Neural network-based filtering process for multiple color components in video coding

Abstract

A method of processing video data includes receiving a syntax element defining a filtering mode for a neural network (NN) model for both a first color component and a second color component, in the defined filtering mode, applying an instance of the NN model to a first block of the first color component to generate a first filtered block, and in the defined filtering mode, applying an instance of the NN model to a second block of the first color component to generate a second filtered block. And storing the first filtered block for a coding unit (CU).

Description

[0001] This application claims the benefit of U.S. Patent Application No. 18 / 331,674, filed on June 8, 2023, and U.S. Provisional Application No. 63 / 367,713, filed on July 5, 2022, the entire contents of which are incorporated herein by reference. U.S. Patent Application No. 18 / 331,674, filed on June 8, 2023, claims the benefit of U.S. Provisional Application No. 63 / 367,713, filed on July 5, 2022. Technical Field

[0002] The present disclosure relates to video encoding and video decoding. Background Art

[0003] Digital video capabilities may be incorporated into a wide variety of devices, including digital televisions, digital direct broadcast systems, wireless broadcast systems, personal digital assistants (PDAs), laptop or desktop computers, tablet computers, e-book readers, digital cameras, digital recording devices, digital media players, video game devices, video game consoles, cellular or satellite wireless telephones, so-called "smart phones", video teleconferencing equipment, video streaming devices, etc. Digital video devices implement video coding techniques, such as the standards specified by MPEG-2, MPEG-4, ITU-T H.263, ITU-T H.264 / MPEG-4 Part 10, Advanced Video Coding (AVC), ITU-T H.265 / High Efficiency Video Coding (HEVC), ITU-T H.266 / Versatile Video Coding (VVC) and extensions of these standards, as well as proprietary video codecs / formats such as those described in AOMedia Video 1 (AV1) developed by the Alliance for Open Media. Video devices may more efficiently transmit, receive, encode, decode and / or store digital video information by implementing these video coding techniques.

[0004] Video coding techniques include spatial (intra-frame) prediction and / or temporal (inter-frame) prediction to reduce or eliminate redundancy inherent in video sequences. For block-based video coding, a video slice (e.g., a video picture or a portion of a video picture) may be divided into video blocks, which may also be referred to as coding tree units (CTUs), coding units (CUs), and / or coding nodes. Video blocks in an intra-coded (I) slice of a picture are encoded using spatial prediction relative to reference samples in neighboring blocks in the same picture. Video blocks in an inter-coded (P or B) slice of a picture may use spatial prediction relative to reference samples in neighboring blocks in the same picture, or temporal prediction relative to reference samples in other reference pictures. Pictures may be referred to as frames, and reference pictures may be referred to as reference frames. Summary of the invention

[0005] In general, the present disclosure describes techniques for filtering distorted pictures. The filtering process may be based on machine learning techniques such as neural network techniques. The example techniques may be used in the context of an advanced video codec, such as according to the Versatile Video Coding (VVC) standard, an extension of VVC, a next generation video coding standard, or any other video codec.

[0006] As described in more detail, the present disclosure describes an example of neural network-based filtering in which color components (e.g., chroma components) of video data share the same neural network mode. For example, a video encoder and a video decoder can select the same neural network mode for the two chroma components, rather than selecting different neural network modes for the two chroma components. In this way, because the video encoder and the video decoder can perform fewer filter selections and / or filter execution times compared to the case where different neural network modes are selected for the two chroma components, this can reduce complexity and processing time.

[0007] In one example, the present disclosure describes a method for processing video data, the method comprising: receiving a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component; in the defined filtering mode, applying an instance of the NN model to a first block of the first color component to generate a first filtered block; and storing the first filtered block for a decoding unit (CU).

[0008] In one example, the present disclosure describes a device for processing video data, the device comprising: a memory configured to store the video data; and one or more processors implemented using circuits coupled to the memory, configured to: receive a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component; in the defined filtering mode, apply an instance of the NN model to a first block of the first color component to generate a first filtered block; and store the first filtered block for a decoding unit (CU).

[0009] In one example, the present disclosure describes a computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to: receive a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component; in the defined filtering mode, apply an instance of the NN model to a first block of the first color component to generate a first filtered block; and store the first filtered block for a decoding unit (CU).

[0010] The details of one or more examples are set forth in the accompanying drawings and the description below. Other features, objects, and advantages will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a block diagram illustrating an example video encoding and decoding system that may perform the techniques of this disclosure.

[0012] Figure 2 is a block diagram illustrating an example video encoder that may perform the techniques of this disclosure.

[0013] Figure 3 is a block diagram illustrating an example video decoder that may perform the techniques of this disclosure.

[0014] Figure 4 is a flow chart illustrating an example method for encoding a current block, according to the techniques of this disclosure.

[0015] Figure 5 is a flow chart illustrating an example method for decoding a current block, according to the techniques of this disclosure.

[0016] Figure 6 is shown similar to Figure 2 Flowchart of an example of a hybrid video coding framework.

[0017] Figure 7 is a conceptual diagram illustrating an example of a hierarchical prediction structure having a group of pictures (GOP) size equal to 16.

[0018] Figure 8 is a conceptual diagram illustrating an example of a convolutional neural network (CNN).

[0019] Fig. 9 is a flow chart illustrating an example method of processing video data according to the techniques of this disclosure.

[0020] Specific implementation method

[0021] The video decoding technique includes filtering to reduce decoding artifacts. In some examples, the filtering technique can be a machine learning based filtering technique. For example, a neural network can be used to perform the machine learning technique. For example, in a neural network (NN) based filtering, the reconstructed samples are input, and the intermediate outputs are residual samples, which are added back to the input to refine the input samples.

[0022] Video data may include multiple color components, such as red, green, and blue (RGB) or luminance and two chrominance components (YCbCr), etc. In some cases, there may be a different NN-based filter for each color component. However, having a different NN-based filter for each color component may be computationally and processing time intensive.

[0023] In some cases, it may be possible to use a single neural network model with different NN model modes. That is, in these cases, a first filtering mode for the NN model is used to filter the first color component, and a second filtering mode for the NN model is used to filter the second color component. The video encoder and / or video decoder may select different modes for each of the two chroma components, which may require performing filtering twice on the decoder side. For example, in such an example, the video encoder and video decoder may execute the NN model in a first filtering mode to filter a first block of the first color component, and then execute the NN model a second time in a second filtering mode to filter a second block of the second color component. This dual execution of the NN model for filtering is computationally intensive.

[0024] According to one or more examples described in the present disclosure, due to similarities between different color components (e.g., similarities between two chroma components), a video encoder and a video decoder may utilize a filtering control mechanism to enable two or more color components (e.g., which become chroma components) to share the same neural network mode selection. For example, a video encoder and a video decoder may apply an instance of an NN model to a first block of a first color component under a specified filtering mode, and apply the same instance of the NN model to a second block of a second color component under a specified filtering mode. In addition to chroma components (e.g., a first color component and a second color component), the input of the NN model may be a luminance component, but the output of the NN model may be a filtered chroma component, but not a filtered luminance component (although a filtered luminance component may be output in some examples).

[0025] To ensure that the NN model is applied to both the first block of the first color component and the second block of the second color component using the same filtering mode (e.g., when NN model filtering is enabled for both color components), the video encoder may signal a syntax element defining the filtering mode of the NN model for both the first color component and the second color component, and the video decoder may receive the syntax element. In this example, the video decoder may set the filtering mode for both the first color component and the second color component to be the same filtering mode.

[0026] In this way, a video encoder and a video decoder can use one execution instance of the NN model to generate a filter block. Using the example techniques described in the present disclosure, the computational complexity can be reduced and the rate-distortion performance can be not reduced compared to techniques in which different chroma components may use different neural network models.

[0027] Figure 1 1 is a block diagram illustrating an example video encoding and decoding system 100 that can perform the techniques of the present disclosure. The techniques of the present disclosure are generally directed to decoding (encoding and / or decoding) video data. Generally, video data includes any data used to process video. Thus, video data can include original, unencoded video, encoded video, decoded (e.g., reconstructed) video, and video metadata (such as signaling data).

[0028] like Figure 1 As shown in , in this example, system 100 includes source device 102, which provides encoded video data to be decoded and displayed by destination device 116. Specifically, source device 102 provides video data to destination device 116 via computer-readable medium 110. Source device 102 and destination device 116 may include any of a wide range of devices, including desktop computers, notebook (e.g., laptop) computers, mobile devices, tablet computers, set-top boxes, telephone handsets (e.g., smart phones), televisions, cameras, display devices, digital media players, video game consoles, video streaming devices, broadcast receiver devices, etc. In some cases, source device 102 and destination device 116 may be equipped for wireless communication and may therefore be referred to as wireless communication devices.

[0029] exist Figure 1 In the example of , source device 102 includes video source 104, memory 106, video encoder 200 and output interface 108. Destination device 116 includes input interface 122, video decoder 300, memory 120 and display device 118. According to the present disclosure, the video encoder 200 of source device 102 and the video decoder 300 of destination device 116 can be configured to apply the following technology: a filtering process based on machine learning (e.g., neural network) for multiple color components in video decoding. Therefore, source device 102 represents an example of a video encoding device, and destination device 116 represents an example of a video decoding device. In other examples, source device and destination device may include other components or arrangements. For example, source device 102 may receive video data from an external video source such as an external camera. Similarly, destination device 116 may be docked with an external display device instead of including an integrated display device.

[0030] like Figure 1The system 100 shown in is only one example. In general, any digital video encoding and / or decoding device can perform the following techniques: a filtering process based on machine learning (e.g., a neural network) for multiple color components in video decoding. The source device 102 and the destination device 116 are only examples of such decoding devices, wherein the source device 102 generates encoded video data for transmission to the destination device 116. The present disclosure refers to a "decoding" device as a device that performs decoding (encoding and / or decoding) of data. Therefore, the video encoder 200 and the video decoder 300 represent examples of decoding devices (specifically, video encoders and video decoders), respectively. In some examples, the source device 102 and the destination device 116 can operate in a substantially symmetrical manner, so that each of the source device 102 and the destination device 116 includes a video encoding and decoding component. Therefore, the system 100 can support one-way or two-way video transmission between the source device 102 and the destination device 116, for example, for video streaming, video playback, video broadcasting, or video telephony.

[0031] Typically, the video source 104 represents a source of video data (i.e., original, unencoded video data) and provides a continuous sequence of pictures (also referred to as "frames") of the video data to the video encoder 200, wherein the video encoder 200 encodes the data for the pictures. The video source 104 of the source device 102 may include a video capture device (such as a camera), a video archive containing previously captured original video, and / or a video feed interface for receiving video from a video content provider. As a further alternative, the video source 104 may generate computer graphics-based data as a source video, or a combination of real-time video, archived video, and computer-generated video. In each case, the video encoder 200 encodes captured, pre-captured, or computer-generated video data. The video encoder 200 may rearrange the pictures from the received order (sometimes referred to as "display order") to a decoding order for decoding. The video encoder 200 may generate a bitstream comprising encoded video data. Source device 102 may then output the encoded video data onto computer-readable medium 110 via output interface 108 for receipt and / or retrieval by, for example, input interface 122 of destination device 116 .

[0032] The memory 106 of the source device 102 and the memory 120 of the destination device 116 represent general purpose memories. In some examples, the memories 106, 120 can store original video data, for example, original video from the video source 104 and original decoded video data from the video decoder 300. Additionally or alternatively, the memories 106, 120 can store software instructions executable by, for example, the video encoder 200 and the video decoder 300, respectively. Although the memory 106 and the memory 120 are shown separately from the video encoder 200 and the video decoder 300 in this example, it should be understood that the video encoder 200 and the video decoder 300 can also include internal memory to achieve functionally similar or equivalent purposes. In addition, the memories 106, 120 can store encoded video data (e.g., output from the video encoder 200 and input to the video decoder 300). In some examples, a portion of the memories 106, 120 can be allocated as one or more video buffers, for example, for storing original, decoded and / or encoded video data.

[0033] The computer-readable medium 110 may represent any type of medium or device capable of transmitting the encoded video data from the source device 102 to the destination device 116. In one example, the computer-readable medium 110 represents a communication medium for enabling the source device 102 to send the encoded video data directly to the destination device 116 in real time, for example, via a radio frequency network or a computer-based network. The output interface 108 may modulate the transmission signal including the encoded video data, and the input interface 122 may demodulate the received transmission signal according to a communication standard such as a wireless communication protocol. The communication medium may include any wireless or wired communication medium, such as a radio frequency (RF) spectrum or one or more physical transmission lines. The communication medium may form part of a packet-based network such as a local area network, a wide area network, or a global network (e.g., the Internet). The communication medium may include a router, a switch, a base station, or any other device that facilitates communication from the source device 102 to the destination device 116.

[0034] In some examples, source device 102 may output the encoded data from output interface 108 to storage device 112. Similarly, destination device 116 may access the encoded data from storage device 112 via input interface 122. Storage device 112 may include any of a variety of distributed or locally accessed data storage media (such as a hard drive, Blu-ray disc, DVD, CD-ROM, flash memory, volatile or non-volatile memory), or any other suitable digital storage media for storing encoded video data.

[0035] In some examples, source device 102 may output the encoded video data to file server 114 or another intermediate storage device that may store the encoded video data generated by source device 102. Destination device 116 may access the stored video data from file server 114 via streaming or downloading.

[0036] The file server 114 may be any type of server device capable of storing encoded video data and sending the encoded video data to the destination device 116. The file server 114 may represent a network server (e.g., for a website), a server configured to provide a file transfer protocol service (such as a file transfer protocol (FTP) or a unidirectional file transfer (FLUTE) protocol), a content delivery network (CDN) device, a hypertext transfer protocol (HTTP) server, a multimedia broadcast multicast service (MBMS) or an enhanced MBMS (eMBMS) server, and / or a network attached storage (NAS) device. The file server 114 may additionally or alternatively implement one or more HTTP streaming protocols, such as Dynamic Adaptive Streaming over HTTP (DASH), HTTP Real-Time Streaming (HLS), Real-Time Streaming Protocol (RTSP), HTTP Dynamic Streaming, and the like.

[0037] Destination device 116 may access the encoded video data from file server 114 through any standard data connection, including an Internet connection. This may include a wireless channel (e.g., a Wi-Fi connection), a wired connection (e.g., a digital subscriber line (DSL), a cable modem, etc.), or a combination of both, suitable for accessing encoded video data already stored on file server 114. Input interface 122 may be configured to operate according to any one or more of the various protocols discussed above for retrieving or receiving media data from file server 114, or other such protocols for retrieving media data.

[0038] Output interface 108 and input interface 122 may represent wireless transmitters / receivers, modems, wired network components (e.g., Ethernet cards), wireless communication components that operate according to any of the various IEEE 802.11 standards, or other physical components. In examples where output interface 108 and input interface 122 include wireless components, output interface 108 and input interface 122 may be configured to transmit data, such as encoded video data, according to a cellular communication standard such as 4G, 4G-LTE (Long Term Evolution), Advanced LTE, 5G, etc. In some examples where output interface 108 includes a wireless transmitter, output interface 108 and input interface 122 may be configured to transmit data, such as encoded video data, according to other wireless standards such as IEEE 802.11 specifications, IEEE 802.15 specifications (e.g., ZigBeeTM ), Bluetooth TM Standards, etc.) to transmit data such as encoded video data. In some examples, source device 102 and / or destination device 116 may include respective system-on-chip (SoC) devices. For example, source device 102 may include an SoC device to perform functions attributed to video encoder 200 and / or output interface 108, and destination device 116 may include an SoC device to perform functions attributed to video decoder 300 and / or input interface 122.

[0039] The technology of the present disclosure can be applied to video encoding to support any of a variety of multimedia applications, such as over-the-air television broadcasting, cable television transmission, satellite television transmission, Internet streaming video transmission (e.g., Dynamic Adaptive Streaming over HTTP (DASH), digital video encoded on a data storage medium), decoding of digital video stored on a data storage medium, or other applications.

[0040] The input interface 122 of the destination device 116 receives the encoded video bitstream from the computer-readable medium 110 (e.g., a communication medium, a storage device 112, a file server 114, etc.). The encoded video bitstream may include signaling information defined by the video encoder 200 and also used by the video decoder 300, such as syntax elements with values ​​describing characteristics and processing of video blocks or other decoding units (e.g., slices, pictures, groups of pictures, sequences, etc.). The display device 118 displays decoded pictures of the decoded video data to a user. The display device 118 may represent any of a variety of display devices, such as a liquid crystal display (LCD), a plasma display, an organic light emitting diode (OLED) display, or another type of display device.

