quality images, such as UHD (Ultra High Definition) images, is increasing across various application fields. As image data becomes higher in resolution and quality, the relative amount of data increases compared to conventional image data. Therefore, transmitting image data using existing media such as wired or wireless broadband lines or storing it using existing storage media leads to increased transmission and storage costs. To address these issues arising from the increasing resolution and quality of image data, high-efficiency image encoding/decoding technologies for higher-resolution and higher-quality images are required.

Specifically, intra prediction can be performed using various methods in image encoding/decoding methods. Specifically, matrix-based intra prediction or neural network-based intra prediction can be utilized in image encoding/decoding methods. In this regard, a method may be needed to improve the efficiency of matrix-based intra prediction or neural network-based intra prediction.

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

In addition, the present disclosure aims to provide a recording medium storing a bitstream generated by an image decoding method or device according to the disclosed embodiment.

In addition, the present disclosure aims to provide a method for signaling information related to intra prediction in order to improve the efficiency of intra prediction as described above.

A video decoding method according to one embodiment of the present disclosure includes a step of obtaining information indicating whether to activate predefined intra prediction according to a slice type, a step of determining a prediction mode of a current block based on the information indicating whether to activate predefined intra prediction according to the slice type, and a step of generating a prediction block of the current block based on the prediction mode, wherein the information indicating whether to activate predefined intra prediction according to the slice type may include information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice.

In the above image decoding method, the information indicating whether to activate predefined intra prediction according to the slice type may further include information indicating whether to activate predefined intra prediction for an inter-predicted block of a P slice or a B slice.

In the above image decoding method, the predefined intra prediction may be matrix-based intra prediction.

In the above image decoding method, the prediction block of the current block can be generated by combining an inter prediction block generated based on an inter prediction mode of the current block and an intra prediction block generated based on a matrix corresponding to an intra prediction mode.

In the above image decoding method, the intra prediction mode can be derived based on a gradient histogram of blocks surrounding the current block.

In the above image decoding method, the intra prediction mode can be derived based on a gradient histogram of samples of the inter prediction block.

In the above image decoding method, information indicating whether to activate intra prediction defined according to the slice type can be obtained based on information indicating whether to activate intra prediction based on a matrix.

In the above image decoding method, the predefined intra prediction may be an intra prediction based on an artificial neural network model.

In the above image decoding method, the prediction block of the current block can be generated by combining an inter prediction block generated based on an inter prediction mode of the current block and an intra prediction block generated based on an artificial neural network model corresponding to an intra prediction mode.

In the above image decoding method, the intra prediction mode can be derived based on a gradient histogram of blocks surrounding the current block.

In the above image decoding method, the intra prediction mode can be derived based on a gradient histogram of samples of the inter prediction block.

In the above image decoding method, information indicating whether to activate intra prediction defined according to the slice type can be obtained based on information indicating whether to activate intra prediction based on an artificial neural network model.

In the above image decoding method, information indicating whether to activate intra prediction defined in advance according to the slice type may indicate whether to activate intra prediction based on a matrix and whether to activate intra prediction based on an artificial neural network model.

A video encoding method according to one embodiment of the present disclosure includes a step of obtaining information indicating whether to activate predefined intra prediction according to a slice type, a step of determining a prediction mode of a current block based on the information indicating whether to activate predefined intra prediction according to the slice type, and a step of generating a prediction block of the current block based on the prediction mode, wherein the information indicating whether to activate predefined intra prediction according to the slice type may include information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice.

A non-transitory computer-readable recording medium according to one embodiment of the present disclosure may store a bitstream generated by a video encoding method, the bitstream including the steps of: obtaining information indicating whether to activate pre-defined intra prediction according to a slice type; determining a prediction mode of a current block based on the information indicating whether to activate pre-defined intra prediction according to the slice type; and generating a prediction block of the current block based on the prediction mode, wherein the information indicating whether to activate pre-defined intra prediction according to the slice type includes information indicating whether to activate pre-defined intra prediction for a block of an I slice and information indicating whether to activate pre-defined intra prediction for a block to be intra-predicted of a P slice or a B slice.

A bitstream transmission method according to one embodiment of the present disclosure comprises the steps of: obtaining information indicating whether to activate pre-defined intra prediction according to a slice type; determining a prediction mode of a current block based on the information indicating whether to activate pre-defined intra prediction according to the slice type; and generating a prediction block of the current block based on the prediction mode, wherein the information indicating whether to activate pre-defined intra prediction according to the slice type includes information indicating whether to activate pre-defined intra prediction for a block of an I slice and information indicating whether to activate pre-defined intra prediction for a block to be intra-predicted of a P slice or a B slice, and a bitstream generated by a video encoding method can be transmitted.

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.

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

In addition, according to the present disclosure, an intra prediction method can be provided that improves the efficiency of intra prediction by signaling information related to intra prediction based on a matrix or intra prediction based on a neural network model and obtaining the signaled information.

Additionally, according to the present disclosure, intra prediction efficiency can be improved.

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.

FIG. 1 is a block diagram showing a configuration according to one embodiment of an encoding device to which the present disclosure is applied.

FIG. 2 is a block diagram showing a configuration according to one embodiment of a decryption device to which the present disclosure is applied.

FIG. 3 is a diagram schematically illustrating a video coding system to which the present disclosure can be applied.

FIG. 4 is a diagram for explaining a matrix-based intra prediction method according to an embodiment of the present disclosure.

FIG. 5 is a drawing for explaining the surrounding pixels of the current block according to one embodiment of the present disclosure.

FIG. 6 is a drawing for explaining the surrounding pixels of the current block according to one embodiment of the present disclosure.

FIG. 7 is a diagram for explaining a neural network-based intra prediction method according to one embodiment of the present disclosure.

FIG. 8 is a flowchart illustrating an image decoding method according to an embodiment of the present disclosure.

FIG. 9 is a diagram exemplifying a content streaming system to which an embodiment according to the present disclosure can be applied.

The present invention is susceptible to various modifications and embodiments, and thus specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present disclosure to specific embodiments, but rather to encompass all modifications, equivalents, and substitutes falling within the spirit and scope of the present disclosure. In the drawings, similar reference numerals designate the same or similar functions throughout. The shapes and sizes of elements in the drawings may be provided for illustrative purposes only for clarity. The detailed description of the exemplary embodiments described below refers to the accompanying drawings, which illustrate specific embodiments by way of example. These embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments. It should be understood that the various embodiments, while different from one another, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the present disclosure. Furthermore, it should be understood that the positions or arrangements of individual components within each disclosed embodiment may be modified without departing from the spirit and scope of the embodiment. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the exemplary embodiments, if properly described, is defined only by the appended claims, along with the full scope equivalents to which such claims are entitled.

While terms such as "first" and "second" may be used herein to describe various components, these components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present disclosure, a first component may be referred to as a "second component," and similarly, a second component may also be referred to as a "first component." The term "and/or" includes a combination of multiple related items described herein or any of multiple related items described herein.

The components shown in the embodiments of the present disclosure are independently depicted to represent different characteristic functions, and do not imply that each component is composed of separate hardware or a single software component. That is, each component is listed and included as a separate component for convenience of explanation, and at least two components among each component may be combined to form a single component, or a single component may be divided into multiple components to perform a function, and such integrated and separate embodiments of each component are also included in the scope of the present disclosure as long as they do not deviate from the essence of the present disclosure.

The terminology used in this disclosure is merely used to describe specific embodiments and is not intended to limit the present disclosure. The singular expression includes the plural expression unless the context clearly dictates otherwise. In addition, some components of the present disclosure may not be essential components that perform essential functions in the present disclosure and may be optional components merely for performance enhancement. The present disclosure may be implemented by including only components essential to implementing the essence of the present disclosure, excluding components used solely for performance enhancement, and a structure including only essential components, excluding optional components used solely for performance enhancement, is also within the scope of the present disclosure.

In an embodiment, the term "at least one" may mean one of a number greater than or equal to 1, such as 1, 2, 3, and 4. In an embodiment, the term "a plurality of" may mean one of a number greater than or equal to 2, such as 2, 3, and 4.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In describing the embodiments of this specification, if a detailed description of a related known configuration or function is judged to obscure the gist of this specification, the detailed description will be omitted. The same reference numerals will be used for identical components in the drawings, and duplicate descriptions of the same components will be omitted.

