Multiple neural network models for filtering during video coding

Abstract

An example device for filtering decoded video data includes one or more processors, where the one or more processors are configured to execute a neural network filtering unit to receive data from one or more other units of the device, where the data from the one or more other units of the device is different from data for a decoded picture of the video data, and to receive data from the one or more other units of the device, the one or more processors are configured to execute a neural network filtering unit to receive boundary strength data from a deblocking unit of the device; determine one or more neural network models to be used to filter a portion of the decoded picture; and filter the portion of the decoded picture using the one or more neural network models and the data including the boundary strength data from the one or more other units of the device.

Description

[Technical Field]

[0001] This application claims priority to U.S. Patent Application No. 17 / 566,282, filed on 30 December 2021, and U.S. Provisional Application No. 63 / 133,733, filed on 4 January 2021, the entire contents of each of these applications being incorporated herein by reference. U.S. Patent Application No. 17 / 566,282, filed on 30 December 2021, claims the benefit of U.S. Provisional Application No. 63 / 133,733, filed on 4 January 2021.

[0002] This disclosure relates to video coding, including video encoding and video decoding. [Background technology]

[0003] Digital video capabilities can be incorporated into a wide range of devices, including digital television, 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 gaming devices, video game consoles, cellular or satellite radio phones, so-called "smartphones," video teleconferencing devices, and video streaming devices. Digital video devices implement video coding techniques such as those described in standards defined 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), and extensions of such standards. By implementing such video coding techniques, video devices can transmit, receive, encode, decode, and / or store digital video information more efficiently.

[0004] Video coding techniques include spatial (intra-picture) prediction and / or temporal (inter-picture) prediction to reduce or eliminate redundancy inherent in video sequences. In 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 called coding tree units (CTUs), coding units (CUs), and / or coding nodes. Video blocks in an intra-coded (I) slice of a picture are coded using spatial predictions for reference samples in adjacent blocks within the same picture. Video blocks in an inter-coded (P or B) slice of a picture may use spatial predictions for reference samples in adjacent blocks within the same picture or temporal predictions for reference samples in other reference pictures. Pictures may be called frames, and reference pictures may be called reference frames. [Overview of the project] [Means for solving the problem]

[0005] In general, this disclosure describes techniques for filtering decoded pictures that may be distorted. The filtering process may be based on neural network techniques. The filtering process may be used in the context of advanced video codecs, such as extensions to ITU-T H.266 / Vulnerable Video Coding (VVC), or subsequent generations of video coding standards, and any other video codecs. In one example, a neural network filtering unit may receive boundary intensity values ​​calculated by a deblocking filter and use the boundary intensity values ​​to further filter the deblocked video data using, for example, one or more neural network models.

[0006] For example, a method for filtering decoded video data includes the steps of: receiving data for a decoded picture of video data by a neural network filtering unit of a video decoding device; receiving data from one or more other units of the video decoding device by the neural network filtering unit, wherein the data from one or more other units is different from the data for the decoded picture, and the step of receiving data from one or more other units of the video decoding device includes the step of receiving boundary intensity data from a deblocking unit of the video decoding device; determining one or more neural network models to be used to filter a portion of the decoded picture by the neural network filtering unit; and filtering a portion of the decoded picture by the neural network filtering unit using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0007] In another example, a device for filtering decoded video data includes a memory configured to store decoded pictures of video data, and one or more processors implemented in the circuit, the one or more processors being configured to perform a neural network filtering unit to receive data from one or more other units of the device, wherein the data from one or more other units of the device is different from the data for the decoded pictures, and in order to receive data from one or more other units of the device, the one or more processors are configured to perform a neural network filtering unit to receive boundary intensity data from a deblocking unit of the device, to receive data from one or more other units of the device, to determine one or more neural network models to be used to filter a portion of the decoded pictures, and to filter a portion of the decoded pictures using one or more neural network models and the data including boundary intensity data from one or more other units of the device.

[0008] In another example, a computer-readable storage medium stores instructions, which, when executed, cause the processor of a video decoding device to execute a neural network filtering unit to receive data for a decoded picture of video data, and to receive data from one or more other units of the video decoding device, wherein the data from one or more other units of the video decoding device is different from the data for the decoded picture, and the instructions causing the processor to receive data from one or more other units of the video decoding device include instructions causing the processor to receive boundary intensity data from the deblocking unit of the video decoding device, to determine one or more neural network models to be used to filter a portion of the decoded picture, and to filter a portion of the decoded picture using one or more neural network models and the data including boundary intensity data from one or more other units of the video decoding device.