[0041] Although not in Figure 1 , but in some examples, the video encoder 200 and the video decoder 300 may be integrated with an audio encoder and / or an audio decoder, respectively, and may include appropriate MUX-DEMUX units or other hardware and / or software to process a multiplexed stream including both audio and video in a common data stream.

[0042] The video encoder 200 and the video decoder 300 can each be implemented as any of a variety of suitable encoder and / or decoder circuits, such as one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), discrete logic, software, hardware, firmware, or any combination thereof. When these techniques are implemented in part in software, the device can store instructions for the software in an appropriate non-transitory computer-readable medium and use one or more processors to execute these instructions in hardware to perform the techniques of the present disclosure. Each of the video encoder 200 and the video decoder 300 can be included in one or more encoders or decoders, any of which can be integrated as part of a combined encoder / decoder (CODEC) in the corresponding device. The device including the video encoder 200 and / or the video decoder 300 can include an integrated circuit, a microprocessor, and / or a wireless communication device (such as a cellular phone).

[0043] The video encoder 200 and the video decoder 300 may operate according to a video coding standard such as ITU-T H.265 (also known as High Efficiency Video Coding (HEVC)) or its extensions (such as multi-view and / or scalable video coding extensions). Alternatively, the video encoder 200 and the video decoder 300 may operate according to other proprietary or industry standards such as ITU-T H.266 (also known as Versatile Video Coding (VVC)). In other examples, the video encoder 200 and the video decoder 300 may operate according to a proprietary video codec / format such as AOMedia Video1 (AV1), an extension of AV1, and / or a subsequent version of AV1 (e.g., AV2). In other examples, the video encoder 200 and the video decoder 300 may operate according to other proprietary formats or industry standards. However, the technology of the present disclosure is not limited to any particular decoding standard or format. In general, the video encoder 200 and the video decoder 300 may be configured to perform the technology of the present disclosure in combination with any video decoding technology using filtering (e.g., video data filtering based on machine learning (e.g., neural network)).

[0044] Typically, the video encoder 200 and the video decoder 300 can perform block-based decoding of the picture. The term "block" generally refers to a structure that includes data to be processed (e.g., encoded, decoded, or other forms used in the encoding and / or decoding process). For example, a block may include a two-dimensional matrix of samples of luminance and / or chrominance data. Typically, the video encoder 200 and the video decoder 300 can decode video data represented in a YUV (e.g., Y, Cb, Cr) format. That is, instead of decoding red, green, and blue (RGB) data of samples of a picture, the video encoder 200 and the video decoder 300 can decode luminance and chrominance components, where the chrominance components may include both red and blue chrominance components. In some examples, the video encoder 200 converts the received RGB format data into a YUV representation before encoding, and the video decoder 300 converts the YUV representation into an RGB format. Alternatively, pre-processing and post-processing units (not shown) can perform these conversions.

[0045] The present disclosure may generally relate to the decoding (e.g., encoding and decoding) of a picture to include the process of encoding or decoding data of a picture. Similarly, the present disclosure may relate to the decoding of blocks of a picture to include the process of encoding or decoding data of these blocks (e.g., prediction and / or residual decoding). A coded video bitstream generally includes a series of values ​​for syntax elements that represent decoding decisions (e.g., decoding modes) and the division of a picture into blocks. Therefore, references to decoding a picture or a block should generally be understood as the decoded values ​​of the syntax elements used to form the picture or block.

[0046] HEVC defines various blocks, including coding units (CUs), prediction units (PUs), and transform units (TUs). According to HEVC, a video decoder (such as the video encoder 200) divides a coding tree unit (CTU) into CUs according to a quadtree structure. That is, the video decoder divides the CTU and CU into four equal, non-overlapping squares, and each node of the quadtree has zero or four child nodes. A node without child nodes may be referred to as a "leaf node", and the CU of such a leaf node may include one or more PUs and / or one or more TUs. The video decoder may further partition the PU and TU. For example, in HEVC, a residual quadtree (RQT) represents the partitioning of a TU. In HEVC, a PU represents inter-frame prediction data, and a TU represents residual data. An intra-predicted CU includes intra-frame prediction information (such as an intra-frame mode indication).

[0047] As another example, the video encoder 200 and the video decoder 300 may be configured to operate according to VVC. According to VVC, a video decoder (such as the video encoder 200) divides a picture into a plurality of coding tree units (CTUs). The video encoder 200 may divide the CTU according to a tree structure such as a quadtree-binary tree (QTBT) structure or a multi-type tree (MTT) structure. The QTBT structure eliminates the concept of multiple partition types, such as the separation between CU, PU, ​​and TU of HEVC. The QTBT structure includes two levels: a first level divided according to quadtree partitioning, and a second level divided according to binary tree partitioning. The root node of the QTBT structure corresponds to the CTU. The leaf nodes of the binary tree correspond to the coding units (CUs).

[0048] In the MTT partition structure, blocks can be partitioned using quadtree (QT) partitioning, binary tree (BT) partitioning, and one or more types of ternary tree (TT) (also called ternary tree type (TT)) partitioning. A ternary tree or ternary tree type partitioning is a partitioning of a block into three sub-blocks. In some examples, a ternary tree or ternary tree type partitioning divides a block into three sub-blocks without dividing the original block through the center. The partitioning types in MTT (e.g., QT, BT, and TT) can be symmetric or asymmetric.

[0049] When operating according to the AV1 codec, the video encoder 200 and the video decoder 300 can be configured to decode the video data in the form of blocks. In AV1, the largest decoding block that can be processed is called a super block. In AV1, a super block can be 128x128 luminance samples or 64x64 luminance samples. However, in subsequent video decoding formats (e.g., AV2), super blocks can be defined by different (e.g., larger) luminance sample sizes. In some examples, the super block is the top layer of the block quadtree. The video encoder 200 can further divide the super block into smaller decoding blocks. The video encoder 200 can use square or non-square partitioning to divide the super block and other decoding blocks into smaller blocks. Non-square blocks can include N / 2xN, NxN / 2, N / 4xN and NxN / 4 blocks. The video encoder 200 and the video decoder 300 can perform separate prediction and transformation processes for each decoding block.

[0050] AV1 also defines tiles of video data. A tile is a rectangular array of superblocks that can be decoded independently of other tiles. That is, the video encoder 200 and the video decoder 300 can encode and decode the decoded blocks within the tile, respectively, without using video data from other tiles. However, the video encoder 200 and the video decoder 300 can perform filtering across tile boundaries. The size of the tile can be uniform or non-uniform. Tile-based decoding can implement parallel processing and / or multi-threading for encoder and decoder implementations.

[0051] In some examples, the video encoder 200 and the video decoder 300 may use a single QTBT or MTT structure to represent each of the luma and chroma components, while in other examples, the video encoder 200 and the video decoder 300 may use two or more QTBT or MTT structures, such as one QTBT / MTT structure for the luma component and another QTBT / MTT structure for the two chroma components (or two QTBT / MTT structures for corresponding chroma components).

[0052] The video encoder 200 and the video decoder 300 may be configured to use quadtree partitioning, QTBT partitioning, MTT partitioning, super-block partitioning, or other partitioning structures.

[0053] In some examples, a CTU includes a coding tree block (CTB) of luma samples, two corresponding CTBs of chroma samples of a picture having three sample arrays, or a CTB of samples of a monochrome picture or a picture coded using three independent color planes and syntax structures for coding the samples. A CTB can be an NxN block of samples for some value of N, such that the partitioning of a component into a CTB is a partition. A component is an array or a single sample from one of the three arrays (luminance and two chroma) that make up a picture of 4:2:0, 4:2:2, or 4:4:4 color format, or an array or a single sample from an array that makes up a picture of monochrome format. In some examples, a coding block is an MxN block of samples for some values ​​of M and N, such that the partitioning of a CTB into a coding block is a partition.

[0054] Blocks (e.g., CTUs or CUs) may be grouped in a picture in various ways. As an example, a brick may refer to a rectangular area with a CTU row within a particular tile in a picture. A tile may be a rectangular area with a CTU within a particular tile column and a particular tile row in a picture. A tile column refers to a CTU with a height equal to the height of the picture and a width specified by a syntax element (e.g., such as in a picture parameter set). A tile row refers to a CTU with a height specified by a syntax element (e.g., such as in a picture parameter set) and a width equal to the width of the picture.

[0055] In some examples, a tile can be divided into multiple bricks, each of which can include one or more CTU rows within the tile. Tiles that are not divided into multiple bricks can also be called bricks. However, bricks that are true subsets of tiles cannot be called tiles. Bricks in a picture can also be arranged in slices. A slice can be an integer number of bricks in a picture that can be exclusively contained in a single network abstraction layer (NAL) unit. In some examples, a slice includes multiple complete tiles, or only a continuous sequence of complete bricks of a tile.

[0056] The present disclosure may use "NxN" and "N by N" interchangeably to refer to the sample size of a block (such as a CU or other video block) in terms of vertical and horizontal dimensions, e.g., 16x16 samples or 16 by 16 samples. Typically, a 16x16 CU will have 16 samples in the vertical direction (y=16) and 16 samples in the horizontal direction (x=16). Likewise, an NxN CU typically has N samples in the vertical direction and N samples in the horizontal direction, where N represents a non-negative integer value. The samples in a CU may be arranged in rows and columns. Furthermore, a CU does not necessarily have the same number of samples in the horizontal direction as in the vertical direction. For example, a CU may include NxM samples, where M is not necessarily equal to N.

[0057] The video encoder 200 encodes video data for a CU representing prediction and / or residual information and other information. The prediction information indicates how the CU will be predicted in order to form a prediction block for the CU. The residual information typically represents the sample-by-sample difference between the samples of the CU before encoding and the prediction block.

[0058] In order to predict a CU, the video encoder 200 can generally form a prediction block for the CU by inter-frame prediction or intra-frame prediction. Inter-frame prediction generally refers to predicting a CU from data of a previously decoded picture, while intra-frame prediction generally refers to predicting a CU from previously decoded data of the same picture. In order to perform inter-frame prediction, the video encoder 200 can use one or more motion vectors to generate a prediction block. The video encoder 200 can generally perform a motion search to identify a reference block that closely matches the CU, for example, from the perspective of the difference between the CU and the reference block. The video encoder 200 can use the sum of absolute differences (SAD), the sum of squared differences (SSD), the mean absolute difference (MAD), the mean square difference (MSD), or other such difference calculations to calculate a difference metric to determine whether the reference block closely matches the current CU. In some examples, the video encoder 200 can use unidirectional prediction or bidirectional prediction to predict the current CU.

[0059] Some examples of VVC also provide an affine motion compensation mode, which can be considered an inter-prediction mode. In the affine motion compensation mode, the video encoder 200 can determine two or more motion vectors representing non-translational motion, such as reduction or enlargement, rotation, perspective motion, or other irregular motion types.

[0060] To perform intra prediction, the video encoder 200 can select an intra prediction mode to generate a prediction block. Some examples of VVC provide 67 intra prediction modes, including various directional modes as well as planar and DC modes. Typically, the video encoder 200 selects an intra prediction mode that describes the neighboring samples relative to the current block (e.g., the block of the CU) and predicts the samples of the current block from the neighboring samples. Assuming that the video encoder 200 decodes the CTU and CU in a raster scan order (from left to right, from top to bottom), these samples can typically be above, above left, or to the left of the current block in the same picture as the current block.

[0061] The video encoder 200 encodes data representing a prediction mode for the current block. For example, for an inter-frame prediction mode, the video encoder 200 may encode data representing which of various available inter-frame prediction modes to use, and motion information for the corresponding mode. For unidirectional or bidirectional inter-frame prediction, for example, the video encoder 200 may encode motion vectors using advanced motion vector prediction (AMVP) or merge mode. The video encoder 200 may use a similar mode to encode motion vectors for affine motion compensation mode.

[0062] AV1 includes two general techniques for encoding and decoding coded blocks of video data. The two general techniques are intra-frame prediction (e.g., intra-frame prediction or spatial prediction) and inter-frame prediction (e.g., inter-frame prediction or temporal prediction). In the context of AV1, when an intra-frame prediction mode is used to predict a block of a current frame of video data, the video encoder 200 and the video decoder 300 do not use video data from other frames of the video data. For most intra-frame prediction modes, the video encoder 200 encodes a block of the current frame based on the difference between the sample values ​​in the current block and the prediction values ​​generated based on the reference samples in the same frame. The video encoder 200 determines the prediction values ​​generated based on the reference samples based on the intra-frame prediction mode.

[0063] After a prediction such as intra prediction or inter prediction of a block, the video encoder 200 may calculate residual data for the block. The residual data (such as a residual block) represents the sample-by-sample difference between the block and the prediction block for the block formed using the corresponding prediction mode. The video encoder 200 may apply one or more transforms to the residual block to produce transformed data in a transform domain rather than a sample domain. For example, the video encoder 200 may apply a discrete cosine transform (DCT), an integer transform, a wavelet transform, or a conceptually similar transform to the residual video data. Additionally, the video encoder 200 may apply a secondary transform after the first transform, such as a mode-dependent non-separable secondary transform (MDNSST), a signal-dependent transform, a Karhunen-Loeve transform (KLT), and the like. After applying the one or more transforms, the video encoder 200 generates transform coefficients.

[0064] As described above, after performing any transforms to produce transform coefficients, the video encoder 200 can perform quantization of the transform coefficients. Quantization generally refers to the process of quantizing the transform coefficients to possibly reduce the amount of data used to represent the transform coefficients, thereby providing further compression. By performing the quantization process, the video encoder 200 can reduce the bit depth associated with some or all of these transform coefficients. For example, the video encoder 200 can round an n-bit value to an m-bit value during quantization, where n is greater than m. In some examples, to perform quantization, the video encoder 200 can perform a bitwise right shift of the value to be quantized.

[0065] After quantization, the video encoder 200 can scan the transform coefficients to generate a one-dimensional vector according to a two-dimensional matrix including the quantized transform coefficients. The scan can be designed to place the transform coefficients of higher energy (and therefore lower frequency) in front of the vector and the transform coefficients of lower energy (and therefore higher frequency) in the back of the vector. In some examples, the video encoder 200 can scan the quantized transform coefficients using a predefined scan order to generate a serialized vector, and then entropy encode the quantized transform coefficients of the vector. In other examples, the video encoder 200 can perform adaptive scanning. After scanning the quantized transform coefficients to form a one-dimensional vector, the video encoder 200 can entropy encode the one-dimensional vector, for example, according to context adaptive binary arithmetic coding (CABAC). The video encoder 200 can also entropy encode the values ​​of syntax elements, which describe metadata associated with the encoded video data for use by the video decoder 300 when decoding the video data.

[0066] To perform CABAC, the video encoder 200 may assign context within a context model to a symbol to be transmitted. For example, the context may relate to whether the neighboring values ​​of the symbol are zero values. The probability determination may be based on the context assigned to the symbol.

[0067] The video encoder 200 may also generate syntax data (such as block-based syntax data, picture-based syntax data, and sequence-based syntax data) for the video decoder 300 in, for example, a picture header, a block header, a slice header, or other syntax data (such as a sequence parameter set (SPS), a picture parameter set (PPS), or a video parameter set (VPS). The video decoder 300 may similarly decode such syntax data to determine how to decode the corresponding video data.

[0068] In this way, the video encoder 200 can generate a bitstream including the encoded video data, for example, a syntax element for describing the division of a picture into blocks (e.g., CUs), and a syntax element for prediction and / or residual information of the blocks. Finally, the video decoder 300 can receive the bitstream and decode the encoded video data.

[0069] In general, the video decoder 300 performs a process that is reciprocal to the process performed by the video encoder 200 to decode the encoded video data of the bitstream. For example, the video decoder 300 may decode the values ​​of the syntax elements of the bitstream using CABAC in a manner substantially similar to the CABAC encoding process of the video encoder 200 (although reciprocal). The syntax elements may define partitioning information for partitioning a picture into CTUs, and partitioning each CTU according to a corresponding partitioning structure (such as a QTBT structure) to define CUs of the CTU. The syntax elements may further specify prediction and residual information for a block (e.g., CU) of video data.

[0070] The residual information may be represented by, for example, quantized transform coefficients. The video decoder 300 may inverse quantize and inverse transform the quantized transform coefficients of the block to reproduce a residual block for the block. The video decoder 300 uses the signaled prediction mode (intra-frame or inter-frame prediction) and related prediction information (e.g., motion information for inter-frame prediction) to form a prediction block for the block. The video decoder 300 may then combine the prediction block and the residual block (on a sample-by-sample basis) to reproduce the original block. The video decoder 300 may perform other processing, such as performing a deblocking process to reduce visual artifacts along the boundaries of the blocks.