Glossary of Terms

Hereinafter, “video” may mean a single picture constituting a video, or may refer to the video itself. For example, “encoding and/or decoding of a video” may mean “encoding and/or decoding of a video,” or may mean “encoding and/or decoding of one of the videos constituting the video.”

Hereinafter, the terms "video" and "movie" may be used interchangeably and have the same meaning. Furthermore, the target image may be an encoding target image, which is the target of encoding, and/or a decoding target image, which is the target of decoding. Furthermore, the target image may be an input image input to an encoding device, or an input image input to a decoding device. Here, the target image may have the same meaning as the current image.

Hereinafter, the terms encoder and image encoding device may be used interchangeably and have the same meaning.

Hereinafter, the terms decoder and image decoding device may be used interchangeably and have the same meaning.

Hereinafter, “image”, “picture”, “frame” and “screen” may be used with the same meaning and may be used interchangeably.

Hereinafter, the term "target block" may refer to an encoding target block, which is the target of encoding, and/or a decoding target block, which is the target of decoding. Furthermore, the target block may refer to a current block, which is the target of current encoding and/or decoding. For example, the terms "target block" and "current block" may be used interchangeably and have the same meaning.

Hereinafter, "block" and "unit" may be used with the same meaning and may be used interchangeably. In addition, "unit" may mean including a luminance component block and a corresponding chroma component block to distinguish it from a block. For example, a coding tree unit (CTU) may be composed of one luma component (Y) coding tree block (CTB) and two chroma component (Cb, Cr) coding tree blocks associated with it.

Hereinafter, the terms “sample,” “pixel,” and “pixel” may be used interchangeably and have the same meaning. Here, a sample may represent a basic unit that constitutes a block.

Hereinafter, “inter” and “between screens” may be used interchangeably and have the same meaning.

Hereinafter, “intra” and “within screen” may be used interchangeably and have the same meaning.

FIG. 1 is a block diagram showing a configuration according to one embodiment of an encoding device to which the present disclosure is applied.

The encoding device (100) may be an encoder, a video encoding device, or an image encoding device. A video may include one or more images. The encoding device (100) may sequentially encode one or more images.

Referring to FIG. 1, the encoding device (100) may include an image segmentation unit (110), an intra prediction unit (120), a motion prediction unit (121), a motion compensation unit (122), a switch (115), a subtractor (113), a transformation unit (130), a quantization unit (140), an entropy encoding unit (150), an inverse quantization unit (160), an inverse transformation unit (170), an adder (117), a filter unit (180), and a reference picture buffer (190).

Additionally, the encoding device (100) can generate a bitstream including encoded information through encoding an input image and output the generated bitstream. The generated bitstream can be stored in a computer-readable recording medium or can be streamed via a wired/wireless transmission medium.

The video segmentation unit (110) can segment the input video into various forms to increase the efficiency of video encoding/decoding. That is, the input video is composed of multiple pictures, and one picture can be hierarchically segmented and processed for compression efficiency, parallel processing, etc. For example, one picture can be segmented into one or more tiles or slices, which can then be segmented into multiple Coding Tree Units (CTUs). Alternatively, one picture can first be segmented into multiple sub-pictures defined as groups of rectangular slices, and each sub-picture can then be segmented into the tiles/slices. Here, the sub-pictures can be utilized to support the function of partially independently encoding/decoding and transmitting the picture. Since multiple sub-pictures can each be individually restored, there is an advantage of easy editing in applications that configure multi-channel input into a single picture. In addition, tiles can be segmented horizontally to generate bricks. Here, a brick can be utilized as the basic unit of intra-picture parallel processing. In addition, one CTU can be recursively split into a quadtree (QT), and the terminal node of the split can be defined as a coding unit (CU). The CU can be split into a prediction unit (PU) and a transformation unit (TU), and prediction and splitting can be performed. Meanwhile, the CU can be utilized as a prediction unit and/or a transformation unit itself. Here, for flexible splitting, each CTU can be recursively split into a multi-type tree (MTT) as well as a quadtree (QT). Splitting of a CTU into a multi-type tree can start from the terminal node of a QT, and the MTT can be composed of a binary tree (BT) and a triple tree (TT). For example, the MTT structure can be divided into vertical binary split mode (SPLIT_BT_VER), horizontal binary split mode (SPLIT_BT_HOR), vertical ternary split mode (SPLIT_TT_VER), and horizontal ternary split mode (SPLIT_TT_HOR). In addition, the minimum block size (MinQTSize) of the quad tree of the luma block during splitting can be set to 16x16, the maximum block size (MaxBtSize) of the binary tree can be set to 128x128, and the maximum block size (MaxTtSize) of the triple tree can be set to 64x64. In addition, the minimum block size (MinBtSize) of the binary tree and the minimum block size (MinTtSize) of the triple tree can be set to 4x4, and the maximum depth (MaxMttDepth) of the multi-type tree can be set to 4. In addition, in order to increase the encoding efficiency of the I slice, a dual tree that uses different CTU split structures for luma and chrominance components can be applied. On the other hand, in P and B slices, the luminance and chrominance CTBs (Coding Tree Blocks) within the CTU can be split into a single tree that shares the coding tree structure.

The encoding device (100) may perform encoding on the input image in intra mode and/or inter mode. Alternatively, the encoding device (100) may perform encoding on the input image in a third mode (e.g., IBC mode, Palette mode, etc.) other than the intra mode and inter mode. However, if the third mode has functional characteristics similar to the intra mode or inter mode, it may be classified as intra mode or inter mode for convenience of explanation. In the present disclosure, the third mode will be classified and described separately only when a specific description is required.

When the intra mode is used as the prediction mode, the switch (115) can be switched to intra, and when the inter mode is used as the prediction mode, the switch (115) can be switched to inter. Here, the intra mode can mean an intra-screen prediction mode, and the inter mode can mean an inter-screen prediction mode. The encoding device (100) can generate a prediction block for an input block of an input image. In addition, after the prediction block is generated, the encoding device (100) can encode a residual block using a residual of the input block and the prediction block. The input image can be referred to as a current image that is currently a target of encoding. The input block can be referred to as a current block that is currently a target of encoding or an encoding target block.

When the prediction mode is intra mode, the intra prediction unit (120) can use samples of blocks already encoded/decoded around the current block as reference samples. The intra prediction unit (120) can perform spatial prediction on the current block using the reference samples, and can generate prediction samples for the input block through spatial prediction. Here, intra prediction can mean prediction within the screen.

As an intra prediction method, non-directional prediction modes such as DC mode and Planar mode, as well as directional prediction modes (e.g., 65 directions) can be applied. Here, the intra prediction method can be expressed as an intra prediction mode or an intra-screen prediction mode.

When the prediction mode is inter mode, the motion prediction unit (121) can search for an area that best matches the input block from the reference image during the motion prediction process and derive a motion vector using the searched area. At this time, the area can be used as a search area. The reference image can be stored in the reference picture buffer (190). Here, when encoding/decoding for the reference image is processed, it can be stored in the reference picture buffer (190).

The motion compensation unit (122) can generate a prediction block for the current block by performing motion compensation using a motion vector. Here, inter prediction may mean inter-screen prediction or motion compensation.

The above motion prediction unit (121) and motion compensation unit (122) can generate a prediction block by applying an interpolation filter to a portion of the reference image when the value of the motion vector does not have an integer value. In order to perform inter-screen prediction or motion compensation, it is possible to determine whether the motion prediction and motion compensation method of the prediction unit included in the corresponding encoding unit is one of Skip Mode, Merge Mode, Advanced Motion Vector Prediction (AMVP) mode, and Intra Block Copy (IBC) mode based on the encoding unit, and perform inter-screen prediction or motion compensation according to each mode.

In addition, based on the above inter-screen prediction method, the AFFINE mode of sub-PU based prediction, the SbTMVP (Subblock-based Temporal Motion Vector Prediction) mode, and the MMVD (Merge with MVD) mode and the GPM (Geometric Partitioning Mode) mode of PU based prediction can be applied. In addition, in order to improve the performance of each mode, the HMVP (History based MVP), the PAMVP (Pairwise Average MVP), the CIIP (Combined Intra/Inter Prediction), the AMVR (Adaptive Motion Vector Resolution), the BDOF (Bi-Directional Optical-Flow), the BCW (Bi-predictive with CU Weights), the LIC (Local Illumination Compensation), the TM (Template Matching), and the OBMC (Overlapped Block Motion Compensation) can be applied.