[0009] In another example, a device for filtering decoded video data comprises means for receiving data for a decoded picture of the video data; means for receiving data from one or more other units of the video decoding device, wherein the data from one or more other units is different from the data for the decoded picture, and the means for receiving data from one or more other units of the video decoding device includes means for receiving boundary intensity data from a deblocking unit of the video decoding device; means for determining one or more neural network models to be used to filter a portion of the decoded picture; and means for filtering a portion of the decoded picture using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0010] Details of one or more examples are described in the accompanying drawings and the following description. Other features, purposes, and advantages will become apparent from the description, drawings, and claims. [Brief explanation of the drawing]

[0011] [Figure 1] Block diagram shows an exemplary video encoding and decoding system capable of performing the techniques of this disclosure. [Figure 2] This is a conceptual diagram illustrating a hybrid video coding framework. [Figure 3] This is a conceptual diagram showing a hierarchical prediction structure using 16 picture group (GOP) sizes. [Figure 4] This is a conceptual diagram showing a neural network-based filter with four layers. [Figure 5] This is a conceptual diagram showing exemplary parts of a picture, including the boundary, boundary sample, and internal sample. [Figure 6] A block diagram illustrating a video encoder capable of performing the techniques of this disclosure. [Figure 7] A block diagram illustrating an exemplary video decoder capable of performing the techniques of this disclosure. [Figure 8] This flowchart shows an exemplary method for encoding the current block using the technique of the present disclosure. [Figure 9] This flowchart shows an exemplary method for decoding the current block using the technique of the present disclosure. [Figure 10] This flowchart shows an exemplary method for filtering decoded video data using the technique of the present disclosure. [Modes for carrying out the invention]

[0012] Video coding standards include High Efficiency Video Coding (HEVC) including 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), its range extensions such as Multi-View Extension (MV-HEVC) and Scalable Extension (SHVC), or ITU-T H.265. Another exemplary video coding standard is Versatile Video Coding (VVC) or ITU-T H.266 developed by the Joint Video Expert Team (JVET) of the ITU-T Video Coding Experts Group (VCEG) and the ISO / IEC Motion Picture Experts Group (MPEG). Version 1 of the VVC specification, hereinafter referred to as "VVC FDIS", is available from http: / / phenix.int-evry.fr / jvet / doc_end_user / documents / 19_Teleconference / wg11 / JVET-S2001-v17.zip.

[0013] FIG. 1 is a block diagram showing an exemplary video encoding and decoding system 100 that can execute the techniques of the present disclosure. The techniques of the present disclosure generally aim to encode (encode and / or decode) video data. Generally, video data includes any data for processing video. Thus, video data can include raw unencoded video, encoded video, decoded (e.g., reconstructed) video, and video metadata such as signaling data.

[0014] As shown in FIG. 1, system 100 includes, in this example, a source device 102 that provides encoded video data to be decoded and displayed by a 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 comprise any of a wide range of devices, including desktop computers, notebook (i.e., laptop) computers, mobile devices, tablet computers, set-top boxes, telephone handsets such as smartphones, televisions, cameras, display devices, digital media players, video gaming consoles, video streaming devices, and the like. In some cases, source device 102 and destination device 116 may be equipped for wireless communication and thus may be referred to as wireless communication devices.

[0015] In the example of FIG. 1, source device 102 includes a video source 104, a memory 106, a video encoder 200, and an output interface 108. Destination device 116 includes an input interface 122, a video decoder 300, a memory 120, and a display device 118. According to the present disclosure, video encoder 200 of source device 102 and video decoder 300 of destination device 116 may be configured to apply techniques for filtering using a plurality of neural network models. Accordingly, 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 devices and destination devices may include other components or configurations. For example, source device 102 may receive video data from an external video source such as an external camera. Similarly, destination device 116 may interface with an external display device rather than including an integrated display device.