[0071] The present disclosure generally relates to "signaling" certain information (such as syntax elements). The term "signaling" may generally refer to transmitting values ​​for syntax elements and / or other data used to decode encoded video data. That is, the video encoder 200 may signal values ​​for syntax elements in a bitstream. Generally, signaling refers to generating values ​​in a bitstream. As described above, the source device 102 may transmit the bitstream to the destination device 116 in substantially real time or in non-real time, such as may occur when storing syntax elements to the storage device 112 for later retrieval by the destination device 116.

[0072] As mentioned above, video coding standards include ITU-T H.261, ISO / IEC MPEG-1 Visual, ITU-T H.262 or ISO / IEC MPEG-2 Visual, ITU-T H.263, ISO / IEC MPEG-4 Visual and ITU-T H.264 (also known as ISO / IEC MPEG-4 AVC), High Efficiency Video Coding (HEVC) or ITU-T H.265, including its range extension, multi-view extension (MV-HEVC) and scalable extension (SHVC). Recently, the Joint Video Experts Team (JVET) of the ITU-T Video Coding Experts Group (VCEG) and the ISO / IEC Moving Picture Experts Group (MPEG) developed the latest standard, Versatile Video Coding (VVC) or ITU-T H.265. Version 1 of the VVC specification was finalized this month and is referred to as VVC FDIS below. The specification is available at http: / / phenix.int-evry.fr / jvet / doc_end_user / documents / 19_Teleconference / wg11 / JVET-S2001-v17.zip.

[0073] The video coding standard is based on the so-called hybrid video coding principle, such as Figure 6 as shown in , and similar to Figure 2 The term hybrid refers to the combination of two techniques to reduce redundancy in video signals, such as prediction and transform coding with quantization of the prediction residual. Prediction and transform reduce redundancy in video signals by decorrelation, while quantization reduces the data represented by the transform coefficients by reducing their precision, ideally by removing only irrelevant details. In the two latest standards HEVC and VVC, this hybrid video coding design principle is also used. Figure 6 As shown in and also refer to Figure 2 Described in more detail, a modern hybrid video decoder consists of various processes.

[0074] like Figure 6As shown in , a modern hybrid video coder 130 typically performs block partitioning, motion compensation or inter-picture prediction, intra-picture prediction, transform, quantization, entropy coding, and post-loop / in-loop filtering. Figure 2 In the example of , the video decoder 130 includes a summing unit 134, a transform unit 136, a quantization unit 138, an entropy decoding unit 140, an inverse quantization unit 142, an inverse transform unit 144, a summing unit 146, a loop filtering unit 148, a decoded picture buffer (DPB) 150, an intra-frame prediction unit 152, an inter-frame prediction unit 154 and a motion estimation unit 156.

[0075] Generally, the video decoder 130 may receive input video data 132 when encoding the video data. Block partitioning is used to partition the received picture (image) of the video data into smaller blocks for the operation of the prediction and transform processes. Early video coding standards used a fixed block size, which was typically 16×16 samples. Recent standards such as HEVC and VVC use a tree-based partitioning structure to provide flexible partitioning.

[0076] The motion estimation unit 156 and the inter prediction unit 154 may predict the input video data 132, for example, based on previously decoded data of the DPB 150. Motion compensation or inter-picture prediction exploits the redundancy present between pictures (hence "inter-pictures") of a video sequence. According to block-based motion compensation used in all modern video codecs, the prediction is obtained based on one or more previously decoded pictures (i.e., reference pictures). The corresponding area used to generate the inter prediction is indicated by motion information including motion vectors and reference picture indices. In recent video codecs, a hierarchical prediction structure inside a group of pictures (GOP) is applied to improve decoding efficiency. In Figure 7 An example of a GOP 700 having a size equal to 16 is shown in FIG.

[0077] The summation unit 134 may calculate the residual data as the difference between the input video data 132 and the prediction data from the intra prediction unit 152 or the inter prediction unit 154. The summation unit 134 provides the residual block to the transform unit 136, which applies one or more transforms to the residual block to generate a transform block. The quantization unit 138 quantizes the transform block to form quantized transform coefficients. The entropy decoding unit 140 entropy decodes the quantized transform coefficients and other syntax elements such as motion information or intra prediction information to generate an output bitstream 158.

[0078] At the same time, the inverse quantization unit 142 inverse quantizes the quantized transform coefficients, and the inverse transform unit 144 inverse transforms the transform coefficients to reproduce the residual block. The summation unit 146 combines the residual block with the prediction block (on a sample-by-sample basis) to generate a decoded block of video data. The loop filtering unit 148 applies one or more filters (e.g., at least one of a neural network-based filter, a neural network-based loop filter, a neural network-based post-loop filter, an adaptive loop filter, or a predefined adaptive loop filter) to the decoded block to generate a filtered decoded block.

[0079] According to the techniques of this disclosure, the neural network filter unit of loop filter unit 148 may receive data for a decoded picture of video data from summation unit 146 and from one or more other units of hybrid video coder 130 (e.g., transform unit 136, quantization unit 138, intra-prediction unit 152, inter-prediction unit 154, motion estimation unit 156, and / or one or more other filtering units within loop filter unit 148). For example, the neural network filter unit may receive data from a deblocking filter unit (also referred to as a “deblocking unit”) of loop filter unit 148.

[0080] exist Figure 6 In , intra-picture prediction exploits the spatial redundancy present within a picture by deriving a prediction of the block from already encoded / decoded spatially neighboring (reference) samples (hence "intra prediction"). In the latest video codecs (including AVC, HEVC, and VVC), angular prediction, DC prediction, and planar or planarized prediction are used.

[0081] Transform: The hybrid video coding standard applies a block transform to the prediction residual (whether it comes from inter-picture prediction or intra-picture prediction). In earlier standards including H.261 / 262 / 263, the discrete cosine transform (DCT) was used. In HEVC and VVC, in addition to the DCT, more transform kernels are applied to take into account different statistical characteristics in a specific video signal.

[0082] Quantization aims to reduce the precision of an input value or a set of input values ​​in order to reduce the amount of data needed to represent these values. In hybrid video coding, quantization is usually applied to the residual samples of each transform (i.e., transform coefficients), resulting in integer coefficient levels. In recent video coding standards, the step size is derived from the so-called quantization parameter (QP) that controls fidelity and bit rate. Larger step sizes reduce bit rate, but also reduce quality, which causes, for example, video pictures to exhibit blocking artifacts and blurred details.

[0083] Entropy Coding: Context-Adaptive Binary Arithmetic Coding (CABAC) is used in recent video codecs (eg, AVC, HEVC, and VVC) due to its high efficiency.

[0084] Post-loop / in-loop filtering is a filtering process (or combination of these processes) applied to a reconstructed picture to reduce decoding artifacts. The input to the filtering process is usually the reconstructed picture, which is a combination of the reconstructed residual signal (including quantization error) and the prediction. In other words, the input to the filtering process is the result of adding the prediction to the residual signal. Figure 6 As shown in , the reconstructed picture after in-loop filtering is stored and used as a reference for inter-picture prediction of subsequent pictures. Decoding artifacts are mainly determined by QP, so QP information is usually used in the design of the filtering process. In HEVC, in-loop filtering includes deblocking filtering and sample adaptive offset (SAO) filtering. In the VVC standard, an adaptive loop filter (ALF) is introduced as the third filter. The filtering process of ALF is shown below,

[0085] R′(i,j)=R(i,j)+((∑ k≠0 ∑ l≠0 f(k,l)×K(R(i+k,j+l)-R(i,j),c(k,l))+64)》7)(1)

[0086] Where, container R(i,j) is the sample before filtering process, R′(i,j) is the sample value after filtering process. f(k,l) represents the filter coefficient, K(x,y) is the clipping function, and c(k,l) represents the clipping parameter. Variables k and l are in and where L represents the filter length. The clipping function K(x,y)=min(y,max(-y,x)), which corresponds to the function Clip3(-y,y,x). The clipping operation introduces nonlinearity, making the ALF more efficient by reducing the impact of adjacent sample values ​​that differ too much from the current sample value. In VVC, the filtering parameters can be signaled in the bitstream and can be selected from a predefined set of filters. The ALF filtering process can also be summarized as the following equation.

[0087] R'(i,j)=R(i,j)+ALF_residual_output(R) (2)

[0088] Neural network (NN) based filtering for video decoding is described below. Embedding neural networks into a hybrid video coding framework can improve compression efficiency. Neural networks have been applied to modules such as intra-frame prediction and inter-frame prediction to improve prediction efficiency. NN-based in-loop filters are also possible. In some examples, the filtering process is applied as a post-filter, in which case the filtering process is only applied to the output picture and the unfiltered picture is used as a reference picture.

[0089] The NN-based filter can be applied in addition to existing filters such as deblocking filter, SAO and ALF. It can also be applied exclusively in the case where it is designed to replace all existing filters.

[0090] like Figure 8 As shown in , the NN-based filtering process takes reconstructed samples 800 as input, and the intermediate output is a residual sample (e.g., residual sample 802), which is added back to the input (e.g., reconstructed sample 800) to refine the input sample and generate filtered sample 804. The NN filter can use all color components as input to exploit cross-component correlation. Different components can share the same filter (including network structure and model parameters), or each component can have its own specific filter.

[0091] As an example, the NN filter can receive all color components even if a subset of color components is being filtered. For example, for brightness and chrominance components, the NN filter can receive both brightness blocks and chrominance blocks. In this example, it is assumed that the Cb chrominance block is to be filtered, while the brightness block or the Cr chrominance block is not filtered. The brightness block, the Cb chrominance block, and the Cr chrominance block are all inputs to the NN filter. In such an example, the NN filter can generate a filtered Cb chrominance block and a filtered Cr chrominance block. A filtered brightness block may not be generated, but these techniques require the generation of a filtered brightness block. However, the video encoder 200 and the video decoder 300 can discard the filtered Cr chrominance block. That is, a reconstructed coding unit (CU) including a brightness block and a chrominance block may include a reconstructed brightness sample (unfiltered), a reconstructed Cr chrominance sample (unfiltered), and a filtered reconstructed Cb chrominance sample.

[0092] The filtering process can also be summarized as follows:

[0093] R'(i,j)=R(i,j)+NN_filter_residual_output(R) (3)

[0094] The model structures and model parameters of the NN-based filters may be pre-defined and stored at the video encoder 200 and the video decoder 300. These filters may also be signaled in the bitstream.

[0095] When NN-based filtering is applied in video decoding, the entire video signal can be divided into multiple processing components, and each processing component can be processed separately. Possible choices for processing components include: frames, slices / tiles, CTUs, or any predefined or signaled shapes and sizes. That is, the term "processing component" can refer to the part of a picture or frame where processing may occur.

[0096] NN-based filtering with a multi-mode design is described below. To further improve the performance of NN-based filtering, a multi-mode solution can be designed. For example, for each processing component, the video encoder 200 can select from a set of modes based on rate-distortion optimization, and the selection can be signaled in the bitstream. Different modes can include different NN models, different values ​​of input information used as NN models, and so on. As an example, JVET-Z0113: Y. Li, K. Zhang, L. Zhang, H. Wang, M. Coban, A. M. Kotra, M. Karczewicz, F. Galpin, K. Andersson, J. D.Liu, R. EE1-1.7: Combined test of EE1-1.6 and EE1-1.3, JVET-Z0113, April 2022 (hereinafter referred to as JVET-Z0113), proposed a NN-based filtering solution that creates multiple modes based on a single NN model by using different QP values ​​as input to the NN model for different modes.

[0097] There may be certain issues with using NN-based filtering techniques. For video signals (e.g., video data) with multiple color components, the filtering process may be different for different color components. However, for some types of filtering (e.g., neural network-based filtering), applying different filters to each color component may significantly increase computational complexity and memory requirements. In these cases, a better trade-off between compression performance and complexity cost can be achieved by designing filters that can cover multiple color components and appropriately controlling how these filters are applied in the video codec.

[0098] For example, in JVET-Z0113, a NN-based filtering solution with multiple modes is proposed, which uses different QP values ​​for different modes, and the video encoder 200 and the video decoder 300 can select from different modes for processing components. In this technology of JVET-Z0113, only one model (e.g., only one neural network model) can be used for filtering the chroma component of a slice (e.g., where the slice is an example of a processing component). Different modes can be selected for the two chroma components, which requires performing two filterings on the decoder side to perform inference on the two chroma components.

[0099] In some techniques (such as those of JVET-Z0113), if a color component has a different mode of an NN filter, the video encoder 200 and the video decoder 300 will execute two instances of the NN filter in corresponding different modes. For different modes, in JVET-Z0113, the input is luma and chroma samples, but the output may be only chroma samples for the NN filter set for filtering the chroma component. That is, the NN filter mode for the chroma component may use the luma component as input, but does not use the output luma samples. For example, assume that a first NN filter mode is applied to a first color component (e.g., Cb), and a second NN filter mode is applied to a second color component (e.g., Cr).

[0100] In this example, the video encoder 200 and the video decoder 300 will apply a first instance of the NN filter in a first NN filtering mode, with inputs being luma, Cb, and Cr components (e.g., reconstructed samples of luma blocks, Cb blocks, and Cr blocks). The video encoder 200 and the video decoder 300 will ignore the filtered Cr samples and maintain the filtered Cb samples.

[0101] Next or in parallel, the video encoder 200 and the video decoder 300 will apply a second instance of the NN filter in a second NN filtering mode, with inputs being luma, Cb, and Cr components (e.g., reconstructed samples of luma blocks, Cb blocks, and Cr blocks). The video encoder 200 and the video decoder 300 will ignore the filtered Cb samples and maintain the filtered Cr samples.

[0102] In this example, the video encoder 200 and the video decoder 300 may maintain the filtered Cb samples from the first instance of the NN filter, maintain the filtered Cr samples from the second instance of the NN filter, and discard the remaining samples. Therefore, in this example, in order to generate a filtered CU including luma and chroma components, the video encoder 200 and the video decoder 300 apply two instances of the NN filter in different modes. This execution of the two instances of the NN filter in different modes may be processing intensive and delay the reconstruction of the image.

[0103] A CU is an example of a composite block including component blocks. For example, a CU includes a luminance block and a chrominance block. In the present disclosure, a CU is used as an example to generally refer to a composite block including different color components (such as luminance and chrominance components). The term CU should not be limited to a CU defined in a video coding standard or part of a video codec, unless otherwise explicitly specified.

[0104] This disclosure describes example techniques for limiting different modes for different color components. That is, the NN filtering mode for one color component is the same as the filtering mode for another color component. In this way, the video encoder 200 and the video decoder 300 can apply one instance of the NN filter in different modes instead of applying two instances of the NN filter.

[0105] In addition, the present disclosure describes example techniques that allow for selectively determining whether to utilize filtered samples from multiple color components or fewer color components (e.g., one color component). In this manner, not all filtered components need to be used, thereby allowing for situations where better coding efficiency or higher image content is generated by utilizing a subset of filtered components.

[0106] In addition, as described in more detail, the present disclosure describes example techniques for signaling different level parameters to indicate which NN filtering mode will be used. For example, a slice level syntax element can have multiple values. A first value can indicate that NN filtering is disabled for a color component. A subset of values ​​of the multiple values ​​can each correspond to a different NN filtering mode. The last value can indicate whether NN filtering is enabled or disabled, and if enabled, the NN filtering mode is indicated at a lower level (e.g., at the CTU level for all blocks of the CTU, at the CU level, etc.). In such an example, the video encoder 200 can signal additional syntax elements for one or more blocks, and the video decoder 300 can receive these additional syntax elements, indicating whether NN filtering is enabled or disabled, and if enabled, indicating the NN filtering mode.

[0107] In one or more examples described in the present disclosure, due to the similarity between the two chroma components, the filtering control mechanism can be designed so that the chroma components share the same NN mode selection to minimize computational complexity without sacrificing rate-distortion performance. That is, the present disclosure describes example techniques for filtering processes where some or all (if any) of the filtering operations are shared by multiple color components.

[0108] The following describes a first implementation of the example technology described in the present disclosure. As an implementation, for a color format having one luma component and two chroma components (e.g., a YCbCr color format), for each processing component, at most one NN-based filter is allowed to complete the filtering process of the two chroma components.

[0109] In a first example, the NN filter for the chrominance color component can be designed to be able to output two filtered chrominance components after a single filtering process. The filtering control of the two chrominance components can be performed jointly. For example, the two chrominance components have exactly the same options in how to apply the NN filter, including the on / off switch for NN filtering, how to create the input data of the NN model, and the values ​​of all input elements, so that filtered samples of the two chrominance components can be obtained after a single filtering process.