Among these, AFFINE mode is a technology that is used in both AMVP and MERGE modes and also has high encoding efficiency. In the existing video coding standard, since MC (Motion Compensation) is performed by considering only the parallel translation of the block, there was a disadvantage in that it could not properly compensate for motions that occur in reality, such as zoom in/out and rotation. To supplement this, a 4-parameter affine motion model using two control point motion vectors (CPMV) and a 6-parameter affine motion model using three control point motion vectors can be applied to inter prediction. Here, CPMV is a vector representing the affine motion model of one of the upper left, upper right, and lower left of the current block.

The subtractor (113) can generate a residual block using the difference between the input block and the predicted block. The residual block may also be referred to as a residual signal. The residual signal may refer to the difference between the original signal and the predicted signal. Alternatively, the residual signal may be a signal generated by transforming, quantizing, or transforming and quantizing the difference between the original signal and the predicted signal. The residual block may be a residual signal in block units.

The transform unit (130) can perform a transform on the residual block to generate a transform coefficient and output the generated transform coefficient. Here, the transform coefficient may be a coefficient value generated by performing a transform on the residual block. When the transform skip mode is applied, the transform unit (130) may also skip the transform on the residual block.

Quantized levels can be generated by applying quantization to transform coefficients or residual signals. In the following embodiments, quantized levels may also be referred to as transform coefficients.

For example, a 4x4 luminance residual block generated through within-screen prediction can be transformed using a basis vector based on DST (Discrete Sine Transform), and the remaining residual blocks can be transformed using a basis vector based on DCT (Discrete Cosine Transform). In addition, through RQT (Residual Quad Tree) technology, the transform block is divided into a quad tree shape for one block, and after performing transformation and quantization on each transform block divided through RQT, a coded block flag (cbf) can be transmitted to increase encoding efficiency when all coefficients become 0.

Another alternative is to apply Multiple Transform Selection (MTS) technology, which selectively performs transformation using multiple transformation bases. That is, instead of dividing CUs into TUs via RQT, a Sub-block Transform (SBT) technology can perform a function similar to TU division. Specifically, SBT is applied only to inter-screen prediction blocks, and unlike RQT, it can divide the current block into ½ or ¼ blocks vertically or horizontally, and then perform transformation on only one of the blocks. For example, in a vertically divided block, the transformation can be performed on the leftmost or rightmost block, and in a horizontally divided block, the transformation can be performed on the topmost or bottommost block.

Additionally, LFNST (Low Frequency Non-Separable Transform), a secondary transform technique that further transforms the residual signal converted to the frequency domain through DCT or DST, can be applied. LFNST additionally performs a transform on the low-frequency region of 4x4 or 8x8 in the upper left, which allows the residual coefficients to be concentrated in the upper left.

The quantization unit (140) can generate a quantized level by quantizing a transform coefficient or residual signal according to a quantization parameter (QP), and can output the generated quantized level. At this time, the quantization unit (140) can quantize the transform coefficient using a quantization matrix.

For example, a quantizer with QP values of 0 to 51 can be used. Alternatively, if the image size is larger and high encoding efficiency is required, a QP of 0 to 63 can be used. In addition, a Dependent Quantization (DQ) method that uses two quantizers instead of a single quantizer can be applied. DQ performs quantization using two quantizers (e.g., Q0 and Q1), but even without signaling information about the use of a specific quantizer, the quantizer to be used for the next transform coefficient can be selected based on the current state through a state transition model.

The entropy encoding unit (150) can generate a bitstream by performing entropy encoding according to a probability distribution on values produced by the quantization unit (140) or coding parameter values produced during the encoding process, and can output the bitstream. The entropy encoding unit (150) can perform entropy encoding on information about image samples and information for decoding the image. For example, the information for decoding the image can include syntax elements, etc.

When entropy encoding is applied, a small number of bits are allocated to symbols with a high occurrence probability, and a large number of bits are allocated to symbols with a low occurrence probability, thereby representing the symbols, whereby the size of the bit string for the symbols to be encoded can be reduced. The entropy encoding unit (150) can use an encoding method such as exponential Golomb, Context-Adaptive Variable Length Coding (CAVLC), or Context-Adaptive Binary Arithmetic Coding (CABAC) for entropy encoding. For example, the entropy encoding unit (150) can perform entropy encoding using a Variable Length Coding/Code (VLC) table. In addition, the entropy encoding unit (150) may perform arithmetic encoding using the binarization method, probability model, and context model derived from the binarization method of the target symbol and the probability model of the target symbol/bin.

In this regard, when applying CABAC, the table probability update method can be changed to a simple formula-based table update method to reduce the size of the probability table stored in the decryption device. Furthermore, two different probability models can be used to obtain more accurate symbol probability values.

The entropy encoding unit (150) can change a two-dimensional block form coefficient into a one-dimensional vector form through a transform coefficient scanning method to encode a transform coefficient level (quantized level).

Coding parameters may include not only information (flags, indexes, etc.) encoded in an encoding device (100) and signaled to a decoding device (200), such as syntax elements, but also information derived during an encoding or decoding process, and may mean information necessary when encoding or decoding an image.

Here, signaling a flag or index may mean that the encoder entropy encodes the flag or index and includes it in the bitstream, and that the decoder entropy decodes the flag or index from the bitstream.

The encoded current image can be used as a reference image for other images to be processed later. Accordingly, the encoding device (100) can reconstruct or decode the encoded current image again and store the reconstructed or decoded image as a reference image in the reference picture buffer (190).

The quantized level can be dequantized in the dequantization unit (160) and inversely transformed in the inverse transformation unit (170). The dequantized and/or inversely transformed coefficients can be combined with a prediction block through an adder (117), and a reconstructed block can be generated by combining the dequantized and/or inversely transformed coefficients and the prediction block. Here, the dequantized and/or inversely transformed coefficients refer to coefficients on which at least one of dequantization and inverse transformation has been performed, and may refer to a reconstructed residual block. The dequantization unit (160) and the inverse transformation unit (170) can be performed in the reverse process of the quantization unit (140) and the transformation unit (130).

The restoration block may pass through a filter unit (180). The filter unit (180) may apply a deblocking filter, a sample adaptive offset (SAO), an adaptive loop filter (ALF), a bilateral filter (BIF), a Luma Mapping with Chroma Scaling (LMCS), etc. as a filtering technique, in whole or in part, to the restoration sample, restoration block, or restoration image. The filter unit (180) may also be referred to as an in-loop filter. In this case, the in-loop filter is also used as a name excluding LMCS.

A deblocking filter can remove block distortion that occurs at the boundaries between blocks. Whether to apply a deblocking filter to the current block can be determined based on the samples contained in several columns or rows within the block. When applying a deblocking filter to a block, different filters can be applied depending on the required deblocking filtering strength.

Sample adaptive offset can be used to compensate for encoding errors by adding an appropriate offset value to sample values. Sample adaptive offset can compensate for the offset from the original image on a sample-by-sample basis for deblocked images. This can be done by dividing the samples contained in the image into a fixed number of regions, determining the regions to be offset, and applying the offset to those regions. Alternatively, the offset can be applied by considering the edge information of each sample.

Bilateral filter (BIF) can also compensate for the offset from the original image on a sample-by-sample basis for the deblocked image.

An adaptive loop filter can perform filtering based on a comparison between a reconstructed image and the original image. By dividing the samples contained in the image into predetermined groups and determining the filter to be applied to each group, filtering can be performed differentially for each group. Information regarding whether to apply an adaptive loop filter can be signaled for each coding unit (CU), and the shape and filter coefficients of the adaptive loop filter applied to each block can vary.

In LMCS (Luma Mapping with Chroma Scaling), luma mapping (LM) refers to remapping luminance values through a piece-wise linear model, and chroma scaling (CS) refers to a technique that scales the residual values of chrominance components according to the average luminance value of the prediction signal. In particular, LMCS can be utilized as an HDR correction technique that reflects the characteristics of HDR (High Dynamic Range) images.

The restored block or restored image that has passed through the filter unit (180) may be stored in the reference picture buffer (190). The restored block that has passed through the filter unit (180) may be a part of the reference image. In other words, the reference image may be a restored image composed of restored blocks that have passed through the filter unit (180). The stored reference image may be used for inter-screen prediction or motion compensation thereafter.