[0016] System 100, as shown in Figure 1, is merely an example. In general, any digital video coding and / or decoding device may perform techniques for filtering using multiple neural network models. Source device 102 and destination device 116 are merely examples of coding devices such that source device 102 generates coded video data for transmission to destination device 116. This disclosure refers to a device that performs coding (encoding and / or decoding) of data as a “coding” device. Thus, video encoder 200 and video decoder 300 represent examples of coding devices, specifically, video encoder and video decoder, respectively. In some examples, source device 102 and destination device 116 may operate in a substantially symmetrical manner such that each of source device 102 and destination device 116 includes video coding and decoding components. Thus, system 100 may support one-way or two-way video transmission between source device 102 and destination device 116 for, for example, video streaming, video playback, video broadcasting, or video telephony.

[0017] Generally, the video source 104 represents a source of video data (i.e., raw, uncoded video data) and provides the video encoder 200 with a sequence of pictures (also called "frames") of video data, which 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 video camera, a video archive containing previously captured raw 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 source video, or a combination of live video, archived video, and computer-generated video. In each case, the video encoder 200 encodes the captured, pre-captured, or computer-generated video data. The video encoder 200 may rearrange the pictures from the order in which they were received (sometimes called the "display order") to a coding order for encoding. The video encoder 200 may generate a bitstream containing the encoded video data. The source device 102 may then output the encoded video data onto a computer-readable medium 110 via the output interface 108 for reception and / or retrieval by the input interface 122 of the destination device 116.

[0018] Memory 106 of source device 102 and memory 120 of destination device 116 represent general-purpose memory. In some examples, memories 106 and 120 may store raw video data, for example, raw video from video source 104 and raw decoded video data from video decoder 300. Additionally or alternatively, memories 106 and 120 may store, for example, software instructions executable by video encoder 200 and video decoder 300, respectively. Although memories 106 and 120 are shown separately from video encoder 200 and video decoder 300 in this example, it should be understood that video encoder 200 and video decoder 300 may also include internal memory for functionally similar or equivalent purposes. Furthermore, memories 106 and 120 may store encoded video data, for example, output from video encoder 200 and input to video decoder 300. In some examples, portions of memory 106, 120 may be allocated as one or more video buffers for storing, for example, raw, decoded, and / or encoded video data.

[0019] The computer-readable medium 110 may represent any type of medium or device capable of transporting encoded video data from the source device 102 to the destination device 116. For example, the computer-readable medium 110 may represent a communication medium that enables the source device 102 to directly transmit encoded video data to the destination device 116 in real time, for example, over a radio frequency network or a computer-based network. According to a communication standard such as a wireless communication protocol, the output interface 108 may modulate the transmission signal containing the encoded video data, and the input interface 122 may demodulate the received transmission signal. The communication medium may comprise 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 such as the Internet. The communication medium may include routers, switches, base stations, or any other equipment that may be useful to facilitate communication from the source device 102 to the destination device 116.

[0020] In some examples, the source device 102 may output encoded data to the storage device 112 via the output interface 108. Similarly, the destination device 116 may access the encoded data from the storage device 112 via the input interface 122. The 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 medium for storing encoded video data.

[0021] In some examples, the source device 102 may output the encoded video data to a file server 114 or another intermediate storage device capable of storing the encoded video data generated by the source device 102. The destination device 116 may access the stored video data from the file server 114 via streaming or download.

[0022] The file server 114 may be any type of server device capable of storing encoded video data and transmitting that encoded video data to the destination device 116. The file server 114 may represent a web server (for example, for a website), a server configured to provide file transfer protocol services (such as the File Transfer Protocol (FTP) or File Delivery over Unidirectional Transport (FLUTE) protocol), a Content Delivery Network (CDN) device, a Hypertext Transfer Protocol (HTTP) server, a Multimedia Broadcast Multicast Service (MBMS) or Enhanced MBMS (eMBMS) server, and / or a Network Attached Storage (NAS) device. The file server 114 may, in addition or alternatively, implement one or more HTTP streaming protocols, such as Dynamic Adaptive Streaming over HTTP (DASH), HTTP Live Streaming (HLS), Real Time Streaming Protocol (RTSP), or HTTP Dynamic Streaming.