[0110] Similar to JVET-Z0113, for chroma components, there is a model for NN filtering, and multiple modes are created by using different QP values ​​in the process of creating the input to the NN model. The selection of the NN filter configuration is signaled and controlled as follows:

[0111] At the slice level (as an example of a processing component, but other examples are possible), a syntax element with a value range of [0,4] (called a "first level filter mode syntax element") is signaled for the chroma component. The meaning of the 5 syntax values ​​is listed below:

[0112] a.0: For this slice, turn off NN filtering of the chroma components.

[0113] b.1: For the chroma component of the slice, turn on NN filtering, and in the process of creating the input of the NN filter

[0114] In the example, the first QP in a predefined or signaled set is used.

[0115] c.2: For the chroma component of the slice, turn on NN filtering, and in the process of creating the input of the NN filter

[0116] In the example, a second QP from a predefined or signaled set is used.

[0117] d.3: For the chroma component of the slice, turn on NN filtering, and in the process of creating the input of the NN filter

[0118] In , a third QP from a predefined or signaled set is used.

[0119] e.4: Send additional syntax elements to control NN filtering individually for each processing component.

[0120] If mode 4 is signaled at the slice level, then for each processing component, an additional syntax element (e.g., "second level filter mode syntax element") with a value range of [0,3] for the corresponding chroma component is signaled. The meaning of the 4 syntax values ​​are listed below:

[0121] a.0: For this processing component, turn off NN filtering of the chrominance component.

[0122] b.1: For the chroma components of this processing component, NN filtering is turned on and in creating the input to the NN filter, the first QP in a predefined or signaled set is used.

[0123] c.2: For the chroma components of the processing component, NN filtering is turned on, and in the process of creating the input to the NN filter, a second QP in a predefined or signaled set is used.

[0124] d.3: For the chroma components of the processing component, NN filtering is turned on, and in the process of creating the input of the NN filter, the third QP in the predefined or signaled set is used.

[0125] For example, in the above example, the video encoder 200 may signal a syntax element (e.g., a first-level filtering mode syntax element) that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component, and the video decoder 300 may receive the syntax element. For example, in the above example, the value of the first-level syntax element is in the range of [0,4]. If the value of the first-level syntax element is 1, 2, or 3, the first-level syntax element defines a filtering mode (e.g., a NN filtering mode) of the NN model for both the first color component and the second color component. For example, a value of 1 means that the filtering mode is based on a first QP in a predefined or signaled set, a value of 2 means that the filtering mode is based on a second QP in a predefined or signaled set, and a value of 3 means that the filtering mode is based on a third QP in a predefined or signaled set.

[0126] However, if the value of the first-level filter mode syntax element is 4, the video encoder 200 may signal a syntax element (e.g., a second-level filter mode syntax element) that defines a filter mode for a neural network (NN) model for both the first color component and the second color component, and the video decoder 300 may receive the syntax element. For example, in the above example, the value of the second-level syntax element is in the range of [0,3]. If the value of the first-level syntax element is 1, 2, or 3, the second-level syntax element defines a filter mode (e.g., a NN filter mode) for the NN model for both the first color component and the second color component. For example, a value of 1 means that the filter mode is based on a first QP in a predefined or signaled set, a value of 2 means that the filter mode is based on a second QP in a predefined or signaled set, and a value of 3 means that the filter mode is based on a third QP in a predefined or signaled set.

[0127] That is, the video encoder 200 may signal a syntax element that defines a filtering mode for the NN model for both the first color component and the second color component, and the video decoder 300 may receive the syntax element. In one example, the syntax element is a first-level filtering mode syntax element. In another example, the syntax element is a second-level filtering mode syntax element. For example, the video encoder 200 may signal a first syntax element (e.g., a first-level filtering mode syntax element) that may be applied to multiple CUs (e.g., a slice of CUs), and the video decoder 300 may receive the first syntax element, wherein the first syntax element indicates that the second syntax element is parsed for a subset of CUs in the multiple CUs (e.g., the value of the first-level filtering mode syntax element is 4, so the second-level filtering mode syntax element is parsed). The CU subset includes one or more CUs having a CU being reconstructed. That is, the first-level filtering mode syntax element is applied to more CUs than the second-level filtering mode syntax element.

[0128] The video encoder 200 may signal the second syntax element based on the first syntax element indicating that the second syntax element is parsed for the CU subset, and the video decoder 300 may receive the second syntax element. That is, under the condition that the value of the first-level filtering mode syntax element is 4, the video encoder 200 may signal the second-level filtering mode syntax element for the CU subset, and the video decoder 300 may receive it.

[0129] Examples with first-level filtering mode syntax elements and second-level filtering mode syntax elements are provided for illustrative purposes only and should not be considered limiting. That is, in some examples, there may be one filtering mode syntax element that defines the filtering mode of a CU. This one filtering mode syntax element may be at the picture level (e.g., for all CUs of a picture), at the slice level (e.g., for all CUs of a slice), at the CTU level (e.g., for all CUs of a CTU), or at the CU level (e.g., block by block).

[0130] The video encoder 200 and the video decoder 300 may apply an instance of the NN model to a first block of a first color component under a defined filtering mode to generate a first filtered block. For example, the first block may be Figure 8 A portion of the reconstructed sample 800, and the first residual value may be Figure 8 The video encoder 200 and the video decoder 300 may generate a first filtered block (eg, filtered samples 804 for a first color component) based on the first block and the first residual value (eg, by summing the reconstructed samples 800 and the residual samples 802).

[0131] In one or more examples, since a syntax element (e.g., a first-level filtering mode syntax element or a second-level filtering mode syntax element) defines a filtering mode for the NN model for both the first color component and the second color component, the video encoder 200 and the video decoder 300 may apply the same instance of the NN model to the second block of the second color component in the defined filtering mode to generate a second filtered block residual value. For example, the video encoder 200 and the video decoder 300 may apply the same instance of the NN model to the second block of the second color component in the defined filtering mode to generate a second residual value. The video encoder 200 and the video decoder 300 may generate a second filtered block based on the second block and the second residual value (e.g., adding the second block to the second residual).

[0132] In the present disclosure, unless otherwise stated, applying the same instance of the NN model means that one execution of the NN model results in filtered samples for multiple color components. For example, the NN filter may receive luma samples, Cb samples, and Cr samples as input. The NN filtering mode may be defined by a syntax element (e.g., a value of 1, 2, or 3 for a first-level filtering mode syntax element or for a second-level filtering mode syntax element). The video encoder 200 and the video decoder 300 may apply an instance of the NN filter in a defined filtering mode, and the output may be a filtered Cb sample and a filtered Cr sample.

[0133] To describe that the filtered Cb samples and the filtered Cr samples are generated according to the same instance of applying the NN model, the present disclosure describes the video encoder 200 and the video decoder 300 as: (1) applying an instance of the NN model to a first block of a first color component to generate a first filtered block (e.g., based on the first block and the first residual value) in a defined filtering mode, and (2) applying the same instance of the NN model to a second block of a second color component to generate a second filtered block (e.g., based on the second block and the second residual value) in the defined filtering mode. That is, only one instance of the NN model is executed to generate a first filtered block for the first color component and a second filtered block for the second color component.

[0134] Thus, in this example, one syntax element (e.g., a first level filter mode syntax element or a second level filter mode syntax element) defines the filter mode for two chroma components. In some other techniques (e.g., Z-0133), one syntax element may define the filter mode for a first color component, while another syntax element may define the filter mode for a second color component. Using the example techniques described in this disclosure, one syntax element defines the filter mode for a NN model for multiple color components.

[0135] In the above example, the video encoder 200 and the video decoder 300 may store sample values ​​for a coding unit (CU) based on a first filtered block and a second filtered block. For example, the video encoder 200 and the video decoder 300 may store the first filtered block and the second filtered block as part of a CU in their respective buffers, so that if the CU is used for inter-frame prediction, the first filtered block and the second filtered block are used for inter-frame prediction. As another example, the video decoder 300 may store the first filtered block and the second filtered block as part of a CU in a buffer, so that when a picture including the CU is displayed, image content is generated based on the first filtered block and the second filtered block.

[0136] As described above, one syntax element defines a filtering mode of the NN model for both the first color component and the second color component (e.g., a NN filtering mode for the NN filter). In some examples, both the first filtered block for the first color component and the second filtered block for the second color component are stored for the CU. However, in some examples, both the first filtered block and the second filtered block may not be stored for the CU.

[0137] It should be noted that in some examples, the first filtered block and the second filtered block may be generated even if one of the first filtered block for the first color component or the second filtered block for the second color component is not stored for the CU. For example, assume that a filtered Cb component is required, but a filtered Cr component is not required for the CU. In this example, the NN model may receive both luminance and chrominance components and generate a filtered Cb component and a filtered Cr component. However, the video encoder 200 and the video decoder 300 may discard the filtered Cr component. In order to store values ​​for a CU, the video encoder 200 and the video decoder 300 may store the original values ​​of the filtered Cb component and the Cr component (e.g., unfiltered reconstructed samples).

[0138] Example techniques for selecting which filtered components are used to store values ​​for a CU are described below. For ease of description, the present disclosure describes a filtering control for switching the NN filter on or off. Such disclosure of the NN filter on or off may refer to examples of whether filtered color components are used. A filtered color component may still be generated, but in examples where filtering of that color component is turned off, the filtered color component is discarded.

[0139] If filtering is enabled, the above example of storing a first filtered block for a first color component and a second filtered block for a second color component for a CU is referred to as a first example technique. That is, in the first example technique, one syntax element defines a filtering mode for the NN model for both the first color component and the second color component. In addition, in the first example technique, the video encoder 200 and the video decoder 300 store the first filtered block for the first color component and the second filtered block for the second color component as values ​​for the CU. That is, the video encoder 200 and the video decoder 300 can apply the same instance of the NN model to the first block of the first color component and the second block of the second color component in the defined filtering mode to generate the first filtered block and the second filtered block, respectively.

[0140] For example, the video encoder 200 and the video decoder 300 may apply the same instance of the NN model to a first block of a first color component and a second block of a second color component under a defined filtering mode to generate a first residual value and a second result value, respectively. The video encoder 200 and the video decoder 300 may generate a first filtered block based on the first block and the first residual value (e.g., by adding them together), and generate a second filtered block based on the second block and the second residual value (e.g., by adding them together).

[0141] In the second example, similar to the first example, the NN filter for the chroma color component is designed to be able to output two chroma components after a single filtering process. The filtering control allows the on / off switching of the NN filter for the two chroma components to be signaled separately, and further, if the NN filtering for the two chroma components is turned on, the output of the two chroma components should be generated by a single filtering process. That is, both filtered chroma blocks can be the output of the NN filter, but at least one filtered chroma block can be discarded.

[0142] At the slice level (as an example of a processing component), a syntax element with a value range of [0, 4] (referred to as first_chroma_mode_slice in the following description) is signaled for the first chroma component. For the second chroma component, if first_chroma_mode_slice == 0, another syntax element with a value range of [0, 4] for the second chroma component (referred to as second_chroma_mode_slice in the following description) is signaled to indicate the selection of NN filtering for the second chroma component. In other cases (first_chroma_mode_slice != 0), a flag with a value range of [0, 1] is signaled, and if the flag is 0, second_chroma_mode_slice is set to 0, otherwise second_chroma_mode_slice is set to first_chroma_mode_slice.

[0143] The meanings of the five syntax values ​​of first_chroma_mode_slice and second_chroma_mode_slice are the same as those in the first example, except that the scope of each mode can be limited to the corresponding chroma component. That is, the values ​​of first_chroma_mode_slice and second_chroma_mode_slice can be the same as the values ​​for the first-level filtering mode syntax element or the second-level filtering mode syntax element described above. The logic for decoding / deriving first_chroma_mode_slice and second_chroma_mode_slice can be summarized as the following pseudo-code. In the pseudo-code below, the syntax elements encoded in the bitstream are given in bold, and all syntax values ​​are assumed to be 0 before the decoding / deriving logic begins.

[0144]

[0145] Similar to the first example where there is a first level filter mode syntax element and a second level filter mode syntax element, if first_chroma_mode_slice or second_chroma_mode_slice is equal to 4 (e.g., the first level filter mode syntax element has a value of 4), an additional syntax element (e.g., a second level filter mode syntax element) is signaled for selecting NN filtering for each processing component separately. The logic of decoding / deriving can be summarized in the following pseudo code. The syntax elements encoded in the bitstream are given in bold, and all syntax values ​​are assumed to be 0 before the decoding / deriving logic begins.

[0146]

[0147] In this example, the interpretation of the slice-level and processing component-level mode values ​​is the same as that for the first-level filtering mode syntax element and the second-level filtering mode syntax element above. At the slice level, 0 indicates that NN filtering is off, 1 to 3 correspond to 3 QP selections that can be used in the process of creating input information for the NN model, and 4 indicates that additional information is signaled at the processing component level (e.g., at the CTB level for all CUs of the CTB, at the CU level, etc.) to indicate the NN filtering selection for each processing component. Similarly, at the processing component level, 0 indicates that NN filtering is off, and 1 to 3 correspond to 3 QP selections that can be used in the process of creating input information for the NN model.

[0148] Thus, in one or more examples, the syntax element signaled by the video encoder 200 and received by the video decoder 300 may have a value indicating that NN-based filtering is enabled for the first color component (e.g., first_chroma_mode_slice is true). In this example, the video encoder 200 may signal a flag indicating that NN-based filtering is enabled for the second color component (e.g., second_chroma_flag_slice is true), and the video decoder 300 may receive the flag (e.g., second_chroma_flag_slice). In this example, the video encoder 200 and the video decoder 300 may generate a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in the defined filtering mode. To store values ​​for a CU, the video encoder 200 and the video decoder 300 may store values ​​for the CU based on the first filtered block and the second filtered block.

[0149] In some examples, the filtered second color component may not be used as a value for the CU. For example, the video encoder 200 may signal a flag indicating that NN-based filtering is disabled for the second color component (e.g., second_chroma_flag_slice is false), and the video decoder 300 may receive the flag (e.g., second_chroma_flag_slice). In this example, the video encoder 200 and the video decoder 300 may store a value for the CU based on a first filtered block of the first color component (e.g., a block using NN filtering) and a second block of the second color component (e.g., a block not using NN filtering).

[0150] In some examples, the first color component may not be filtered (e.g., first_chroma_mode_slice==0). In this example, the video encoder 200 may signal another syntax element indicating a filtering mode for the second color component (e.g., second_chroma_mode_slice), and the video decoder 300 may receive it. In this example, the video encoder 200 and the video decoder 300 may store a value for the CU based on a first block for the first color component (e.g., a block not filtered using NN) and a second filtering block for the second color component (e.g., a block filtered using NN).

[0151] In general, for the second example, the first_chroma_mode_slice syntax element may be considered to be a syntax element that defines a filtering mode for a neural network (NN) model for both the first color component and the second color component. For example, if the first_chroma_mode_slice syntax element is not 0, NN filtering is enabled for the first color component, and second_chroma_flag_slice indicates that filtering is enabled for the second color component, then first_chroma_mode_slice defines which filtering mode is used for both the first color component and the second color component. Even in the example where second_chroma_flag_slice is false, first_chroma_mode_slice may be considered to define a filtering mode for both the first color component and the second color component, because no additional syntax element indicating a filtering mode is required.

[0152] As a third example, the third example is the same as the second example, except that an alternative way of decoding / deriving the NN filtering selection is used. For each color component, a flag indicating the on / off selection is decoded, and if at least one of the flags indicates that NN filtering is on, an additional syntax element is signaled. Slice level (as an example of a processing component, but other examples are possible) decoding is summarized as follows. Syntax elements encoded in the bitstream are given in bold, and all syntax values ​​are assumed to be 0 before the decoding / derivation logic begins.

[0153]

[0154] In this example, first_chroma_flag_slice and second_chroma_filg_slice have range values ​​of [0,1], and chroma_mode_slice has a range of [0,3], so the value range of first_chrome_mode_stice and second_chrome_mode_slice remains the same as the value range in the second example. The interpretation of the range [0,4] and the numerical values ​​is also consistent. That is, chroma_mode_slice can be considered an example syntax element that defines the filtering mode for a neural network (NN) model for both the first color component and the second color component. The value for chroma_mode_slice can be the same as the first-level filtering mode syntax element described above.

[0155] For example, the video encoder 200 may signal a flag that enables NN-based filtering for a first color component, and the video decoder 300 may receive it. In this example, the video encoder 200 may signal first_chroma_flag_slice that enables NN-based filtering for a first color component, and the video decoder 300 may receive it. Similarly, the video encoder 200 may signal a flag that enables NN-based filtering for a second color component, and the video decoder 300 may receive it. In this example, the video encoder 200 may signal second_chroma_flag_slice that enables NN-based filtering for a second color component, and the video decoder 300 may receive it.