FIG. 2 is a block diagram showing a configuration according to one embodiment of a decryption device to which the present disclosure is applied.

The decoding device (200) may be a decoder, a video decoding device, or an image decoding device.

Referring to FIG. 2, the decoding device (200) may include an entropy decoding unit (210), an inverse quantization unit (220), an inverse transformation unit (230), an intra prediction unit (240), a motion compensation unit (250), an adder (201), a switch (203), a filter unit (260), and a reference picture buffer (270).

The decoding device (200) can receive a bitstream output from the encoding device (100). The decoding device (200) can receive a bitstream stored in a computer-readable recording medium, or a bitstream streamed through a wired/wireless transmission medium. The decoding device (200) can perform decoding on the bitstream in intra mode or inter mode. In addition, the decoding device (200) can generate a restored image or a decoded image through decoding, and can output the restored image or the decoded image.

If the prediction mode used for decryption is intra mode, the switch (203) can be switched to intra. If the prediction mode used for decryption is inter mode, the switch (203) can be switched to inter.

The decoding device (200) can decode the input bitstream to obtain a reconstructed residual block and generate a prediction block. Once the reconstructed residual block and the prediction block are obtained, the decoding device (200) can generate a reconstructed block to be decoded by adding the reconstructed residual block and the prediction block. The block to be decoded may be referred to as a current block.

The entropy decoding unit (210) can generate symbols by performing entropy decoding according to a probability distribution for the bitstream. The generated symbols may include symbols in the form of quantized levels. Here, the entropy decoding method may be the reverse process of the entropy encoding method described above.

The entropy decoding unit (210) can change a one-dimensional vector-shaped coefficient into a two-dimensional block-shaped coefficient through a transform coefficient scanning method to decode a transform coefficient level (quantized level).

The quantized level can be inversely quantized in the inverse quantization unit (220) and inversely transformed in the inverse transformation unit (230). The quantized level can be generated as a restored residual block as a result of performing inverse quantization and/or inverse transformation. At this time, the inverse quantization unit (220) can apply a quantization matrix to the quantized level. The inverse quantization unit (220) and inverse transformation unit (230) applied to the decoding device can apply the same technology as the inverse quantization unit (160) and inverse transformation unit (170) applied to the encoding device described above.

When intra mode is used, the intra prediction unit (240) can generate a predicted block by performing spatial prediction on the current block using sample values of already decoded blocks surrounding the block to be decoded. The intra prediction unit (240) applied to the decoding device can apply the same technology as the intra prediction unit (120) applied to the encoding device described above.

When the inter mode is used, the motion compensation unit (250) can generate a prediction block by performing motion compensation using a motion vector and a reference image stored in the reference picture buffer (270) on the current block. The motion compensation unit (250) can generate a prediction block by applying an interpolation filter to a portion of the reference image when the value of the motion vector does not have an integer value. In order to perform motion compensation, it is possible to determine whether the motion compensation method of the prediction unit included in the corresponding encoding unit is skip mode, merge mode, AMVP mode, or current picture reference mode based on the encoding unit, and motion compensation can be performed according to each mode. The motion compensation unit (250) applied to the decoding device can apply the same technology as the motion compensation unit (122) applied to the encoding device described above.

The adder (201) can add the restored residual block and the predicted block to generate a restored block. The filter unit (260) can apply at least one of an Inverse-LMCS, a deblocking filter, a sample adaptive offset, and an adaptive loop filter to the restored block or restored image. The filter unit (260) applied to the decoding device can apply the same filtering technology as that applied to the filter unit (180) applied to the encoding device described above.

The filter unit (260) can output a restored image. The restored block or restored image can be stored in the reference picture buffer (270) and used for inter prediction. The restored block that has passed through the filter unit (260) can be a part of the reference image. In other words, the reference image can be a restored image composed of restored blocks that have passed through the filter unit (260). The stored reference image can be used for inter-screen prediction or motion compensation thereafter.

FIG. 3 is a diagram schematically illustrating a video coding system to which the present disclosure can be applied.

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

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.

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.

The encoding unit (12) can encode the input video/image. The encoding unit (12) can perform a series of procedures such as prediction, transformation, and quantization for compression and encoding efficiency. The encoding unit (12) can output encoded data (encoded video/image information) in the form of a bitstream. The detailed configuration of the encoding unit (12) can also be configured in the same manner as the encoding device (100) of FIG. 1 described above.

The transmission unit (13) can transmit encoded video/image information or data output in the form of a bitstream to the reception unit (21) of the decoding device (20) via a digital storage medium or a network in the form of a file or streaming. The digital storage medium can include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, SSD, etc. The transmission unit (13) can include an element for generating a media file through a predetermined file format and can include an element for transmission via a broadcasting/communication network. The reception unit (21) can extract/receive the bitstream from the storage medium or network and transmit it to the decoding unit (22).

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). The detailed configuration of the decoding unit (22) can also be configured in the same manner as the decoding device (200) of FIG. 2 described above.

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

Various methods can be used to perform intra prediction in video encoding/decoding methods. Specifically, matrix-based intra prediction or neural network-based intra prediction methods can be used to perform intra prediction. In this regard, information regarding these intra prediction methods can be signaled. To enhance the efficiency of matrix-based intra prediction or neural network-based intra prediction, a method for efficiently signaling information regarding these intra prediction methods may be required.

Matrix-based intra prediction is a technique that replaces conventional intra prediction by multiplying the restored reference sample line(s) on the left side of the block and the restored reference sample line(s) on the top side of the block by a weight matrix to derive a predicted value.

Matrix-based intra prediction can generate a predicted block for the current block by applying a weight matrix to the surrounding left and upper reference pixels of the current block. The process of performing matrix-based intra prediction can be described as follows.

FIG. 4 is a diagram illustrating a matrix-based intra prediction method according to an embodiment of the present disclosure. Here, a MIP prediction block may refer to a prediction block generated by matrix-based intra prediction.

Referring to FIG. 4, the previously restored region within the current picture based on the current block (401) may include reference pixels (403) adjacent to the current block. Here, the reference pixels (403) may include a left reference pixel and an upper reference pixel. In addition, a set of reference pixels adjacent to the current block may be defined as a reference template. The horizontal and vertical lengths of the reference template may be determined according to the intra prediction mode of the current block. For example, when the intra prediction mode of the current block is within a predetermined range, the horizontal length of the reference template may be twice the horizontal length of the current block, and the vertical length of the reference template may be twice the vertical length of the current block.

A MIP prediction block for the current block can be generated by multiplying pixels of the reference template by a weight matrix. Here, the matrix weights can be determined based on the size and intra prediction mode of the current block.

Matrix-based intra prediction can provide high performance using a low delay configuration, but has the disadvantages of long runtime and high complexity.

The present disclosure proposes various syntax elements related to intra prediction and signaling methods of syntax elements for activating matrix-based intra prediction on a slice-by-slice basis.

However, the intra prediction-related syntax elements and signaling methods of the syntax elements of the present disclosure may not be limited to slices. For example, the syntax elements and signaling methods of the syntax elements of the present disclosure may be extended and applied to various groups of coding blocks, such as tiles, blocks, segments, groups, and regions.

According to one embodiment of the present disclosure, the intra prediction related syntax element may include a syntax element capable of enabling/disabling matrix-based intra prediction for blocks of an intra slice (e.g., I slice) and a syntax element capable of enabling/disabling matrix-based intra prediction for intra-predicted blocks of an inter slice (e.g., P slice, B slice).

For example, intra prediction related syntactic elements can be independently signaled in the sequence parameter set (SPS), as shown in Table 1.

Here, sps_intra_mip_intra_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks of an intra slice. If sps_intra_mip_intra_slice_enabled_flag is not signaled, the value of the flag may be inferred to be 1. And, sps_intra_mip_inter_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for intra-predicted blocks of an inter slice. If sps_intra_mip_inter_slice_enabled_flag is not signaled, the value of the flag may be inferred to be 1.

The above syntax elements can be used to reduce the execution time/complexity of matrix-based intra prediction. For example, in a low-latency configuration, if the value of sps_intra_mip_intra_slice_enabled_flag signaled is 1 and the value of sps_intra_mip_inter_slice_enabled_flag is 0, matrix-based intra prediction can be enabled only in intra slices among slices. Therefore, the execution time/complexity can be reduced while maintaining coding performance.