[0023] The destination device 116 may access the encoded video data from the file server 114 through any standard data connection, including an internet connection. This may include wireless channels (e.g., Wi-Fi connection), wired connections (e.g., digital subscriber line (DSL), cable modem, etc.), or a combination of both suitable for accessing the encoded video data stored on the file server 114. The input interface 122 may be configured to operate according to one or more of the various protocols described above for retrieving or receiving media data from the file server 114, or other such protocols for retrieving media data.

[0024] The output interface 108 and input interface 122 may represent a wireless transmitter / receiver, a modem, a wired networking component (e.g., an Ethernet card), a wireless communication component operating according to any of the various IEEE 802.11 standards, or other physical components. In examples where the output interface 108 and input interface 122 include wireless components, the output interface 108 and input interface 122 may be configured to transfer data such as encoded video data according to cellular communication standards such as 4G, 4G-LTE (Long Term Evolution), LTE Advanced, or 5G. In some examples where the output interface 108 includes a wireless transmitter, the output interface 108 and input interface 122 may be configured to transfer data such as encoded video data according to other wireless standards such as the IEEE 802.11 specification, the IEEE 802.15 specification (e.g., ZigBee®), or the Bluetooth® standard. In some examples, the source device 102 and / or destination device 116 may include their respective system-on-chip (SoC) devices. For example, source device 102 may include an SoC device for performing functions related to the video encoder 200 and / or output interface 108, and destination device 116 may include an SoC device for performing functions related to the video decoder 300 and / or input interface 122.

[0025] The techniques of this disclosure can be applied to video coding that supports any of a variety of multimedia applications, such as over-the-air television broadcasting, cable television transmission, satellite television transmission, internet streaming video transmission such as 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.

[0026] The input interface 122 of the destination device 116 receives an encoded video bitstream from a 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 having values ​​that describe the characteristics and / or processing of video blocks or other coded units (e.g., slices, pictures, picture groups, sequences, etc.). The display device 118 displays the decoded picture of the decoded video data to the user. The display device 118 may represent any of various 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.

[0027] Although not shown in Figure 1, in some examples the video encoder 200 and video decoder 300 may be integrated with an audio encoder and / or audio decoder, respectively, and may include a suitable MUX-DEMUX unit or other hardware and / or software to handle multiplexed streams containing both audio and video in a common data stream. Where applicable, the MUX-DEMUX unit may comply with the ITU H.223 Multiplexer Protocol or other protocols such as the User Datagram Protocol (UDP).

[0028] The video encoder 200 and video decoder 300 may each be implemented as one or more 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 the technique is partially implemented in software, the device may store instructions for the software in a suitable non-temporary computer-readable medium and execute the instructions in hardware using one or more processors to perform the technique of this disclosure. Each of the video encoder 200 and video decoder 300 may be included in one or more encoders or decoders, any of which may be integrated as part of a composite encoder / decoder (CODEC) in their respective devices. A device including the video encoder 200 and / or video decoder 300 may include an integrated circuit, a microprocessor, and / or a wireless communication device such as a cellular telephone.

[0029] The video encoder 200 and video decoder 300 may operate in accordance with video coding standards such as ITU-T H.265, also known as High Efficiency Video Coding (HEVC), or its extensions, such as the Multiview and / or Scalable Video Coding extension. Alternatively, the video encoder 200 and video decoder 300 may operate in accordance with other proprietary or industry standards, such as Versatile Video Coding (VVC). A draft of the VVC standard is described in Bross et al., "Versatile Video Coding (Draft 9)," ITU-T SG 16 WP 3 and the Joint Video Experts Team (JVET) of ISO / IEC JTC 1 / SC 29 / WG 11, 18th meeting, April 15-24, JVET-R2001-v8 (hereinafter referred to as "VVC Draft 9"). However, the techniques of this disclosure are not limited to any particular coding standard.

[0030] Generally, the video encoder 200 and video decoder 300 can perform block-based coding of a picture. The term “block” generally refers to a structure containing data to be processed (e.g., encoded, decoded, or otherwise used in the encoding and / or decoding process). For example, a block may contain a two-dimensional matrix of samples of luminance and / or chrominance data. Generally, the video encoder 200 and video decoder 300 can code video data represented in YUV (e.g., Y, Cb, Cr) format. That is, rather than coding red, green, and blue (RGB) data for the samples of a picture, the video encoder 200 and video decoder 300 can code luminance and chrominance components, and the chrominance component may contain both red and blue chrominance components. In some examples, the video encoder 200 converts the received RGB-formatted data to a YUV representation prior to encoding, and the video decoder 300 converts the YUV representation to RGB format. Alternatively, pre-processing units and post-processing units (not shown) may perform these conversions.