[0156] The video encoder 200 may signal a syntax element that defines a filtering mode for the NN model for both the first color component and the second color component based on a flag indicating that NN-based filtering is enabled for the first color component, and the video decoder 300 may receive the syntax element. For example, the video encoder 200 may signal a chroma_mode_slice syntax element based on first_chroma_flag_slice being true, and the video decoder 300 may receive the syntax element. Similarly, the video encoder 200 may signal a syntax element that defines a filtering mode for the NN model for both the first color component and the second color component based on a flag indicating that NN-based filtering is enabled for the second color component, and the video decoder 300 may receive the syntax element. For example, the video encoder 200 may signal a chroma_mode_slice syntax element based on second_chroma_flag_slice being true, and the video decoder 300 may receive the syntax element.

[0157] If NN filtering is enabled (e.g., turned on) for one or both of the first and second color components, the video decoder 300 can determine the filtering mode based on the value of chroma_mode_slice. As shown above, the equations for determining the filtering mode for both color components are the same (e.g., the filtering mode for both color components is chroma_mode_slice+1). Therefore, chroma_mode_slice defines the filtering mode for the NN model for both the first color component and the second color component.

[0158] The equivalent of this example can be created by modifying the way the syntax elements are derived and interpreted. In the following example, an example of such an equivalent design is described.

[0159] In this example, if first_chroma_mode_slice or second_chroma_mode_slice is equal to 4, additional syntax elements for NN filtering selection for each processing component, respectively, are signaled (e.g., similar to the second stage filter mode syntax elements). The logic of decoding / deriving can be summarized as pseudo code. The syntax elements encoded in the bitstream are given in bold, and all syntax values ​​are assumed to be 0 before the decoding / deriving logic begins.

[0160]

[0161] In this example, first_chroma_flag_processing_unit and second_chroma_flag_processing_unit have a range value of [0,1], and chroma_mode_processing_unit has a range value domain of [0,2], so the value range of first_chroma_mode_processing_unit and second_chroma_flag_processing_unit remains the same as the value range in the second example. The interpretation of the range [0,3] and the numerical value is also consistent. An equivalent of this example can be created by modifying the way the syntax elements are derived and interpreted. An example of such an equivalent design is described in the following example.

[0162] As a fourth example, the fourth example is equivalent to the third example, the derivation / interpretation of the syntax values ​​is different, but the actual NN control is the same. Slice level decoding can be summarized as follows. The syntax elements encoded in the bitstream are given in bold, and all syntax values ​​are assumed to be initialized to 0 before the decoding / derivation logic begins.

[0163]

[0164] In this case, the range values ​​of first_chroma_flag_slice and second_chroma_flag_slice are [0,1], and the range value of chroma_mode_slice is [0,3]. As a result, the value range of first_chroma_mode_slice and second_chroma_mode_slice becomes [0,3]. According to the following explanation, this example is equivalent to the third example:

[0165] a. If first_chroma_flag_slice == 0, NN filtering is turned off for the first chroma component.

[0166] b. If first_chroma_flag_slice == 1, then further signaling / deriving the NN filter selection is as follows:

[0168] i. If first_chroma_mode_slice == 0, then in creating the input to the NN filter, the first QP in the predefined or signaled set is used.

[0169] ii. If first_chroma_mode_slice == 1, then in creating the input to the NN filter, a second QP from a predefined or signaled set is used.

[0170] iii. If first_chroma_mode_slice == 2, then in creating the input to the NN filter, the third QP in the predefined or signaled set is used.

[0171] iv. If first_chroma_mode_slice == 4, additional syntax elements are sent to control the NN filtering for each processing component separately.

[0172] Similar to the slice level, when the NN filtering selection is signaled at the processing component level, first_chroma_mode_processing_unit and second_chroma_mode_processing_unit are assigned with chroma_mode_processing_unit when NN filtering is turned on (as shown in the pseudo code below). The syntax elements encoded in the bitstream are given in bold and all syntax values ​​are assumed to be initialized to 0 before the decoding / derivation logic begins.

[0173]

[0174] if(first_chroma_flag_processing_unit)

[0175] first_chroma_mode_processing_unit=chroma_mode_processing_unit

[0176] else

[0177] first_chroma_mode_processing_unit=0

[0178] if(second_chroma_flag_processing_unit)

[0179] second_chroma_mode_processing_unit=chroma_mode_processing_unit

[0180] else

[0181] second_chroma_mode_processing_unit=0

[0182] }

[0183] The interpretation may be the same as at the slice level, except that the mode value 4 may not be present at the processing component level:

[0184] a. If first_chroma_flag_processing_unit == 0, NN filtering is turned off for the first chroma component.

[0185] b. If first_chroma_flag_processing_unit == 1, further signal / derive NN filter selection

[0186] Select as follows:

[0187] i. If first_chroma_mode_processing_unit == 0, then in creating the input to the NN filter, the first QP in a predefined or signaled set is used.

[0188] ii. If first_chroma_mode_processing_unit == 1, then in creating the input to the NN filter, a second QP from a predefined or signaled set is used.

[0189] iii. If first_chroma_mode_processing_unit == 2, then in the process of creating the input to the NN filter, a third QP from a predefined or signaled set is used.

[0190] The first to fourth examples can be extended to any multi-mode NN filtering design, and the example techniques described in the present disclosure can still be applied. For example, in one or more examples, a syntax element defining a filtering mode for an NN model for both a first color component and a second color component defines which parameter is selected from a plurality of parameters, and the defined parameters define the filtering mode. That is, the syntax element defining the filtering mode can mean that the syntax element defines which parameter to use, and the parameter defines the filtering mode.

[0191] For example, the syntax element may have a value of 1, 2, or 3, where a value of 1 indicates that a first parameter from a predefined set or a signaled set defines a filtering mode. A value of 2 indicates that a second parameter from a predefined set or a signaled set defines a filtering mode, and a value of 3 indicates that a third parameter from a predefined set or a signaled set defines a filtering mode. In some examples, the parameter is a quantization parameter.

[0192] Here are some examples of additional parameters or collections from which to select parameters:

[0193] a. Instead select a QP value from a predefined / signaled set with size 3. This approach can be extended to the case where a candidate set of N values ​​is used.

[0194] b. Instead of using different QP values ​​for different modes, a multi-mode NN filtering method can be designed using any values ​​used in the process of creating the input of the NN filtering model.

[0195] c. Multi-mode design can use different NN models for different modes instead of using different QP values ​​for different modes.

[0196] d. The different ways of designing multi-mode filtering methods described above can be combined to create more complex multi-mode designs. For example, these techniques can be combined to create M models, and for each model, there are N QP values ​​that can be used when creating the input to the model. Then, a total of M*N models are created.

[0197] A 4-model design can be created by using two models and choosing two QPs for each model.

[0198] As a second implementation, the example techniques of the first implementation can be extended to cover more color components. For example, all examples of the first implementation can be designed so that the NN model can output all three color components (RGB, YUV, etc.), and the filtering control described in the present disclosure can be used to implement at most one NN filtering operation for all three color components.

[0199] Figure 2 is a block diagram illustrating an example video encoder 200 that may perform the techniques of this disclosure. Figure 2 For the purpose of explanation, it should not be considered as limiting the techniques widely illustrated and described in the present disclosure. For the purpose of explanation, the present disclosure describes the video encoder 200 according to VVC technology (ITU-T H.266 under development) and HEVC (ITU-T H.265) technology. However, the techniques of the present disclosure can be performed by a video encoding device configured to implement other video coding standards and video coding formats (such as AV1 and successors of the AV1 video coding format).

[0200] exist Figure 2In the example of , the video encoder 200 includes a video data memory 230, a mode selection unit 202, a residual generation unit 204, a transform processing unit 206, a quantization unit 208, an inverse quantization unit 210, an inverse transform processing unit 212, a reconstruction unit 214, a filtering unit 216, a decoded picture buffer (DPB) 218, and an entropy coding unit 220. Any one or all of the video data memory 230, the mode selection unit 202, the residual generation unit 204, the transform processing unit 206, the quantization unit 208, the inverse quantization unit 210, the inverse transform processing unit 212, the reconstruction unit 214, the filtering unit 216, the DPB 218, and the entropy coding unit 220 can be implemented in one or more processors or in a processing circuit. For example, the units of the video encoder 200 can be implemented as one or more circuits or logic elements as part of a hardware circuit, or as part of a processor, ASIC, or FPGA. In addition, the video encoder 200 may include additional or alternative processors or processing circuits to perform these functions and other functions.

[0201] The video data memory 230 may store video data to be encoded by the components of the video encoder 200. The video encoder 200 may receive video data from, for example, the video source 104 ( Figure 1 ) receives the video data stored in the video data memory 230. DPB218 can act as a reference picture memory, which stores reference video data for use when the video encoder 200 predicts subsequent video data. Video data memory 230 and DPB 218 can be formed by any one of a variety of storage devices (such as, dynamic random access memory (DRAM) (which includes synchronous DRAM (SDRAM)), magnetoresistive RAM (MRAM), resistive RAM (RRAM) or other types of storage devices). Video data memory 230 and DPB 218 can be provided by the same storage device or different storage devices. In various examples, video data memory 230 can be on the chip with other components of the video encoder 200, as shown, or off-chip relative to those components.

[0202] In the present disclosure, references to the video data memory 230 should not be interpreted as limited to memory internal to the video encoder 200 (unless specifically described as such), nor should they be interpreted as limited to memory external to the video encoder 200 (unless specifically described as such). Rather, references to the video data memory 230 should be understood as a reference memory storing video data, where the video encoder 200 receives the video data (e.g., video data for a current block to be encoded) for encoding. Figure 1 The memory 106 may also provide temporary storage for outputs from the various units of the video encoder 200 .

[0203] Shows Figure 2 The various units of the video encoder 200 are described to help understand the operations performed by the video encoder 200. These units can be implemented as fixed-function circuits, programmable circuits, or a combination thereof. Fixed-function circuits refer to circuits that provide specific functions and are pre-set on the operations that can be performed. Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functions in the operations that can be performed. For example, a programmable circuit can execute software or firmware that causes the programmable circuit to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuits can execute software instructions (e.g., for receiving parameters or outputting parameters), but the type of operation performed by the fixed-function circuit is generally immutable. In some examples, one or more of these units may be different circuit blocks (fixed function or programmable), and in some examples, the one or more units may be integrated circuits.

[0204] The video encoder 200 may include an arithmetic logic unit (ALU), an elementary function unit (EFU), a digital circuit, an analog circuit, and / or a programmable core formed by a programmable circuit. In an example where the operation of the video encoder 200 is performed using software executed by a programmable circuit, the memory 106 ( Figure 1 ) may store instructions (eg, object code) for software received and executed by the video encoder 200, or another memory (not shown) in the video encoder 200 may store such instructions.

[0205] The video data memory 230 is configured to store received video data. The video encoder 200 can retrieve the picture of the requested video data from the video data memory 230 and provide the video data to the residual generation unit 204 and the mode selection unit 202. The video data in the video data memory 230 can be the original video data to be encoded.

[0206] The mode selection unit 202 includes a motion estimation unit 222, a motion compensation unit 224, and an intra prediction unit 226. The mode selection unit 202 may include other functional units to perform video prediction according to other prediction modes. For example, the mode selection unit 202 may include a palette unit, an intra-block copy unit (which may be part of the motion estimation unit 222 and / or the motion compensation unit 224), an affine unit, a linear model (LM) unit, and the like.

[0207] The mode selection unit 202 generally coordinates multiple encoding passes to test combinations of encoding parameters and final rate-distortion values ​​for such combinations. The encoding parameters may include: CTU to CU partitioning, prediction mode for CU, transform type for residual data of CU, quantization parameter for residual data of CU, etc. The mode selection unit 202 may ultimately select a combination of encoding parameters that has a better rate-distortion value than other tested combinations.

[0208] The video encoder 200 may divide the picture retrieved from the video data memory 230 into a series of CTUs and encapsulate one or more CTUs in a fragment. The mode selection unit 202 may divide the CTUs of the picture according to a tree structure (such as the MTT structure, QTBT structure, super block structure, or quadtree structure described above). As described above, the video encoder 200 may form one or more CUs by dividing the CTUs according to the tree structure. Such CUs may also be generally referred to as "video blocks" or "blocks".

[0209] Typically, the mode selection unit 202 also controls its components (e.g., the motion estimation unit 222, the motion compensation unit 224, and the intra prediction unit 226) to generate a prediction block for the current block (e.g., the current CU, or in HEVC, the overlapping portion of the PU and TU). For inter prediction of the current block, the motion estimation unit 222 may perform a motion search to identify one or more closely matching reference blocks in one or more reference pictures (e.g., one or more previously encoded pictures stored in the DPB 218). Specifically, the motion estimation unit 222 may calculate a value indicating how similar a potential reference block is to the current block, for example, based on the sum of absolute differences (SAD), the sum of squared differences (SSD), the mean absolute difference (MAD), the mean squared difference (MSD), and the like. The motion estimation unit 222 may typically perform these calculations using the sample-by-sample difference between the current block and the reference block being considered. The motion estimation unit 222 may identify the reference block having the minimum value produced by these calculations, which indicates the reference block that most closely matches the current block.

[0210] The motion estimation unit 222 may form one or more motion vectors (MVs) that define the position of a reference block in a reference picture relative to a current block in a current picture. The motion estimation unit 222 may then provide the motion vectors to the motion compensation unit 224. For example, for unidirectional inter prediction, the motion estimation unit 222 may provide a single motion vector, and for bidirectional inter prediction, the motion estimation unit 222 may provide two motion vectors. The motion compensation unit 224 may then use the motion vectors to generate a prediction block. For example, the motion compensation unit 224 may use the motion vectors to retrieve data for the reference block. As another example, if the motion vector has fractional sampling accuracy, the motion compensation unit 224 may interpolate the values ​​for the prediction block according to one or more interpolation filters. In addition, for bidirectional inter prediction, the motion compensation unit 224 may retrieve data for two reference blocks identified by corresponding motion vectors, for example, by sample-by-sample averaging or weighted averaging, and combine the retrieved data.

[0211] When operating according to the AV1 video coding format, the motion estimation unit 222 and the motion compensation unit 224 may be configured to encode coding blocks of video data (e.g., luma and chroma coding blocks) using translational motion compensation, affine motion compensation, overlapped block motion compensation (OBMC), and / or composite intra prediction.

[0212] As another example, for intra prediction or intra prediction decoding, the intra prediction unit 226 can generate a prediction block based on samples adjacent to the current block. For example, for directional mode, the intra prediction unit 226 can generally mathematically combine the values ​​of adjacent samples and fill these calculated values ​​across the current block in a defined direction to produce a prediction block. As another example, for DC mode, the intra prediction unit 226 can calculate the average value of adjacent samples to the current block and generate a prediction block to include the resulting average value for each sample of the prediction block.

[0213] When operating according to the AV1 video coding format, the intra prediction unit 226 can be configured to encode coding blocks of video data (e.g., luma and chroma coding blocks) using directional intra prediction, non-directional intra prediction, recursive filtering intra prediction, chroma from luma (CFL) prediction, intra block copy (IBC), and / or palette mode. The mode selection unit 202 may include additional functional units to perform video prediction according to other prediction modes.

[0214] The mode selection unit 202 provides the prediction block to the residual generation unit 204. The residual generation unit 204 receives the original uncoded version of the current block from the video data memory 230 and receives the prediction block from the mode selection unit 202. The residual generation unit 204 calculates the sample-by-sample difference between the current block and the prediction block. The resulting sample-by-sample difference defines a residual block for the current block. In some examples, the residual generation unit 204 may also determine the difference between the sample values ​​in the residual block to generate the residual block using residual differential pulse code modulation (RDPCM). In some examples, the residual generation unit 204 may be formed using one or more subtractor circuits that perform binary subtraction.

[0215] In the example where the mode selection unit 202 divides the CU into PUs, each PU may be associated with a luma prediction unit and a corresponding chroma prediction unit. The video encoder 200 and the video decoder 300 may support PUs of various sizes. As described above, the size of the CU may refer to the size of the luma coding block of the CU, and the size of the PU may refer to the size of the luma prediction unit of the PU. Assuming that the size of a particular CU is 2Nx2N, the video encoder 200 may support PU sizes of 2Nx2N or NxN for intra-frame prediction, and support symmetric PU sizes of 2Nx2N, 2NxN, Nx2N, NxN, etc. for inter-frame prediction. The video encoder 200 and the video decoder 300 may also support asymmetric partitioning of PU sizes of 2NxnU, 2NxnD, nLx2N, and nRx2N for inter-frame prediction.