According to another embodiment of the present disclosure, in addition to the conventional matrix-based intra prediction, matrix-based prediction using surrounding pixels of the current block can be used.

According to a matrix-based intra prediction method using the surrounding pixels of the current block, a virtual intra prediction mode (VIPM) can be derived using the gradients of the surrounding pixels. Then, a matrix corresponding to the VIPM can be applied to the surrounding pixels to generate a prediction value for the current block.

Here, the surrounding pixels may include adjacent surrounding pixels located adjacent to the current block and non-adjacent surrounding pixels located not adjacent to the current block. The adjacent surrounding pixels may include pixels surrounding the current block of a preset shape and location. In addition, the non-adjacent surrounding pixels may include pixels in a predetermined area in the encoder/decoder or pixels in an arbitrary area indicated by additional information of the current block.

The adjacent and non-adjacent surrounding pixels used to derive VIPM may be as described below.

FIG. 5 is a diagram for explaining the surrounding pixels of a current block according to one embodiment of the present disclosure. Specifically, FIG. 5 is a diagram for explaining adjacent surrounding pixels among the surrounding pixels of the current block.

Referring to Fig. 5, adjacent neighboring pixels (503), which are pixels spatially adjacent to the current block (501) in the current picture (500), can be defined. For example, the adjacent neighboring pixels can be composed of at least one of an upper adjacent neighboring pixel (A-D), an upper right adjacent neighboring pixel (E-H), a left adjacent neighboring pixel (I-L), a left below adjacent neighboring pixel (M-P), and an upper left adjacent neighboring pixel (Q).

Meanwhile, the location of the adjacent surrounding pixels in FIG. 5 is an example, and the location of the adjacent surrounding pixels may be any location adjacent to the current block. The location of the adjacent surrounding pixels may be predefined by the encoder/decoder. Alternatively, information regarding the location of the adjacent surrounding pixels may be determined by the encoder and transmitted to the decoder. Alternatively, the location of the adjacent surrounding pixels may be indicated by information regarding the current block.

FIG. 6 is a diagram for explaining the surrounding pixels of a current block according to one embodiment of the present disclosure. Specifically, FIG. 6 is a diagram for explaining non-adjacent surrounding pixels among the surrounding pixels of the current block.

Referring to Fig. 6, a predetermined area around a current block (601) in a current picture (600) can be defined as a neighboring area (602). In addition, pixels included in the neighboring area but not spatially adjacent to the current block can be defined as non-adjacent neighboring pixels (603).

Meanwhile, in Fig. 6, the surrounding area including the non-adjacent surrounding pixels (603) is the left area, the upper left area, and the upper area of the current block, but this is just one example, and the non-adjacent surrounding pixels (603) may be included in a preset area. In this case, the preset area may be any one of the current tile, the current slice, and the current picture including the current block.

Meanwhile, the locations of non-adjacent surrounding pixels in FIG. 6 are just one example, and the locations of non-adjacent surrounding pixels can be any location within the surrounding area. The locations of non-adjacent surrounding pixels can be determined by an agreement between the encoder and decoder. Furthermore, information regarding the locations of non-adjacent surrounding pixels can be determined by the encoder and transmitted to the decoder. Furthermore, the locations of non-adjacent surrounding pixels can be indicated by information regarding the current block.

And, VIPM of the current block can be derived based on the gradient histogram of the surrounding pixels. Edge detection filters such as Sobel filter, Roberts cross filter, Prewitt filter, Scharr filter, Laplacian filter, etc. can be applied to the surrounding pixels. As a result of applying the edge detection filter to the surrounding pixels, the gradient of the corresponding pixel can be calculated. And, based on the calculated gradient, a histogram of gradient (HoG) can be generated.

And, the VIPM of the current block can be determined based on intra prediction modes mapped to any N gradients selected in ascending order of amplitude from a histogram of gradients. For example, the VIPM of the current block can be determined as one intra prediction mode among the intra prediction modes mapped to the N gradients. Here, the determined one intra prediction mode can be an intra prediction mode having a smallest index value or an intra prediction mode having a largest index value among the intra prediction modes mapped to the N gradients.

Here, if the intensity of the gradient in the histogram of the gradient is below a certain value, the VIPM of the current block can be determined as a predetermined non-directional mode. The predetermined non-directional mode can be a planar mode or a DC mode.

According to another embodiment, prediction blocks for the current block can be generated using each of the intra prediction modes mapped to any N gradients selected from a histogram of gradients. Then, based on a cost function, the cost values of the prediction blocks can be compared, and the matrix corresponding to the intra prediction mode with the lowest cost can be used.

On the other hand, according to another embodiment, the VIPM of the current block can be derived based on a gradient histogram of pixels within the current block. An edge detection filter, such as a Sobel filter, a Roberts cross filter, a Prewitt filter, a Scharr filter, or a Laplacian filter, can be applied to the pixels within the current block. As a result of applying the edge detection filter to the pixels within the current block, the gradient of the corresponding pixel can be calculated. Then, a histogram of gradients (HoG) can be generated based on the calculated gradients.

In addition, the VIPM of the current block can be determined based on intra prediction modes mapped to N random gradients selected in ascending order of amplitude from the gradient histogram. For example, the VIPM of the current block can be determined based on one intra prediction mode among the N intra prediction modes mapped to the gradients.

According to one embodiment of a syntax element signaling method at a high level of the present disclosure, syntax elements capable of activating/deactivating matrix-based intra prediction for blocks of an intra slice, syntax elements capable of activating/deactivating matrix-based intra prediction for intra-predicted blocks of an inter slice, and syntax elements capable of activating/deactivating matrix-based intra prediction for inter-predicted blocks in an inter slice may be signaled, respectively.

For example, intra prediction related syntactic elements can be independently signaled in SPS, as shown in Table 2.

Here, sps_intra_mip_intra_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks in an intra slice. If sps_intra_mip_intra_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1.

Additionally, sps_intra_mip_inter_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks in an inter-slice. If sps_intra_mip_inter_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1.

And, sps_intra_mip_inter_mode_enabled_flag can be a flag indicating whether intra prediction is enabled for blocks that are inter-predicted in an inter slice. That is, sps_intra_mip_inter_mode_enabled_flag can be a flag indicating whether matrix-based prediction using adjacent neighboring pixels and/or non-adjacent neighboring pixels of a block that is inter-predicted is enabled. If sps_intra_mip_inter_mode_enabled_flag is not signaled, the value of the flag can be assumed to be 0.

The above syntax elements can reduce the execution time and complexity of matrix-based intra prediction. For example, when the value of sps_intra_mip_intra_slice_enabled_flag signaled in a low-latency configuration is 1, the value of sps_intra_mip_inter_slice_enabled_flag is 0, and the value of sps_intra_mip_inter_mode_enabled_flag is 1, matrix-based intra prediction and VIPM-based matrix-based intra prediction in intra slices can be activated.

Alternatively, in a low-latency configuration, if the value of sps_intra_mip_intra_slice_enabled_flag is 0, the value of sps_intra_mip_inter_slice_enabled_flag is 0, and the value of sps_intra_mip_inter_mode_enabled_flag is 1, VIPM-based matrix-based intra prediction for inter-predicted blocks can be enabled.

Therefore, complexity can be significantly reduced while maintaining coding performance.

The intra prediction-related syntax elements and signaling methods of the syntax elements of the present disclosure may not be limited to slice units. For example, the syntax elements and signaling methods of the syntax elements of the present disclosure may be extended and applied to various coding blocks, such as tiles, blocks, segments, groups, and regions.

In addition, the intra prediction related syntax elements of the present disclosure can be signaled at other upper layer levels, such as video parameter set (VPS), picture parameter set (PPS), picture header (PH), slice header (SH), etc., in addition to SPS.

According to another embodiment of the present disclosure, the syntax element signaled in the SPS may further include a syntax element sps_mip_enabled_flag indicating whether matrix-based intra prediction technology is enabled. If the value of sps_mip_enabled_flag is 1, matrix-based intra prediction may be enabled. On the other hand, if the value of sps_mip_enabled_flag is 0, matrix-based intra prediction may be disabled.

Matrix-based intra prediction related syntax elements including sps_mip_enabled_flag can be signaled as shown in Table 3.