[0031] This disclosure may refer to coding a picture (e.g., encoding and decoding) to include, in general, the process of encoding or decoding the data of a picture. Similarly, this disclosure may refer to coding a block of a picture (e.g., predictive and / or residual coding) to include the process of encoding or decoding the data for that block. An encoded video bitstream generally contains a set of values ​​for syntax elements representing coding decisions (e.g., coding modes) and divisions of the picture into blocks. Thus, references to coding a picture or a block should generally be understood as coding values ​​for the syntax elements that make up the picture or block.

[0032] HEVC defines various blocks, including coding units (CUs), prediction units (PUs), and transformation units (TUs). According to HEVC, a video coder (such as video encoder 200) divides coding tree units (CTUs) into CUs according to a quadtree structure. That is, the video coder divides the CTUs and CUs into four equal, non-overlapping squares, and each node in the quadtree has either zero or four child nodes. Nodes without child nodes are sometimes called "leaf nodes," and the CUs of such leaf nodes may contain one or more PUs and / or one or more TUs. The video coder may further divide the PUs and TUs. For example, in HEVC, a residual quadtree (RQT) represents a division of TUs. In HEVC, PUs represent intra-prediction data, and TUs represent residual data. Intra-predicted CUs contain intra-prediction information, such as intra-mode indications.

[0033] As another example, a video encoder 200 and a video decoder 300 may be configured to operate according to VVC. According to VVC, a video coder (such as the video encoder 200) divides a picture into multiple coding tree units (CTUs). The video encoder 200 may divide the CTUs according to a tree structure such as a quad-binary tree (QTBT) structure or a multi-type tree (MTT) structure. The QTBT structure eliminates the concept of multiple division types, such as the distinction between CU, PU, ​​and TU in HEVC. The QTBT structure includes two levels: a first level divided according to quad-tree divisions and a second level divided according to binary tree divisions. The root node of the QTBT structure corresponds to a CTU. The leaf nodes of the binary tree correspond to coding units (CUs).

[0034] In an MTT partitioned structure, blocks can be partitioned using quadrant (QT) partitions, binary (BT) partitions, and one or more types of triple tree (TT) partitions (also called ternary tree) partitions. A triple tree or ternary tree partition is a partition in which a block is divided into three subblocks. In some examples, a triple tree or ternary tree partition divides a block into three subblocks without dividing the original block through a center. The partition types in MTT (e.g., QT, BT, and TT) can be symmetric or asymmetric.

[0035] In some examples, the video encoder 200 and video decoder 300 may use a single QTBT or MTT structure to represent each of the luminance and chrominance components, while in other examples, the video encoder 200 and video decoder 300 may use two or more QTBT or MTT structures, such as one QTBT / MTT structure for the luminance component and another QTBT / MTT structure for both chrominance components (or two QTBT / MTT structures for each chrominance component).

[0036] The video encoder 200 and video decoder 300 may be configured to use a quadtree partition, QTBT partition, MTT partition, or other partitioning structure per HEVC. For illustrative purposes, the description of the technique in this disclosure is presented in relation to the QTBT partition. However, it should be understood that the technique in this disclosure may also be applicable to video coders configured to use a quadtree partition or other types of partitions.

[0037] In some examples, a CTU includes a coding tree block (CTB) of a lumen sample, two corresponding CTBs of a chroma sample of a picture having three sample arrays, or a CTB of a sample of a picture coded using three separate color planes and syntax structures used to code a monochrome picture or sample. A CTB can be an N×N block of samples for some value N, such that the division of components into the CTB is a partition. Components can be an array from one of three arrays (lumen and two chroma) of a picture in a 4:2:0, 4:2:2, or 4:4:4 color format, or a single sample from that array, or an array of a picture in a monochrome format, or a single sample from that array. In some examples, a coding block is an M×N block of samples for some values ​​M and N, such that the division of the CTB into the coding block is a partition.