[0216] In an example where the mode selection unit 202 does not further divide the CU into PUs, each CU may be associated with a luma coding block and a corresponding chroma coding block. As described above, the size of a CU may refer to the size of the luma coding block of the CU. The video encoder 200 and the video decoder 300 may support a CU size of 2Nx2N, 2NxN, or Nx2N.

[0217] For other video coding techniques (such as intra block copy mode coding, affine mode coding, and linear model (LM) mode coding, to name a few examples), the mode selection unit 202 generates a prediction block for the current block being encoded via various units associated with the coding technique. In some examples (such as palette mode coding), the mode selection unit 202 may not generate a prediction block, but instead generate syntax elements that indicate how to reconstruct the block based on the selected palette. In such a mode, the mode selection unit 202 may provide these syntax elements to the entropy coding unit 220 for encoding.

[0218] As described above, the residual generation unit 204 receives video data for a current block and a corresponding prediction block. The residual generation unit 204 then generates a residual block for the current block. To generate the residual block, the residual generation unit 204 calculates the sample-by-sample difference between the prediction block and the current block.

[0219] The transform processing unit 206 applies one or more transforms to the residual block to generate a block of transform coefficients (referred to herein as a "transform coefficient block"). The transform processing unit 206 may apply various transforms to the residual block to form a transform coefficient block. For example, the transform processing unit 206 may apply a discrete cosine transform (DCT), a directional transform, a Karhunen-Loeve transform (KLT), or a conceptually similar transform to the residual block. In some examples, the transform processing unit 206 may perform multiple transforms (e.g., a primary transform and a secondary transform (e.g., a rotation transform)) on the residual block. In some examples, the transform processing unit 206 does not apply a transform to the residual block.

[0220] When operating according to AV1, the transform processing unit 206 may apply one or more transforms to the residual block to generate a transform coefficient block (referred to herein as a "transform coefficient block"). The transform processing unit 206 may apply various transforms to the residual block to form a transform coefficient block. For example, the transform processing unit 206 may apply a horizontal / vertical transform combination, which may include a discrete cosine transform (DCT), an asymmetric discrete sine transform (ADST), a flipped ADST (e.g., an inverse ADST), and an identity transform (IDTX). When an identity transform is used, a transform may be skipped in one of the vertical or horizontal directions. In some examples, the transform process may be skipped.

[0221] The quantization unit 208 may quantize the transform coefficients in the transform coefficient block to produce a quantized transform coefficient block. The quantization unit 208 may quantize the transform coefficients of the transform coefficient block according to a quantization parameter (QP) value associated with the current block. The video encoder 200 (e.g., via the mode selection unit 202) may adjust the degree of quantization applied to the transform coefficient block associated with the current block by adjusting the QP value associated with the CU. Quantization may result in a loss of information, and therefore, the precision of the quantized transform coefficients may be lower than the precision of the original transform coefficients produced by the transform processing unit 206.

[0222] The inverse quantization unit 210 and the inverse transform processing unit 212 may apply inverse quantization and inverse transform to the quantized transform coefficient block, respectively, to reconstruct a residual block from the transform coefficient block. The reconstruction unit 214 may generate a reconstructed block corresponding to the current block (although it may have a certain degree of distortion) based on the reconstructed residual block and the prediction block generated by the mode selection unit 202. For example, the reconstruction unit 214 may add samples of the reconstructed residual block to corresponding samples in the prediction block generated by the mode selection unit 202 to generate a reconstructed block.

[0223] Filtering unit 216 may perform one or more filtering operations on the reconstructed block. For example, filtering unit 216 may perform a deblocking operation to reduce blocking artifacts along the edge of the CU. In some examples, the operations of filtering unit 216 may be skipped.

[0224] According to one or more examples described in the present disclosure, the filtering unit 216 can be configured to perform a neural network-based filtering technique. For example, in addition to or in place of other filtering techniques such as ALF and SAO, the filtering unit 216 can perform a neural network-based filtering technique. For example, the filtering unit 216 can be part of a reconstruction loop that includes a decoding process performed by the video encoder 200. The filtering unit 216 can perform the neural network-based filtering described in the present disclosure as part of in-loop filtering in the reconstruction loop of the decoding process of the video encoder 200.

[0225] When operating according to AV1, filtering unit 216 may perform one or more filtering operations on the reconstructed blocks. For example, filtering unit 216 may perform a deblocking operation to reduce block artifacts along the edge of the CU. In other examples, filtering unit 216 may apply a constrained direction enhancement filter (CDEF), which may be applied after deblocking and may include applying an inseparable nonlinear low-pass directional filter based on the estimated edge direction. Filtering unit 216 may also include a loop recovery filter applied after CDEF, and may include a separable symmetric normalized Wiener filter or a dual self-guided filter.

[0226] The video encoder 200 stores the reconstructed blocks in the DPB 218. For example, in an example where the operation of the filtering unit 216 is not performed, the reconstruction unit 214 may store the reconstructed blocks in the DPB 218. In an example where the operation of the filtering unit 216 is performed, the filtering unit 216 may store the filtered reconstructed blocks in the DPB 218. The motion estimation unit 222 and the motion compensation unit 224 may retrieve a reference picture from the DPB 218, the reference picture being formed by the reconstructed (and possibly filtered) blocks, to perform inter-frame prediction on subsequently encoded pictures. In addition, the intra-frame prediction unit 226 may use the reconstructed blocks in the DPB 218 of the current picture to perform intra-frame prediction on other blocks in the current picture.

[0227] In general, the entropy coding unit 220 may entropy encode syntax elements received from other functional components of the video encoder 200. For example, the entropy coding unit 220 may entropy encode the quantized transform coefficient blocks from the quantization unit 208. As another example, the entropy coding unit 220 may entropy encode the prediction syntax elements (e.g., motion information for inter-frame prediction or intra-frame mode information for intra-frame prediction) from the mode selection unit 202. The entropy coding unit 220 may perform one or more entropy coding operations on syntax elements as another example of video data to generate entropy-encoded data. For example, the entropy coding unit 220 may perform a context-adaptive variable length coding (CAVLC) operation, a CABAC operation, a variable-to-variable (V2V) length coding operation, a syntax-based context-adaptive binary arithmetic coding (SBAC) operation, a probability interval partitioning entropy (PIPE) coding operation, an exponential Grunb coding operation, or another type of entropy coding operation on the data. In some examples, the entropy coding unit 220 may operate in a bypass mode where the syntax elements are not entropy-encoded.

[0228] The video encoder 200 may output a bitstream including entropy-encoded syntax elements required for reconstructing blocks of a slice or picture. Specifically, the entropy encoding unit 220 may output a bitstream.

[0229] According to AV1, the entropy coding unit 220 may be configured as a symbol-to-symbol adaptive multi-symbol arithmetic decoder. The syntax elements in AV1 include an alphabet of N elements, and the context (e.g., a probability model) includes a set of N probabilities. The entropy coding unit 220 may store the probabilities as an n-bit (e.g., 15-bit) cumulative distribution function (CDF). The entropy coding unit 220 may perform recursive scaling using an update factor based on the size of the alphabet to update the context.

[0230] The operations described above are described with respect to blocks. Such descriptions should be understood as operations for luma coding blocks and / or chroma coding blocks. As described above, in some examples, the luma coding blocks and chroma coding blocks are the luma and chroma components of a CU. In some examples, the luma coding blocks and chroma coding blocks are the luma and chroma components of a PU.

[0231] In some examples, operations performed for luma coding blocks do not need to be repeated for chroma coding blocks. For one example, operations for identifying a motion vector (MV) and reference picture for a luma coding block do not need to be repeated to identify an MV and reference picture for a chroma block. Instead, the MV for the luma coding block may be scaled to determine the MV for the chroma block, and the reference picture may be the same. For another example, the intra prediction process may be the same for luma coding blocks and chroma coding blocks.

[0232] The video encoder 200 represents an example of a device configured to encode video data, the device including a memory configured to store the video data, and one or more processing units implemented using circuits, the one or more processing units being configured to: filter two or more color components of the video data using an NN-based filter from a single neural network (NN) model, and output the two or more color components after a single filtering process using the NN-based filter. In some examples, filtering includes: determining how to apply the NN-based filter, whether to turn the NN-based filter on or off, how to create input data for a single NN model, and determining the values ​​of all input elements in the same manner for two or more color components.

[0233] In some examples, the video encoder 200 can be configured to: signal information indicating whether the NN-based filter is turned on or off for each of the two or more color components. In such examples, filtering includes: filtering according to whether the NN-based filter is turned on or off for each of the two or more color components.

[0234] For example, the video encoder 200 may signal a syntax element that defines a filtering mode for a neural network (NN) model for both the first color component and the second color component. Examples of syntax elements include a first level filtering mode syntax element, a second level filtering mode syntax element, first_chroma_mode_slice (e.g., where first_chroma_mode_slice is non-zero and second_chroma_flag_slice is true), and chroma_mode_slice (e.g., where first_chroma_flag_slice and / or second_chroma_flag_slice are true), as described above.

[0235] The filtering unit 216 may be configured to apply an instance of the NN model to a first block of a first color component in a defined filtering mode to generate a first filtered block. For example, the filtering unit 216 may generate a first residual sample using a reconstructed sample of a first color component (e.g., a first chroma block), and add the first residual sample to the reconstructed sample of the first color component to generate a first filtered block.

[0236] The filtering unit 216 may be configured to apply the same instance of the NN model to a second block of the second color component in a defined filtering mode to generate a second filtered block. For example, the filtering unit 216 may use the reconstructed samples of the second color component (e.g., the second chroma block) to generate a second residual sample, and add the second residual sample to the reconstructed samples of the second color component to generate a second filtered block.

[0237] In one or more examples, the filtering unit 216 may store the first filtered block and the second filtered block. For example, the sample values ​​stored in the DPB 218 by the filtering unit 216 for the CU may be the first filtered block and the second filtered block. Thus, if the CU is used for inter-frame prediction, the filtered block will be used for inter-frame prediction.

[0238] In some cases, filtering unit 216 may store the second filtered block only when filtering is enabled for the second color component. For example, filtering unit 216 may generate the first filtered block and the second filtered block for the same (e.g., single) instance of the NN model. However, sometimes the second filtered block may not be stored (e.g., discarded).

[0239] As an example, the video encoder 200 may signal the second_chroma_flag_slice flag described above as true to indicate that NN-based filtering is enabled for the second color component. In this example, the filtering unit 216 may store a value for the CU based on the first filtered block (for the first color component) and the second filtered block (for the second color component). In another example, the video encoder 200 may signal the second_chroma_flag_slice flag described above as false to indicate that NN-based filtering is disabled for the second color component. In this example, the filtering unit 216 may store a value for the CU based on the first filtered block (for the first color component) and the second block (for the second color component) without filtering. Again, the second filtered block may be generated by applying an instance of the NN model; however, when the second_chroma_flag_slice flag is false, the second filtered block may be discarded.

[0240] Figure 3 is a block diagram illustrating an example video decoder 300 that may perform the techniques of this disclosure. Figure 3 For the purpose of explanation, it should not be considered as limiting the techniques widely exemplified and described in the present disclosure. For the sake of explanation, the present disclosure describes the video decoder 300 according to VVC technology (ITU-T H.266 under development) and HEVC technology (ITU-T H.265). However, the techniques of the present disclosure can be performed by a video encoding device configured to implement other video encoding standards.

[0241] exist Figure 3 In the example of , the video decoder 300 includes a coded picture buffer (CPB) memory 320, an entropy decoding unit 302, a prediction processing unit 304, an inverse quantization unit 306, an inverse transform processing unit 308, a reconstruction unit 310, a filtering unit 312, and a decoded picture buffer (DPB) 314. Any or all of the CPB memory 320, the entropy decoding unit 302, the prediction processing unit 304, the inverse quantization unit 306, the inverse transform processing unit 308, the reconstruction unit 310, the filtering unit 312, and the DPB 314 may be implemented in one or more processors or in processing circuits. For example, the units of the video decoder 300 may be implemented as one or more circuits or logic elements as part of a hardware circuit, or as part of a processor, ASIC, or FPGA. In addition, the video decoder 300 may include additional or alternative processors or processing circuits to perform these functions and other functions.

[0242] The prediction processing unit 304 includes a motion compensation unit 316 and an intra prediction unit 318. The prediction processing unit 304 may include other units for performing predictions according to other prediction modes. For example, the prediction processing unit 304 may include a palette unit, an intra-block copy unit (which may form part of the motion compensation unit 316), an affine unit, a linear model (LM) unit, etc. In other examples, the video decoder 300 may include more, fewer, or different functional components.

[0243] When operating according to AV1, the compensation unit 316 can be configured to decode the coding blocks of the video data (e.g., luma and chroma coding blocks) using translational motion compensation, affine motion compensation, OBMC, and / or composite inter-intra prediction, as described above. The intra prediction unit 318 can be configured to decode the coding blocks of the video data (e.g., luma and chroma coding blocks) using directional intra prediction, non-directional intra prediction, recursive filtering intra prediction, CFL, intra block copy (IBC), and / or palette mode, as described above.

[0244] CPB memory 320 may store video data (such as an encoded video bitstream) to be decoded by components of video decoder 300. For example, the video bitstream may be decoded from computer readable medium 110 ( Figure 1 ) to obtain video data stored in the CPB memory 320. The CPB memory 320 may include a CPB that stores encoded video data (e.g., syntax elements) from an encoded video bitstream. Moreover, the CPB memory 320 may store video data other than syntax elements of encoded pictures, such as temporary data representing outputs from various units of the video decoder 300. The DPB 314 typically stores decoded pictures, and the video decoder 300 may output and / or use the decoded pictures as reference video data when decoding subsequent data or pictures of the encoded video bitstream. The CPB memory 320 and the DPB 314 may be formed by any of a variety of storage devices such as DRAM (including SDRAM), MRAM, RRAM, or other types of storage devices. The CPB memory 320 and the DPB 314 may be provided by the same storage device or different storage devices. In various examples, the CPB memory 320 may be on-chip with other components of the video decoder 300, or off-chip relative to those components.

[0245] Additionally or alternatively, in some examples, video decoder 300 may retrieve the video from memory 120 ( Figure 1) to retrieve the decoded video data. That is, memory 120 may store data, as discussed above with reference to CPB memory 320. Likewise, when some or all of the functionality of video decoder 300 is implemented using software executed by processing circuitry of video decoder 300, memory 120 may store instructions to be executed by video decoder 300.

[0246] Shows Figure 3 The various units are described to help understand the operations performed by the video decoder 300. These units may be implemented as fixed function circuits, programmable circuits, or a combination thereof. Figure 2 , fixed-function circuits refer to circuits that provide specific functions and are pre-set in the operations that can be performed. Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functions in the operations that can be performed. For example, a programmable circuit can execute software or firmware that causes the programmable circuit to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuits can execute software instructions (e.g., for receiving parameters or outputting parameters), but the types of operations performed by fixed-function circuits are generally immutable. In some examples, one or more of these units may be different circuit blocks (fixed-function or programmable), and in some examples, the one or more units may be integrated circuits.

[0247] The video decoder 300 may include an ALU, an EFU, a digital circuit, an analog circuit, and / or a programmable core formed by a programmable circuit. In an example where the operation of the video decoder 300 is performed by software executed on a programmable circuit, an on-chip or off-chip memory may store instructions (e.g., object code) of the software received and executed by the video decoder 300.

[0248] The entropy decoding unit 302 may receive the encoded video data from the CPB and entropy decode the video data to reproduce the syntax elements. The prediction processing unit 304, the inverse quantization unit 306, the inverse transform processing unit 308, the reconstruction unit 310, and the filtering unit 312 may generate decoded video data based on the syntax elements extracted from the bitstream.

[0249] Typically, the video decoder 300 reconstructs a picture on a block-by-block basis. The video decoder 300 may perform a reconstruction operation on each block individually (wherein a block currently being reconstructed (ie, decoded) may be referred to as a "current block").

[0250] The entropy decoding unit 302 may entropy decode syntax elements defining quantized transform coefficients of the quantized transform coefficient block, as well as transform information such as a quantization parameter (QP) and / or a transform mode indication. The inverse quantization unit 306 may use the QP associated with the quantized transform coefficient block to determine a degree of quantization, and likewise, determine a degree of inverse quantization for the inverse quantization unit 306 to apply. For example, the inverse quantization unit 306 may perform a bitwise left shift operation to inverse quantize the quantized transform coefficients. The inverse quantization unit 306 may thereby form a transform coefficient block including the transform coefficients.