Here, sps_intra_mip_intra_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks of an intra slice. And, sps_intra_mip_inter_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks to be intra-predicted in an inter slice.

These two flags can be signaled dependently on the sps_mip_enabled_flag syntactic element, which indicates whether matrix-based intra prediction technology is enabled. Specifically, these two flags can be signaled only when sps_mip_enabled_flag is 1. If sps_mip_enabled_flag is 0, the two flags are not signaled and can be assumed to be 0.

Alternatively, matrix-based intra prediction related syntax elements including sps_mip_enabled_flag can be signaled as shown in Table 4.

Here, sps_intra_mip_intra_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks of an intra slice. And, sps_intra_mip_inter_slice_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks to be intra-predicted of an inter slice. And, sps_intra_mip_inter_mode_enabled_flag may be a flag indicating whether matrix-based intra prediction is enabled for blocks to be inter-predicted of an inter slice.

These three flags can be signaled dependently on the sps_mip_enabled_flag syntactic element, which indicates whether matrix-based intra prediction technology is enabled. Specifically, these three flags can be signaled only when sps_mip_enabled_flag is 1. If sps_mip_enabled_flag is 0, the three flags are not signaled and can be assumed to be 0.

Neural network-based intra prediction is an intra prediction technique that extends matrix-based intra prediction. Specifically, neural network-based intra prediction uses a single or multiple models based on fully connected layers (FC layers).

Neural network-based intra prediction can generate a predicted block for the current block using neighboring left and upper reference pixels of the current block through a preprocessing process, a neural network-based parameter determination process, and a postprocessing process. The preprocessing process may include normalization and sample padding. The neural network-based intra prediction process may be described as follows.

FIG. 7 is a diagram illustrating a neural network-based intra prediction method according to an embodiment of the present disclosure. Here, a neural network-based intra prediction block may refer to a prediction block generated by neural network-based intra prediction.

Referring to FIG. 7, the context generated by the restored pixels adjacent to the left and/or top of the current block (701) can be preprocessed. Then, the preprocessed context can be input to a neural network for block prediction. The predicted value for the current block can be generated by applying postprocessing to the initial predicted value.

Neural network-based intra prediction provides high performance for low delay configurations, but has the disadvantage of high runtime/complexity.

Accordingly, the present disclosure proposes various syntactic elements and their signaling structures for controlling neural network-based intra prediction on a slice-by-slice basis.

According to one embodiment of the present disclosure, the intra prediction related syntax element may include a syntax element capable of activating/deactivating neural network-based intra prediction for blocks of an intra slice and a syntax element capable of activating/deactivating neural network-based intra prediction for intra-predicted blocks of an inter slice.

For example, intra prediction related syntactic elements can be independently signaled in SPS, as shown in Table 5.

Here, sps_intra_nnip_intra_slice_enabled_flag may be a flag indicating whether to enable neural network-based intra prediction for blocks of an intra slice. If sps_intra_nnip_intra_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1. And, sps_inter_nnip_inter_slice_enabled_flag may be a flag indicating whether to enable neural network-based intra prediction for blocks to be intra-predicted in an inter slice. If sps_inter_nnip_inter_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1.

The above syntax elements can be used to reduce the execution time/complexity of neural network-based intra prediction. For example, if the signaled sps_intra_nnip_intra_slice_enabled_flag value is 1 and sps_inter_nnip_inter_slice_enabled_flag value is 0, neural network-based intra prediction can be performed only on intra slices among slices. Therefore, the execution time/complexity can be reduced while maintaining coding performance.

According to another embodiment of the present disclosure, in addition to the existing neural network-based intra prediction, a neural network-based intra prediction using surrounding pixels of the current block may be used.

According to a neural network-based intra prediction method utilizing the surrounding pixels of the current block, a VIPM can be derived using the gradients of the surrounding pixels. Then, by applying a neural network model corresponding to the VIPM to the surrounding pixels, a predicted value for the current block can be generated.

Here, the surrounding pixels may include adjacent surrounding pixels located adjacent to the current block and non-adjacent surrounding pixels located not adjacent to the current block. The adjacent surrounding pixels may include pixels surrounding the current block of a preset shape and location. In addition, the non-adjacent surrounding pixels may include pixels in a predetermined area in the encoder/decoder or pixels in an arbitrary area indicated by additional information of the current block.

The adjacent and non-adjacent surrounding pixels used to derive VIPM may be as described in FIGS. 5 and 6 and their related contents.

Furthermore, the VIPM of the current block can be derived based on the gradient histogram of the surrounding pixels. Edge detection filters such as the Sobel filter, Roberts cross filter, Prewitt filter, Schar filter, and Laplacian filter can be applied to the surrounding pixels. As a result of applying the edge detection filter to the surrounding pixels, the gradient of the corresponding pixel can be calculated. Furthermore, a gradient histogram can be generated based on the calculated gradient.

According to one embodiment, the VIPM of the current block may be determined based on intra prediction modes mapped to any N gradients selected in ascending order of amplitude from a histogram of gradients. For example, the VIPM of the current block may be determined as one intra prediction mode among the intra prediction modes mapped to the N gradients. Here, the determined one intra prediction mode may be an intra prediction mode having a smallest index value or an intra prediction mode having a largest index value among the intra prediction modes mapped to the N gradients.

Here, if the intensity of the gradient in the histogram of the gradient is below a certain value, the VIPM of the current block can be determined as a predetermined non-directional mode. The predetermined non-directional mode can be a planar mode or a DC mode.

According to another embodiment, prediction blocks for the current block can be generated using each of the intra prediction modes mapped to any N gradients selected from a histogram of gradients. Then, based on a cost function, the cost values of the prediction blocks can be compared, and the neural network model corresponding to the intra prediction mode with the lowest cost can be used.

On the other hand, according to another embodiment, the VIPM of the current block can be derived based on a gradient histogram of pixels within the current block. An edge detection filter, such as a Sobel filter, a Roberts cross filter, a Prewitt filter, a Schar filter, or a Laplacian filter, can be applied to the pixels within the current block. As a result of applying the edge detection filter to the pixels within the current block, the gradient of the corresponding pixel can be calculated. Then, a histogram of gradients (HoG) can be generated based on the calculated gradients.

In addition, the VIPM of the current block can be determined based on intra prediction modes mapped to N random gradients selected in ascending order of amplitude from the gradient histogram. For example, the VIPM of the current block can be determined based on one intra prediction mode among the N intra prediction modes mapped to the gradients.

In another embodiment, in addition to conventional neural network-based intra prediction, neural network-based intra prediction based on the quantization coefficients of the current block can be additionally used. Depending on the quantization coefficients, the correlation between pixels in the current block and pixels in surrounding blocks can vary. Therefore, utilizing different neural network models trained based on quantization coefficients can improve the performance of neural network-based intra prediction.

According to one embodiment of the syntax element signaling method at a high level of the present disclosure, syntax elements capable of activating/deactivating neural network-based intra prediction for blocks of an intra slice, syntax elements capable of activating/deactivating neural network-based intra prediction for intra-predicted blocks of an inter slice, and syntax elements capable of activating/deactivating neural network-based intra prediction for inter-predicted blocks in an inter slice may be signaled, respectively.

For example, intra prediction related syntactic elements can be independently signaled in SPS, as shown in Table 6.

Here, sps_intra_nnip_intra_slice_enabled_flag may be a flag indicating whether neural network-based intra prediction is enabled for blocks in an intra slice. If sps_intra_nnip_intra_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1.

Additionally, sps_intra_nnip_inter_slice_enabled_flag may be a flag indicating whether neural network-based intra prediction is enabled for intra-predicted blocks of an inter-slice. If sps_intra_nnip_inter_slice_enabled_flag is not signaled, the value of the flag may be assumed to be 1.

And, sps_intra_nnip_inter_mode_enabled_flag can be a flag indicating whether intra prediction is enabled for blocks that are inter-predicted in an inter slice. That is, sps_intra_nnip_inter_mode_enabled_flag can be a flag indicating whether neural network-based intra prediction using adjacent neighboring pixels and/or non-adjacent neighboring pixels of a block that is inter-predicted is enabled. If sps_intra_nnip_inter_mode_enabled_flag is not signaled, the value of the flag can be assumed to be 0.