[0038] Blocks (e.g., CTUs or CUs) can be grouped in various ways within a picture. For example, a brick may refer to a rectangular area of ​​a row of CTUs within a particular tile in a picture. A tile can be a rectangular area of ​​CTUs within a particular tile column or row in a picture. A tile column refers to a rectangular area of ​​CTUs with a height equal to the height of the picture and a width specified by a syntax element (e.g., in a picture parameter set). A tile row refers to a rectangular area of ​​CTUs with a height specified by a syntax element (e.g., in a picture parameter set) and a width equal to the width of the picture.

[0039] In some examples, a tile may be divided into multiple bricks, each brick containing one or more CTU rows within the tile. A tile that is not divided into multiple bricks may also be called a brick. However, a brick that is a true subset of a tile may not be called a tile.

[0040] Bricks within a picture can also be arranged in slices. A slice can be an integer number of bricks in a picture that can exclusively be contained within a single Network Abstraction Layer (NAL) unit. In some examples, a slice may contain either a certain number of complete tiles or only a continuous sequence of complete bricks of a single tile.

[0041] This disclosure may interchangeably use "N×N" and "N by N," e.g., 16×16 samples or 16 by 16 samples, to refer to the sample dimension of a block (such as a CU or other video block) in terms of vertical and horizontal dimensions. Generally, a 16×16 CU has 16 samples vertically (y=16) and 16 samples horizontally (x=16). Similarly, an N×N CU generally has N samples vertically and N samples horizontally, where N represents a non-negative integer. The samples in a CU can be arranged in rows and columns. Furthermore, a CU does not necessarily have to have the same number of samples horizontally as vertically. For example, a CU may have N×M samples, where M is not necessarily equal to N.

[0042] The video encoder 200 encodes video data for CUs that represent prediction and / or residual information, as well as other information. The prediction information indicates how the CUs will be predicted to form prediction blocks for the CUs. The residual information generally represents the sample-by-sample difference between the samples of the CUs prior to encoding and the samples of the prediction blocks.

[0043] To predict a CU, the video encoder 200 can generally form prediction blocks for the CU through inter-prediction or intra-prediction. Inter-prediction generally refers to predicting the CU from data of a previously coded picture, while intra-prediction generally refers to predicting the CU from previously coded data of the same picture. To perform inter-prediction, the video encoder 200 can generate prediction blocks using one or more motion vectors. The video encoder 200 can generally perform motion search to identify a reference block that exactly matches the CU with respect to the difference between the CU and the reference block. The video encoder 200 can compute a difference metric using absolute difference sum (SAD), squared difference sum (SSD), mean absolute difference (MAD), mean squared difference (MSD), or other such difference calculations to determine whether the reference block exactly matches the current CU. In some examples, the video encoder 200 can predict the current CU using unidirectional or bidirectional prediction.

[0044] Some examples of VVC also offer an affine motion compensation mode, which can be considered an interpredictive mode. In affine motion compensation mode, the video encoder 200 may determine two or more motion vectors representing non-translational motion, such as zooming in or out, rotation, perspective motion, or other irregular motion types.

[0045] To perform intra-prediction, the video encoder 200 may select an intra-prediction mode to generate a prediction block. Several examples of VVCs provide 67 intra-prediction modes, including various directional modes, as well as planar and DC modes. Generally, the video encoder 200 selects an intra-prediction mode that describes adjacent samples to the current block (e.g., a block of CUs) from which to predict a sample of the current block. Such samples could generally be above, above and to the left of, or to the left of, the current block in the same picture as the current block, assuming that the video encoder 200 codes CTUs and CUs in raster scanning order (left to right, top to bottom).

[0046] The video encoder 200 encodes data representing the prediction mode for the current block. For example, in interprediction mode, the video encoder 200 may encode data representing which of the various available interprediction modes is used, as well as motion information about the corresponding mode. In the case of unidirectional or bidirectional interprediction, for example, the video encoder 200 may encode the motion vectors using advanced motion vector prediction (AMVP) or merge mode. The video encoder 200 may use similar modes to encode the motion vectors for affine motion compensation mode.