[0251] After the inverse quantization unit 306 forms the transform coefficient block, the inverse transform processing unit 308 may apply one or more inverse transforms to the transform coefficient block to generate a residual block associated with the current block. For example, the inverse transform processing unit 308 may apply an inverse DCT, an inverse integer transform, an inverse Karhunen-Loeve transform (KLT), an inverse rotational transform, an inverse directional transform, or another inverse transform to the transform coefficient block.

[0252] In addition, prediction processing unit 304 generates a prediction block based on the prediction information syntax element entropy decoded by entropy decoding unit 302. For example, if the prediction information syntax element indicates that the current block is inter-predicted, motion compensation unit 316 can generate a prediction block. In this case, the prediction information syntax element can indicate a reference picture in DPB 314 from which the reference block is retrieved, and a motion vector that identifies the position of the reference block in the reference picture relative to the current block in the current picture. Motion compensation unit 316 can generally generate a prediction block in the same manner as described for motion compensation unit 224 ( Figure 2 ) to perform inter-frame prediction processing in a manner substantially similar to that described herein.

[0253] As another example, if the prediction information syntax element indicates that the current block is intra-predicted, the intra-prediction unit 318 can generate a prediction block according to the intra-prediction mode indicated by the prediction information syntax element. Again, the intra-prediction unit 318 can generally generate a prediction block in the same manner as the intra-prediction unit 226 ( Figure 2 The intra prediction unit 318 may retrieve data of neighboring samples of the current block from the DPB 314.

[0254] The reconstruction unit 310 may reconstruct the current block using the prediction block and the residual block. For example, the reconstruction unit 310 may add samples of the residual block to corresponding samples of the prediction block to reconstruct the current block.

[0255] The filtering unit 312 may perform one or more filtering operations on the reconstructed block. For example, the filtering unit 312 may perform a deblocking operation to reduce blocking artifacts along the edges of the reconstructed block. The operations of the filtering unit 312 may not necessarily be performed in all examples.

[0256] According to one or more examples described in the present disclosure, the filtering unit 312 may be configured to perform a neural network-based filtering technique. For example, in addition to or in place of other filtering techniques such as ALF and SAO, the filtering unit 312 may perform a neural network-based filtering technique. In some examples, the filtering unit 312 may perform the neural network-based filtering described in the present disclosure as part of in-loop filtering. Although not shown, in some examples, the filtering unit may be coupled to the output of the DPB 314, and the output from the filtering unit may be a decoded video. In some examples, the filtering unit coupled to the output of the DPB 314 may be configured to perform the exemplary neural network-based filtering technique described in the present disclosure as part of post-loop filtering.

[0257] The video decoder 300 may store the reconstructed block in the DPB 314. For example, in an example where the operation of the filtering unit 312 is not performed, the reconstruction unit 310 may store the reconstructed block in the DPB 314. In an example where the operation of the filtering unit 312 is performed, the filtering unit 312 may store the filtered reconstructed block in the DPB 314. As described above, the DPB 314 may provide reference information to the prediction processing unit 304, such as samples of the current picture for intra-frame prediction and previously decoded pictures for subsequent motion compensation. In addition, the video decoder 300 may output a decoded picture (e.g., a decoded video) from the DPB 314 for subsequent use in, for example, Figure 1 The display device 118 is displayed on a display device.

[0258] In this way, the video decoder 300 represents an example of a video decoding device that includes a memory configured to store video data, and one or more processing units implemented using circuits, wherein the one or more processing units are configured to: filter two or more color components of the video data using an NN-based filter from a single neural network (NN) model, and output the two or more color components after a single filtering process using the NN-based filter. In some examples, filtering includes: determining how to apply the NN-based filter, whether to turn the NN-based filter on or off, how to create input data for a single NN model, and determining the values ​​of all input elements in the same manner for two or more color components.

[0259] In some examples, the video decoder 300 can be configured to receive information indicating whether the NN-based filter is turned on or off for each of the two or more color components. In such examples, filtering includes filtering based on whether the NN-based filter is turned on or off for each of the two or more color components.

[0260] For example, the filtering unit 312 may receive a syntax element that defines a filtering mode for a neural network (NN) model for both the first color component and the second color component. Examples of syntax elements include a first level filtering mode syntax element, a second level filtering mode syntax element, first_chroma_mode_slice (e.g., where first_chroma_mode_slice is not zero and second_chroma_flag_slice is true), and chroma_mode_slice (e.g., where first_chroma_flag_slice and / or second_chroma_flag_slice are true) as described above.

[0261] In some examples, the syntax element defines which parameter is selected from a plurality of parameters, and the defined parameter specifies a filtering mode. As an example, the parameter is a quantization parameter, and the plurality of parameters is one of a predefined set or a signaled set. For example, a value of a syntax element for a first-level filtering mode is 1, indicating that the filtering mode is defined by a first parameter in a predefined set or a signaled set, a value of a syntax element for a first-level filtering mode is 2, indicating that the filtering mode is defined by a second parameter in a predefined set or a signaled set, and a value of a syntax element for a first-level filtering mode is 3, indicating that the filtering mode is defined by a third parameter in a predefined set or a signaled set. The values ​​of the second-level filtering mode syntax elements first_chroma_mode_slice and chroma_mode_stice can similarly define filtering modes, as described in the examples above.

[0262] The filtering unit 312 may apply an instance of the NN model to a first block of a first color component in a defined filtering mode to generate a first filtered block. In addition, the filtering unit 312 may apply the same instance of the NN model to a second block of a second color component in a defined filtering mode to generate a second filtered block. The filtering unit 312 may store values ​​for the CU based on the first filtered block. In the case where NN-based filtering is enabled for both the first color component and the second color component, the filtering unit 312 may store values ​​for the CU based on the first filtered block and the second filtered block. As described above, CU is used as a term to describe a composite block comprising multiple different color components.

[0263] In this manner, one syntax element defines a filtering mode for two or more color components, rather than having a syntax element define a filtering mode for each color component separately. For example, in the execution of the NN model, in the defined filtering mode, the filtering unit 312 may generate a first filtered block for a first color component and a second filtered block for a second color component. The filtering unit 312 may store a value for the CU based on the first filtering block, and if filtering is enabled for the second color component, store a value for the CU based on the first filtering block and the second filtering block.

[0264] Storing the value of the CU based on the first filtered block and / or the second filtered block may mean that the samples of the CU stored in the DPB 314 are the first filtered block and the second filtered block, or if filtering is not enabled for the second color component, the stored samples of the CU are the first filtered block and the second block (no filtering). As another example, the decoded video data output by the DPB 314 may include the first filtered block and the second filtered block (if filtering is enabled for both), or if filtering is not enabled for the second color component, the decoded video data output by the DPB 314 may include the first filtered block and the second block (no filtering).

[0265] As an example, the syntax element may be a syntax element applicable to multiple CUs. For example, the syntax element may be a first-level filtering mode syntax element defining a filtering mode for multiple CUs (e.g., CUs within a slice). As another example, the syntax element may be a second-level filtering mode syntax element defining a filtering mode for a CU subset. For example, the video decoder 300 may receive a first syntax element applicable to multiple CUs, the first syntax element indicating that a second syntax element is parsed for a CU subset in the multiple CUs (e.g., in the above example, the first-level filtering mode syntax element is 4). In this example, the CU subset includes one or more CUs whose values ​​are stored. The video decoder 300 may receive a second syntax element (e.g., a second-level filtering mode syntax element) based on a first syntax element (e.g., a first-level filtering mode syntax element) indicating that the second syntax element is parsed for a CU subset. That is, in the above example, when the value of the first-level syntax element is 4, the video decoder 300 may receive a second-level syntax element with a value between 0 and 3.

[0266] As described above, whether to use a second filtered block (e.g., generated according to NN-based filtering) can be set based on a parameter notified by a signal. For example, a syntax element defining a filtering mode for an NN model for both a first color component and a second color component received by the video decoder 300 can have a value indicating that NN-based filtering is enabled for the first color component. For example, the value of first_chroma_mode_slice can be non-zero. In this example, if a flag (e.g., second_chroma_flag_slice) indicates that NN-based filtering is enabled for the second color component, the filtering unit 312 can generate a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in the defined filtering mode.

[0267] That is, the first_chroma_mode_slice value may define a filtering mode for the NN model, and if filtering is enabled for the second color component, the value of first_chroma_mode_slice defines the filtering mode of the NN model for the second color component. Thus, in this example, the filtering unit 312 may store values ​​for the CU using the first filtered block and the second filtered block generated by applying the same instance of the NN model in the defined filtering mode.

[0268] However, in an example where second_chroma_flag_slice is false (which indicates that NN-based filtering is disabled for the second color component), filtering unit 312 may store a value for the CU based on the first filtered block and the second block of the second color component. That is, filtering unit 312 may discard the second filtered block of the second color component and instead store the first filtered block and the second block in DPB 314 (e.g., using NN filtering).

[0269] The use of second_chroma_flag_slice is one example. In some examples, such as where the syntax defining the filtering mode for two color components is chroma_mode_slice, the video decoder 300 may receive a flag indicating that NN-based filtering is enabled for the first color component (e.g., receiving first_chroma_flag_slice or second_chroma_flag_slice). In such an example, the video decoder 300 may receive a syntax element (e.g., chroma_mode_slice) based on a flag indicating that NN-based filtering is enabled for the first color component.

[0270] Figure 42 is a flowchart illustrating an example method for encoding a current block according to the techniques of the present disclosure. The current block may include a current CU. Figure 1 and Figure 2 ) is described, but it should be understood that other devices may also be configured to perform the same Figure 4 Similar approach.

[0271] In this example, the video encoder 200 initially predicts the current block (350). For example, the video encoder 200 may form a prediction block for the current block. The video encoder 200 may then calculate a residual block for the current block (352). To calculate the residual block, the video encoder 200 may calculate the difference between the original uncoded block and the prediction block of the current block. Subsequently, the video encoder 200 may transform the residual block and quantize the transform coefficients of the residual block (354). Next, the video encoder 200 may scan the quantized coefficients of the residual block (356). During or after the scan, the video encoder 200 may entropy encode the transform coefficients (358). For example, the video encoder 200 may encode the transform coefficients using CAVLC or CABAC. The video encoder 200 may then output the entropy encoded data of the block (360).

[0272] Figure 5 1 is a flowchart illustrating an example method for decoding a current block of video data according to the techniques of the present disclosure. The current block may include a current CU. Figure 1 and 3 ) is described, but it should be understood that other devices may also be configured to perform the same Figure 5 Similar approach.

[0273] The video decoder 300 may receive entropy-encoded data for a current block (e.g., entropy-encoded prediction information and entropy-encoded data for transform coefficients of a residual block corresponding to the current block) (370). The video decoder 300 may entropy decode the entropy-encoded data to determine the prediction information for the current block and reproduce the transform coefficients of the residual block (372). The video decoder 300 may predict the current block (374), for example, using an intra-frame or inter-frame prediction mode as indicated by the prediction information for the current block, to calculate a prediction block for the current block. The video decoder 300 may then inverse scan the reproduced transform coefficients (376) to create a block of quantized transform coefficients. The video decoder 300 may then inverse quantize the transform coefficients and apply an inverse transform to the transform coefficients to produce a residual block (378). The video decoder 300 may ultimately decode the current block (380) by combining the prediction block and the residual block.

[0274] In one or more examples, the video decoder 300 can also be configured to perform neural network-based filtering according to one or more examples described in the present disclosure. For example, the filtering unit 312 can be configured to perform in-loop filtering using neural network-based filtering. In some examples, the filtering unit coupled to the output of the DPB 314 can be configured to perform filtering using neural network-based filtering described in the present disclosure as part of post-loop filtering.

[0275] Although the video decoder 300 is described Figure 5 , but in some examples, the video encoder 200 also includes a reconstruction process, and the video encoder 200 (eg, via the inverse quantization unit 210, the inverse transform processing unit 212, and the reconstruction unit 214) may be configured to perform Figure 5 In some examples, filtering unit 216 can be configured to perform the neural network-based filtering techniques described in the present disclosure. For example, filtering unit 216 can perform in-loop filtering as part of a reconstruction loop of video encoder 200.

[0276] Fig. 9 is a flowchart illustrating an example method for processing video data according to the techniques of this disclosure. For ease of illustration, these examples are described with respect to video decoder 300, but video encoder 200 may perform similar operations.

[0277] The video decoder 300 may receive a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component (900). Examples of syntax elements include a first level filtering mode syntax element, a second level filtering mode syntax element, first_chroma_mode_slice (e.g., where first_chroma_mode_slice is non-zero and second_chroma_flag_slice is true), and chroma_mode_slice (e.g., where first_chroma_flag_slice and / or second_chroma_flag_slice are true) as described above. In some examples, the syntax element defines which parameter is selected from a plurality of parameters, and the defined parameter specifies the filtering mode. As an example, the parameter is a quantization parameter, and the plurality of parameters are one of a predefined set or a signaled set.

[0278] As described above, the value of the first-level filtering mode syntax element can be between 0 and 4. A value of 0 can indicate that NN-based filtering is disabled for the color component of the block within the slice (as an example). A value of 1, 2, or 3 can indicate a filtering mode for the NN model for both the first color component and the second color component (e.g., defining whether the first, second, or third QP in the set is used, and the filtering mode defined by the first, second, or third QP in the set). A value of 4 can indicate that the filtering mode for the NN model is defined at a lower level (e.g., at the CTU level or the CU level) by the second-level filtering mode syntax element. A value of 0 for the second-level filtering mode syntax element can indicate that NN-based filtering is disabled for the color component (as an example). A value of 1, 2, or 3 can indicate a filtering mode for the NN model for both the first color component and the second color component (e.g., defining whether the first, second, or third QP in the set is used, and the filtering mode defined by the first, second, or third QP in the set).

[0279] first_chroma_mode_slice is another example of a syntax element that defines a filtering mode for a neural network (NN) model for both the first color component and the second color component. For example, if first_chroma_mode_slice has a non-zero value and NN-based filtering is enabled for the second color component, first_chroma_mode_slice defines a filtering mode for both the first color component and the second color component.

[0280] Chroma_mode_slice is another example of a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component. For example, where first_chroma_flag_slice and / or second_chroma_flag_slice are true, the value of chroma_mode_slice may define the filtering mode (e.g., whether the first, second, or third QP value in the set is used to define the filtering mode).

[0281] The filtering unit 312 may apply the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first filtered block (902). For example, the filtering unit 312 may apply the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first residual value, and generate the first filtered block based on the first block and the first residual value (e.g., by summing the first residual value and the first filtered block).

[0282] In some examples, if NN-based filtering is enabled for the first color component, NN-based filtering is automatically enabled for the second color component. That is, in some examples, filtering of the second color component cannot be selectively not used. Therefore, in one or more examples, the filtering unit 312 can apply the same instance of the NN model to the second block of the second color component in the defined filtering mode to generate a second filtered block (906). As described above, applying the same instance of the NN model can mean that the NN model receives both a first block of the first color component and a second block of the second color component (e.g., including a luminance component) as input, and generates a first filtered block of the first color component and a second filtered block of the second color component as output.

[0283] That is, in some examples, an NN model for a chrominance component (e.g., a first color component and a second color component) may also receive a luma component as input, but outputs a first filtered block of the first color component and a second filtered block of the second color component. The NN model may not generate a filtered luma block, but in some examples, the NN model may generate a filtered luma block.

[0284] In this case, the filtering unit 312 may store the first filtered block and the second filtered block (908).For example, the sample values ​​stored in the DPB 314 by the filtering unit 312 for the CU may be the values ​​of the first filtered block and the second filtered block.

[0285] However, in some examples, utilizing the second filtered block may not always be possible and may be optional. For example, in some examples, filtering unit 312 may determine whether to enable NN-based filtering for the second color component (904). For example, filtering unit 312 may determine the value of first_chroma_flag_slice or second_chroma_flag_slice.

[0286] For example, the syntax element defining the filtering mode may be first_chroma_mode_slice. If the value of first_chroma_mode_slice is non-zero, the filtering unit 312 may determine the value of a flag (e.g., second_chroma_flag_slice). That is, the filtering unit 312 may receive a flag indicating that NN-based filtering is enabled for the second color component ("Yes" of 904). In this example, the filtering unit 312 may apply the same instance of the NN model to the second block of the second color component in the defined filtering mode to generate a second filtered block (906), and store the first filtered block and the second filtered block (908).

[0287] However, in some examples, filtering unit 312 may receive a flag indicating that NN-based filtering is disabled for the second color component (“No” of 904). In this example, filtering unit 312 may store the first filtered block and the second block (e.g., non-NN filtered block) (910).