The above syntax elements can be used to reduce the execution time/complexity of the low-latency configuration. For example, if the value of sps_intra_nnip_intra_slice_enabled_flag signaled in the low-latency configuration is 1, the value of sps_intra_nnip_inter_slice_enabled_flag is 0, and the value of sps_intra_nnip_inter_mode_enabled_flag is 1, neural network-based intra prediction in the intra slice and neural network-based intra prediction based on VIPM can be activated.

Alternatively, in a low-latency configuration, if the value of sps_intra_nnip_intra_slice_enabled_flag is 0, the value of sps_intra_nnip_inter_slice_enabled_flag is 0, and the value of sps_intra_nnip_inter_mode_enabled_flag is 1, neural network-based intra prediction based on VIPM can be enabled.

Therefore, complexity can be significantly reduced while maintaining coding performance.

The intra prediction-related syntax elements and signaling methods of the syntax elements of the present disclosure may not be limited to slice units. For example, the syntax elements and signaling methods of the syntax elements of the present disclosure may be extended and applied to various coding blocks, such as tiles, blocks, segments, groups, and regions.

In addition, the intra prediction related syntax elements of the present disclosure can be signaled at other upper layer levels, such as video parameter set (VPS), picture parameter set (PPS), picture header (PH), slice header (SH), etc., in addition to SPS.

According to another embodiment of the present disclosure, the syntax element signaled in the SPS may further include a syntax element sps_nnip_enabled_flag indicating whether a neural network-based intra prediction technique is enabled. If the value of sps_nnip_enabled_flag is 1, the neural network-based intra prediction may be enabled. On the other hand, if the value of sps_nnip_enabled_flag is 0, the neural network-based intra prediction may be disabled.

Intra prediction related syntax elements including sps_nnip_enabled_flag can be signaled as shown in Table 7.

Here, sps_intra_nnip_intra_slice_enabled_flag may refer to a flag that enables neural network-based intra prediction for blocks in an intra slice. sps_intra_nnip_inter_slice_enabled_flag may refer to a flag that enables neural network-based intra prediction for blocks to be intra-predicted in an inter slice.

These two flags can be signaled dependently on the sps_nnip_enabled_flag syntactic element, which indicates whether the neural network-based intra prediction technology is enabled. Specifically, these two flags can be signaled only when sps_nnip_enabled_flag is 1. If sps_nnip_enabled_flag is 0, the two flags are not signaled and can be assumed to be 0.

Alternatively, intra prediction related syntax elements including sps_nnip_enabled_flag can be signaled as shown in Table 8.

Here, sps_intra_nnip_intra_slice_enabled_flag may be a flag indicating whether to enable neural network-based intra prediction for blocks in an intra slice. And, sps_intra_nnip_inter_slice_enabled_flag may be a flag indicating whether to enable neural network-based intra prediction for blocks that are intra-predicted in an inter slice. And, sps_intra_nnip_inter_mode_enabled_flag may be a flag indicating whether to enable neural network-based intra prediction for blocks that are inter-predicted in an inter slice.

These three flags can be signaled dependent on the sps_nnip_enabled_flag syntactic element, which indicates whether the neural network-based intra prediction technology is enabled. Specifically, these three flags can be signaled only when sps_nnip_enabled_flag is 1. If sps_nnip_enabled_flag is 0, the three flags are not signaled and can be assumed to be 0.

According to one embodiment of the present disclosure, a syntax element indicating whether matrix-based intra prediction is enabled and a syntax element indicating whether neural network-based intra prediction is enabled may be signaled together. Specifically, the syntax element indicating whether matrix-based intra prediction is enabled and the syntax element indicating whether neural network-based intra prediction is enabled may be used together, either independently or dependently.

For example, a syntactic element indicating whether matrix-based intra prediction is enabled and a syntactic element indicating whether neural network-based intra prediction is enabled can be independently signaled as shown in Table 9 below.

Alternatively, the syntax element indicating whether matrix-based intra prediction is enabled and the syntax element indicating whether neural network-based intra prediction is enabled can be signaled independently as shown in Table 10 below.

In this case, there is an advantage of not using conditional statements that cause delays when signaling/parsing syntactic elements.

On the other hand, the syntactic element indicating whether matrix-based intra prediction is enabled and the syntactic element indicating whether neural network-based intra prediction is enabled can be signaled dependently as shown in Table 11 below.

Here, sps_intra_nnip_intra_slice_enabled_flag can be signaled only when sps_intra_mip_intra_slice_enabled_flag is 0. On the other hand, if sps_intra_mip_intra_slice_enabled_flag is 1, sps_intra_nnip_intra_slice_enabled_flag is not signaled and can be assumed to be 0.

Also, sps_intra_nnip_inter_slice_enabled_flag can be signaled only when sps_intra_mip_inter_slice_enabled_flag is 0. On the other hand, if sps_intra_mip_inter_slice_enabled_flag is 1, sps_intra_nnip_inter_slice_enabled_flag is not signaled and can be assumed to be 0.

Alternatively, the syntax element indicating whether matrix-based intra prediction is enabled and the syntax element indicating whether neural network-based intra prediction is enabled can be signaled dependently as shown in Table 12 below.

Here, sps_intra_nnip_intra_slice_enabled_flag can be signaled only when sps_intra_mip_intra_slice_enabled_flag is 0. On the other hand, if sps_intra_mip_intra_slice_enabled_flag is 1, sps_intra_nnip_intra_slice_enabled_flag is not signaled and can be assumed to be 0.

Also, sps_intra_nnip_inter_slice_enabled_flag can be signaled only when sps_intra_mip_inter_slice_enabled_flag is 0. On the other hand, if sps_intra_mip_inter_slice_enabled_flag is 1, sps_intra_nnip_inter_slice_enabled_flag is not signaled and can be assumed to be 0.

And, sps_intra_nnip_inter_mode_enabled_flag can be signaled only when sps_intra_mip_inter_mode_enabled_flag is 0. On the other hand, if sps_intra_mip_inter_mode_enabled_flag is 1, sps_intra_nnip_inter_mode_enabled_flag is not signaled and can be assumed to be 0.

That is, when utilizing the proposed syntax elements, there is an advantage in that the number of signaled syntax elements can be reduced in a situation where matrix-based intra prediction is to be used for blocks of an intra slice and neural network-based intra prediction is to be used for intra-predicted blocks of an inter slice.

According to the embodiments of Tables 11 and 12, the neural network-based intra prediction syntax element can be signaled dependently on the matrix-based intra prediction-related syntax element. However, it is also possible for the matrix-based intra prediction-related syntax element to be signaled dependently on the neural network-based intra prediction syntax element.

In another embodiment, matrix-based intra prediction and neural network-based intra prediction can be activated by a single syntactic element. For example, intra prediction-related syntactic elements can be signaled as shown in Table 13.

Here, sps_intra_mip_intra_slice_type and sps_intra_mip_inter_slice_type can have values from 0 to 2. When the value of sps_intra_mip_intra_slice_type is 0, matrix-based intra prediction and neural network-based intra prediction can be disabled in blocks of an intra slice. When the value of sps_intra_mip_intra_slice_type is 1, matrix-based intra prediction can be activated in blocks of an intra slice. When the value of sps_intra_mip_intra_slice_type is 2, neural network-based intra prediction can be activated in blocks of an intra slice.

When the value of sps_intra_mip_inter_slice_type is 0, matrix-based intra prediction and neural network-based intra prediction can be disabled in the intra-predicted blocks of the inter-slice. When the value of sps_intra_mip_inter_slice_type is 1, matrix-based intra prediction can be enabled in the intra-predicted blocks of the inter-slice. When the value of sps_intra_mip_inter_slice_type is 2, neural network-based intra prediction can be enabled in the intra-predicted blocks of the inter-slice.

Alternatively, matrix-based intra prediction and neural network-based intra prediction can be activated by a single syntactic element. For example, intra prediction-related syntactic elements can be signaled as shown in Table 14.

When the value of sps_intra_mip_inter_mode_type is 0, matrix-based intra prediction and neural network-based intra prediction can be disabled in intra-predicted blocks of an inter-slice. When the value of sps_intra_mip_inter_mode_type is 1, matrix-based intra prediction can be enabled in intra-predicted blocks of an inter-slice. When the value of sps_intra_mip_inter_mode_type is 2, neural network-based intra prediction can be enabled in intra-predicted blocks of an inter-slice.

A method of image decoding that performs intra prediction using information indicating whether intra prediction is activated on a slice-by-slice basis may be as described below.