[0288] Example techniques based on one or more examples described in this disclosure are described below.

[0289] Item 1A. A method of processing video data, the method comprising: filtering two or more color components of the video data using a single neural network (NN) model based filter; and outputting the two or more color components after a single filtering process using the single NN based filter.

[0290] Clause 2A. The method of clause 1A, wherein filtering comprises determining how to apply the NN-based filter, whether to turn the NN-based filter on or off, how to create input data for the single NN model, and determining values ​​of all input elements in the same manner for the two or more color components.

[0291] Clause 3A. The method of clause 1A, further comprising: receiving or signaling information indicating whether the NN-based filter is turned on or off for each of the two or more color components, filtering comprising: filtering based on whether the NN-based filter is turned on or off for each of the two or more color components.

[0292] Clause 4A. The method of any of clauses 1A to 3A, further comprising reconstructing sample values ​​of a picture, wherein filtering comprises filtering the two or more color components of the reconstructed sample values ​​of the picture.

[0293] Clause 5A. The method of Clause 4A, wherein filtering comprises in-loop filtering in a video encoder or a video decoder.

[0294] Clause 6A. The method of Clause 4A, wherein filtering comprises post-loop filtering in a video decoder.

[0295] Clause 7A. An apparatus for processing video data, the apparatus comprising: a memory configured to store the video data; and a processing circuit configured to perform the method of any of clauses 1A-6A.

[0296] Clause 8A. The apparatus of Clause 7A, further comprising a display configured to display the decoded video data.

[0297] Clause 9A. The device of any of clauses 7A and 8A, wherein the device comprises one or more of: a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

[0298] Clause 10A. The apparatus of any of clauses 7A-9A, wherein the apparatus comprises a video decoder.

[0299] Clause 11A. The apparatus of any of clauses 7A-10A, wherein the apparatus comprises a video encoder.

[0300] Clause 12A. A computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to perform the method of any of clauses 1A-6A.

[0301] Clause 13A. An apparatus for processing video data, the apparatus comprising: means for performing the method according to any of clauses 1A-6A.

[0302] Clause 1B. A method of processing video data, the method comprising: receiving a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component; applying an instance of the NN model to a first block of the first color component in the defined filtering mode to generate a first filtered block; and storing the first filtered block for a coding unit (CU).

[0303] Clause 2B. The method of clause 1B, further comprising: applying the same instance of the NN model to a second block of the second color component in the defined filtering mode to generate a second filtered block, wherein storing comprises: storing the first filtered block and the second filtered block for the CU.

[0304] Clause 3B. The method of any of clauses 1B and 2B, wherein receiving the syntax element comprises receiving the syntax element applicable to a plurality of CUs, wherein the CU is one of the plurality of CUs.

[0305] Clause 4B. The method of any of clauses 1B-3B, wherein the syntax element is a second syntax element, the method further comprising: receiving a first syntax element applicable to multiple CUs, the first syntax element indicating that the second syntax element is to be parsed for a subset of CUs in the multiple CUs, wherein the CU subset includes one or more CUs that include the CU, wherein receiving the syntax element comprises: receiving the second syntax element based on the first syntax element indicating that the second syntax element is to be parsed for the subset of CUs.

[0306] Clause 5B. A method as recited in any of Clauses 1B-4B, wherein the syntax element has a value indicating that NN-based filtering is enabled for the first color component.

[0307] Clause 6B. The method of clause 5B further comprises: receiving a flag indicating that NN-based filtering is enabled for the second color component; and generating a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in the defined filtering mode, wherein storing comprises: storing the first filtered block and the second filtered block for the CU.

[0308] Clause 7B. The method of Clause 5B, further comprising receiving a flag indicating that NN-based filtering is disabled for the second color component, wherein storing comprises storing the first filtered block and a second block of the second color component for the CU.

[0309] Clause 8B. The method of any of clauses 1B-7B, further comprising receiving a flag indicating that NN-based filtering is enabled for the first color component, wherein receiving the syntax element comprises receiving the syntax element based on the flag indicating that NN-based filtering is enabled for the first color component.

[0310] Clause 9B. The method of any of clauses 1B-8B, wherein the syntax element defines which parameter to select from a plurality of parameters, and wherein the defined parameter specifies the filtering mode.

[0311] Clause 10B. The method of clause 9B, wherein the parameter is a quantization parameter and the plurality of parameters is one of a predefined set or a signaled set.

[0312] Clause 11B. The method of any of clauses 1B-10B, wherein the first color component is a first chrominance component and the second color component is a second chrominance component.

[0313] Clause 12B. A method according to any of clauses 1B-11B, wherein applying the instance of the NN model to the first block of the first color component in the defined filtering mode to generate the first filtered block comprises: applying the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first residual value; and generating the first filtered block based on the first block and the first residual value.

[0314] Clause 13B. An apparatus for processing video data, the apparatus comprising: a memory configured to store the video data; and one or more processors implemented with circuitry coupled to the memory, configured to: receive a syntax element defining a filtering mode for a neural network (NN) model for a first color component and a second color component; in the defined filtering mode, apply an instance of the NN model to a first block of the first color component to generate a first filtered block; and store the first filtered block in the memory for a coding unit (CU).

[0315] Clause 14B. The apparatus of clause 13B, wherein the one or more processors are configured to: apply the same instance of the NN model to a second block of the second color component in a defined filtering mode to generate a second filtered block, wherein, for storage, the one or more processors are configured to: store the first filtered block and the second filtered block for the CU.

[0316] Clause 15B. The apparatus of any of clauses 13B or 14B, wherein to receive the syntax element, the one or more processors are configured to: receive the syntax element applicable to a plurality of CUs, wherein the CU is one of the plurality of CUs.

[0317] Clause 16B. An apparatus as described in any of clauses 13B-15B, wherein the syntax element is a second syntax element, and wherein the one or more processors are configured to: receive a first syntax element applicable to multiple CUs, the first syntax element indicating that the second syntax element is to be parsed for a subset of CUs in the multiple CUs, wherein the CU subset includes one or more CUs having the CU, and wherein, to receive the syntax element, the one or more processors are configured to: receive the second syntax element based on the first syntax element indicating that the second syntax element is to be parsed for the subset of CUs.

[0318] Clause 17B. The apparatus of any of clauses 13B-16B, wherein the syntax element has a value indicating that NN-based filtering is enabled for the first color component.

[0319] Clause 18B. The apparatus of clause 17B, wherein the one or more processors are configured to: receive a flag indicating that NN-based filtering is enabled for the second color component; and generate a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in a defined filtering mode, wherein, for storage, the one or more processors are configured to: store the first filtered block and the second filtered block for the CU.

[0320] Clause 19B. The apparatus of clause 17B, wherein the one or more processors are configured to: receive a flag indicating that NN-based filtering is disabled for the second color component, wherein, for storage, the one or more processors are configured to: store the first filtered block and a second block of the second color component for the CU.

[0321] Clause 20B. A device as described in any of clauses 13B-19B, wherein the one or more processors are configured to: receive a flag indicating that NN-based filtering is enabled for the first color component, wherein to receive the syntax element, the one or more processors are configured to: receive the syntax element based on the flag indicating that NN-based filtering is enabled for the first color component.

[0322] Clause 21B. The apparatus of any of clauses 13B-20B, wherein the syntax element defines which parameter to select from a plurality of parameters, and wherein the defined parameter specifies the filtering mode.

[0323] Clause 22B. The apparatus of clause 21B, wherein the parameter is a quantization parameter and the plurality of parameters is one of a predefined set or a signaled set.

[0324] Clause 23B. The apparatus of any of Clauses 13B-22B, wherein the first color component is a first chrominance component and the second color component is a second chrominance component.

[0325] Clause 24B. A device according to any of clauses 13B-23B, wherein, in order to apply the instance of the NN model to the first block of the first color component in the defined filtering mode to generate the first filtered block, the one or more processors are configured to: apply the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first residual value; and generate the first filtered block based on the first block and the first residual value.

[0326] Clause 25B. A computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to perform the following operations: receive a syntax element that defines a filtering mode for a neural network (NN) model for both a first color component and a second color component; in the defined filtering mode, apply an instance of the NN model to a first block of the first color component to generate a first filtered block; and store the first filtered block for a coding unit (CU).

[0327] It should be appreciated that, according to examples, certain actions or events of any of the techniques described herein may be performed in a different order, may be added, combined, or omitted entirely (e.g., not all described actions or events are required to implement the technique). In addition, in some examples, actions or events may be performed concurrently rather than sequentially, such as through multithreading, interrupt handling, or multiple processors.

[0328] In one or more examples, the functions described may be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, the functions may be stored on a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. A computer-readable medium may include a computer-readable storage medium, which corresponds to a tangible medium such as a data storage medium or a communication medium, wherein the communication medium includes any medium that facilitates, for example, transmitting a computer program from one place to another according to a communication protocol. In this manner, a computer-readable medium may generally correspond to: (1) a non-temporary tangible computer-readable storage medium; or (2) a communication medium such as a signal or carrier waveform. A data storage medium may be any available medium that one or more computers or one or more processors can access to obtain instructions, codes, and / or data structures for implementing the techniques described in the present disclosure. A computer program product may include a computer-readable medium.

[0329] By way of example, but not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage devices, flash memory or any other medium capable of storing desired program code in the form of instructions or data structures and capable of being accessed by a computer. In addition, any connection may be appropriately referred to as a computer-readable medium. For example, if the instruction is transmitted from a website, server or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, wireless and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, wireless and microwave are included in the definition of the medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waveforms, signals or other temporary media, but are directed to non-temporary tangible storage media. As used herein, disks and optical disks include compact disks CD, laser optical disks, optical disks, digital versatile disks (DVD), floppy disks and blue-ray disks, wherein disks usually reproduce data magnetically, while optical disks reproduce data optically using lasers. The above combinations should also be included within the protection scope of computer-readable media.

[0330] Instructions may be executed by one or more processors such as one or more DSPs, general-purpose microprocessors, ASICs, FPGAs, or other equivalent integrated or discrete logic circuits. Therefore, as used herein, the terms "processor" and "processing circuit" may refer to any of the aforementioned structures or any other structures suitable for implementing the techniques described herein. In addition, in some aspects, the functions described herein may be provided in dedicated hardware and / or software modules configured to implement encoding and decoding, or incorporated into a combined codec. In addition, these techniques may be fully implemented in one or more circuits or logic elements.

[0331] The techniques of the present disclosure may be implemented using a variety of devices or apparatuses, including the use of a wireless handheld device, an integrated circuit (IC), or a set of ICs (e.g., a chipset). Various components, modules, or units are described in the present disclosure to emphasize the functional aspects of the devices configured to perform the disclosed techniques, but do not necessarily need to be implemented by different hardware units. Instead, as described above, the various units may be combined in a codec hardware unit, or provided by a collection of cooperating hardware units (which include one or more processors as described above) in combination with appropriate software and / or firmware.

[0332] Various examples are described. These and other examples are within the scope of protection of the following claims.

Claims

1. A method for processing video data, the method comprising: receiving a syntax element defining a filtering mode for a neural network (NN) model for both a first color component and a second color component; applying, in the defined filtering mode, an instance of the NN model to a first block of the first color component to generate a first filtered block; as well as The first filtered block is stored for a coding unit (CU).

2. The method according to claim 1, further comprising: applying the same instance of the NN model to a second block of the second color component to generate a second filtered block in the defined filtering mode, The storing includes: storing the first filtered block and the second filtered block for the CU.

3. The method according to claim 1, wherein: Receiving the syntax element includes receiving the syntax element applicable to multiple CUs, wherein the CU is one CU of the multiple CUs.

4. The method according to claim 1, wherein: The syntax element is a second syntax element, and the method further includes: receiving a first syntax element applicable to a plurality of CUs, the first syntax element indicating that the second syntax element is to be parsed for a subset of CUs in the plurality of CUs, wherein the subset of CUs includes one or more CUs including the CU, Receiving the syntax element includes: parsing the second syntax element for the CU subset based on the indication of the first syntax element to receive the second syntax element.

5. The method according to claim 1, wherein: The syntax element has a value indicating that NN-based filtering is enabled for the first color component.

6. The method according to claim 5, further comprising: receiving a flag indicating enabling NN-based filtering for the second color component; as well as generating a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in the defined filtering mode, The storing includes: storing the first filtered block and the second filtered block for the CU.

7. The method according to claim 5, further comprising: receiving a flag indicating disabling NN-based filtering for the second color component, The storing comprises: storing the first filtered block and the second block of the second color component for the CU.

8. The method according to claim 1, further comprising: receiving a flag indicating that NN-based filtering is enabled for the first color component, The receiving of the syntax element comprises: receiving the syntax element based on the flag indicating enabling NN-based filtering for the first color component.

9. The method according to claim 1, wherein: The syntax element defines which parameter is selected from a plurality of parameters, and wherein the defined parameter specifies the filtering mode.

10. The method according to claim 9, wherein: The parameter is a quantization parameter and the plurality of parameters is one of a predefined set or a signaled set.

11. The method according to claim 1, wherein: The first color component is a first chrominance component and the second color component is a second chrominance component.

12. The method according to claim 1, wherein: Applying the instance of the NN mode to the first block of the first color component in the defined filtering mode to generate the first filtered block, comprising: applying the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first residual value; and Based on the first block and the first residual value, the first filtered block is generated.

13. A device for processing video data, the device comprising: a memory configured to store the video data; as well as One or more processors implemented with circuitry coupled to the memory and configured to: receiving a syntax element defining a filtering mode for a neural network (NN) model for both a first color component and a second color component; applying, in the defined filtering mode, an instance of the NN model to a first block of the first color component to generate a first filtered block; as well as In the memory, the first filtered block is stored for a coding unit (CU).

14. The device according to claim 13, wherein: The one or more processors are configured to: applying the same instance of the NN model to a second block of the second color component to generate a second filtered block in the defined filtering mode, In which, for storage, the one or more processors are configured to: store the first filtered block and the second filtered block for the CU.

15. The apparatus according to claim 13, wherein: To receive the syntax element, the one or more processors are configured to: receive the syntax element applicable to multiple CUs, wherein the CU is one CU of the multiple CUs.

16. The apparatus according to claim 13, wherein: The syntax element is a second syntax element, and wherein the one or more processors are configured to: receiving a first syntax element applicable to a plurality of CUs, the first syntax element indicating that the second syntax element is to be parsed for a subset of CUs in the plurality of CUs, wherein the subset of CUs includes one or more CUs including the CU, In order to receive the syntax element, the one or more processors are configured to: parse the second syntax element for the CU subset based on the first syntax element indication to receive the second syntax element.

17. The apparatus according to claim 13, wherein: The syntax element has a value indicating that NN-based filtering is enabled for the first color component.

18. The apparatus according to claim 17, wherein: The one or more processors are configured to: receiving a flag indicating enabling NN-based filtering for the second color component; as well as generating a second filtered block based on the second block of the second color component by applying the same instance of the NN model to the second block in the defined filtering mode, Wherein, for storage, the one or more processors are configured to: store the first filtered block and the second filtered block for the CU.

19. The apparatus according to claim 17, wherein: The one or more processors are configured to: receiving a flag indicating disabling NN-based filtering for the second color component, Wherein, for storage, the one or more processors are configured to: store the first filtered block and the second block of the second color component for the CU.

20. The apparatus of claim 13, wherein: The one or more processors are configured to: receiving a flag indicating that NN-based filtering is enabled for the first color component, In order to receive the syntax element, the one or more processors are configured to: receive the syntax element based on the flag indicating that NN-based filtering is enabled for the first color component.

21. The apparatus of claim 13, wherein: The syntax element defines which parameter is selected from a plurality of parameters, and wherein the defined parameter specifies the filtering mode.

22. The apparatus according to claim 21, wherein The parameter is a quantization parameter and the plurality of parameters is one of a predefined set or a signaled set.

23. The apparatus of claim 13, wherein: The first color component is a first chrominance component and the second color component is a second chrominance component.

24. The apparatus of claim 13, wherein: To apply the instance of the NN mode to the first block of the first color component in the defined filtering mode to generate the first filtered block, the one or more processors are configured to: applying the instance of the NN model to the first block of the first color component in the defined filtering mode to generate a first residual value; as well as Based on the first block and the first residual value, the first filtered block is generated.

25. A computer-readable storage medium having stored thereon instructions which, when executed, cause one or more processors to: receiving a syntax element defining a filtering mode for a neural network (NN) model for both a first color component and a second color component; applying, in the defined filtering mode, an instance of the NN model to a first block of the first color component to generate a first filtered block; as well as The first filtered block is stored for a coding unit (CU).

Images