FIG. 8 is a flowchart illustrating an image decoding method according to an embodiment of the present disclosure. The image decoding method of FIG. 8 can be performed by an image decoding device.

Referring to FIG. 8, the video decoding device can obtain information indicating whether to activate predefined intra prediction according to a slice type (S810). Here, the information indicating whether to activate predefined intra prediction according to the slice type may include information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted in a P slice or a B slice.

In addition, information indicating whether to activate predefined intra prediction according to the slice type may further include information indicating whether to activate predefined intra prediction for an inter-predicted block of a P slice or a B slice.

The video decoding device can determine the prediction mode of the current block based on information indicating whether to activate predefined intra prediction according to the slice type (S820).

The video decoding device can generate a prediction block of the current block based on the prediction mode (S830).

Here, the predefined intra prediction may be matrix-based intra prediction.

Here, the prediction block of the current block can be generated by combining an inter prediction block generated based on the inter prediction mode of the current block and an intra prediction block generated based on a matrix corresponding to the intra prediction mode.

Here, the intra prediction mode can be derived based on the gradient histogram of the surrounding blocks of the current block. Alternatively, the intra prediction mode can be derived based on the gradient histogram of the samples of the inter prediction block.

Here, information indicating whether to activate intra prediction defined according to the slice type can be obtained based on information indicating whether to activate intra prediction based on a matrix.

Meanwhile, the predefined intra prediction may be an intra prediction based on an artificial neural network model.

Here, the prediction block of the current block can be generated by combining an inter prediction block generated based on the inter prediction mode of the current block and an intra prediction block generated based on an artificial neural network model corresponding to the intra prediction mode.

Here, the intra prediction mode can be derived based on the gradient histogram of the surrounding blocks of the current block. Alternatively, the intra prediction mode can be derived based on the gradient histogram of the samples of the inter prediction block.

Here, information indicating whether to activate intra prediction defined according to the slice type can be obtained based on information indicating whether to activate intra prediction based on an artificial neural network model.

Here, information indicating whether to activate predefined intra prediction according to the slice type can indicate whether to activate matrix-based intra prediction and whether to activate intra prediction based on an artificial neural network model.

Meanwhile, the steps described in FIG. 8 can be performed in the same manner in an image encoding method. Furthermore, a bitstream can be generated by an image encoding method including the steps described in FIG. 8. The bitstream can be stored on a non-transitory computer-readable recording medium and can also be transmitted (or streamed).

FIG. 9 is a diagram exemplifying a content streaming system to which an embodiment according to the present disclosure can be applied.

As illustrated in FIG. 9, 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.

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

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.

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.

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.

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.

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.

The above embodiments can be performed in the same or corresponding manner in an encoding device and a decoding device. In addition, an image can be encoded/decoded using at least one or a combination of at least one of the above embodiments.

The order in which the above embodiments are applied may be different in the encoding device and the decoding device. Alternatively, the order in which the above embodiments are applied may be the same in the encoding device and the decoding device.

The above embodiments can be performed for each of the luminance and chrominance signals. Alternatively, the above embodiments can be performed identically for the luminance and chrominance signals.

In the above embodiments, the methods are described based on a flowchart as a series of steps or units. However, the present disclosure is not limited to the order of the steps, and some steps may occur in a different order or simultaneously with other steps described above. Furthermore, those skilled in the art will understand that the steps depicted in the flowchart are not exclusive, and that other steps may be included, or one or more steps in the flowchart may be deleted without affecting the scope of the present disclosure.

The above embodiments may be implemented in the form of program commands that can be executed by various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable recording medium may be those specifically designed and configured for the present disclosure, or may be known and usable by those skilled in the art of computer software.

The bitstream generated by the encoding method according to the above embodiment can be stored in a non-transitory computer-readable recording medium. In addition, the bitstream stored in the non-transitory computer-readable recording medium can be decoded by the decoding method according to the above embodiment.

Here, examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices may be configured to operate as one or more software modules to perform processing according to the present disclosure, and vice versa.

Although the present disclosure has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present disclosure, and the present disclosure is not limited to the above examples, and a person having ordinary knowledge in the technical field to which the present disclosure belongs can make various modifications and variations from this description.

Therefore, the spirit of the present disclosure should not be limited to the embodiments described above, and all modifications that are equivalent or equivalent to the following claims as well as the claims are considered to fall within the scope of the spirit of the present disclosure.

The present invention can be used in a device for encoding/decoding an image and a recording medium storing a bitstream.

Claims (16)

In the video decryption method, A step of obtaining information indicating whether to activate predefined intra prediction according to a slice type; A step of determining a prediction mode of a current block based on information indicating whether to activate intra prediction defined according to the above slice type; and A step of generating a prediction block of the current block based on the prediction mode, Information indicating whether to activate intra prediction defined according to the above slice type is: A video decoding method characterized by including information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice. In the first paragraph, Information indicating whether to activate intra prediction defined according to the above slice type is: A video decoding method, characterized in that it further includes information indicating whether to activate predefined intra prediction for an inter-predicted block of a P slice or a B slice. In the first paragraph, The above defined intra prediction is, An image decoding method characterized by matrix-based intra prediction. In the first paragraph, The prediction block of the current block above is, An image decoding method characterized in that the image is generated by combining an inter prediction block generated based on an inter prediction mode of the current block and an intra prediction block generated based on a matrix corresponding to an intra prediction mode. In paragraph 4, The above intra prediction mode is, An image decoding method characterized in that it is derived based on a gradient histogram of surrounding blocks of the current block. In paragraph 4, The above intra prediction mode is, An image decoding method characterized in that it is derived based on a gradient histogram of samples of the above inter prediction block. In the first paragraph, Information indicating whether to activate intra prediction defined according to the above slice type is: An image decoding method characterized in that it is obtained based on information indicating whether matrix-based intra prediction is activated. In the first paragraph, The above defined intra prediction is, An image decoding method characterized by intra prediction based on an artificial neural network model. In the first paragraph, The prediction block of the current block above is, An image decoding method characterized in that the image is generated by combining an inter prediction block generated based on the inter prediction mode of the current block and an intra prediction block generated based on an artificial neural network model corresponding to the intra prediction mode. In paragraph 9, The above intra prediction mode is, An image decoding method characterized in that it is derived based on a gradient histogram of surrounding blocks of the current block. In paragraph 9, The above intra prediction mode is, An image decoding method characterized in that it is derived based on a gradient histogram of samples of the above inter prediction block. In the first paragraph, Information indicating whether to activate intra prediction defined according to the above slice type is: An image decoding method characterized in that it is obtained based on information indicating whether to activate intra prediction based on an artificial neural network model. In the first paragraph, Information indicating whether to activate intra prediction defined according to the above slice type is: An image decoding method characterized by indicating whether to activate matrix-based intra prediction and whether to activate artificial neural network model-based intra prediction. In the image encoding method, A step of obtaining information indicating whether to activate predefined intra prediction according to a slice type; A step of determining a prediction mode of a current block based on information indicating whether to activate intra prediction defined according to the above slice type; and A step of generating a prediction block of the current block based on the prediction mode, Information indicating whether to activate intra prediction defined according to the above slice type is: A video encoding method characterized in that it includes information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice. In a non-transitory computer-readable recording medium storing a bitstream generated by a video encoding method, The above image encoding method is, A step of obtaining information indicating whether to activate predefined intra prediction according to a slice type; A step of determining a prediction mode of a current block based on information indicating whether to activate intra prediction defined according to the above slice type; and A step of generating a prediction block of the current block based on the prediction mode, Information indicating whether to activate intra prediction defined according to the above slice type is: A non-transitory computer-readable recording medium characterized by including information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice. In a method for transmitting a bitstream generated by a video encoding method, The above transmission method includes a step of transmitting the bitstream, The above image encoding method is, A step of obtaining information indicating whether to activate predefined intra prediction according to a slice type; A step of determining a prediction mode of a current block based on information indicating whether to activate intra prediction defined according to the above slice type; and A step of generating a prediction block of the current block based on the prediction mode, Information indicating whether to activate intra prediction defined according to the above slice type is: A transmission method characterized in that it includes information indicating whether to activate predefined intra prediction for a block of an I slice and information indicating whether to activate predefined intra prediction for a block to be intra-predicted of a P slice or a B slice.