[0047] Following predictions such as intra-prediction or inter-prediction of a block, the video encoder 200 may compute residual data for the block. Residual data, such as a residual block, represents the sample-by-sample difference between the block and the predicted block for that block formed using the corresponding prediction mode. The video encoder 200 may apply one or more transformations to the residual block to generate transformation data in the transformation domain rather than the sample domain. For example, the video encoder 200 may apply a discrete cosine transform (DCT), integer transform, wavelet transform, or a conceptually similar transform to the residual video data. In addition, the video encoder 200 may apply a second-order transform such as a mode-dependent non-separable secondary transform (MDNSST), signal-dependent transform, or Karhunen-Loeve transform (KLT) following the first transformation. Following the application of one or more transformations, the video encoder 200 generates transformation coefficients.

[0048] As described above, following any transformation to generate the transformation coefficients, the video encoder 200 may perform quantization of the transformation coefficients. Quantization generally refers to the process of quantizing the transformation coefficients to reduce the amount of data used to represent them as much as possible, thereby achieving further compression. By performing the quantization process, the video encoder 200 may reduce the bit depth associated with some or all of the transformation coefficients. For example, the video encoder 200 may truncate 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 may perform a bitwise right shift of the value to be quantized.

[0049] Following quantization, the video encoder 200 may scan the transformation coefficients and generate a one-dimensional vector from a two-dimensional matrix containing the quantized transformation coefficients. The scan may be designed to place higher-energy (and therefore lower-frequency) transformation coefficients at the beginning of the vector and lower-energy (and therefore higher-frequency) transformation coefficients at the end. In some examples, the video encoder 200 may utilize a predefined scan order for scanning the quantized transformation coefficients to generate a serialized vector and then entropy-encode the quantized transformation coefficients of the vector. In other examples, the video encoder 200 may perform an adaptive scan. After scanning the quantized transformation coefficients to form a one-dimensional vector, the video encoder 200 may entropy-encode the one-dimensional vector, for example, according to context-adaptive binary arithmetic coding (CABAC). The video encoder 200 may also entropy-encode values ​​for syntax elements that describe metadata associated with the encoded video data for use by the video decoder 300 when decoding the video data.

[0050] To perform CABAC, the video encoder 200 may assign a context within a context model to the symbols to be transmitted. The context may relate, for example, to whether the symbol's adjacency values ​​are zero-valued. Probability decisions may be based on the context assigned to the symbols.

[0051] The video encoder 200 may further generate syntax data for the video decoder 300, such as block-based syntax data, picture-based syntax data, and sequence-based syntax data, in other syntax data such as a picture header, block header, slice header, or sequence parameter set (SPS), picture parameter set (PPS), or video parameter set (VPS). The video decoder 300 may similarly decode such syntax data to determine how to decode the corresponding video data.

[0052] Thus, the video encoder 200 can generate a bitstream containing encoded video data, for example, a bitstream containing syntax elements that describe the division of a picture into blocks (e.g., CUs) and predictive and / or residual information about the blocks. Finally, the video decoder 300 can receive the bitstream and decode the encoded video data.

[0053] Generally, the video decoder 300 decodes the encoded video data of the bitstream by performing a process that is the reverse of the process performed by the video encoder 200. For example, the video decoder 300 may decode values ​​for syntax elements of the bitstream using CABAC in a substantially similar, but reverse, manner to the CABAC encoding process of the video encoder 200. The syntax elements may define the CUs of the CTUs by defining partitioning information for partitioning the picture into CTUs, and partitioning each CTU according to a corresponding partitioning structure such as a QTBT structure. The syntax elements may further define prediction and residual information for blocks of video data (e.g., CUs).

[0054] Residual information may be represented, for example, by quantized transformation coefficients. The video decoder 300 may dequantize and inverse transform the quantized transformation coefficients of a block in order to reconstruct the residual block for the block. The video decoder 300 uses a signaled prediction mode (intra-prediction or inter-prediction) and associated prediction information (for example, motion information about inter-prediction) to form a prediction block for the block. The video decoder 300 may then synthesize the prediction block and the residual block (sample by sample) to reconstruct the original block. The video decoder 300 may perform additional processing, such as performing a deblocking process to reduce visual artifacts along the block boundaries.

[0055] This disclosure may generally refer to “signaling” certain information, such as syntax elements. The term “signaling” may generally refer to the communication of values ​​for syntax elements and / or other data used to decode the encoded video data. That is, the video encoder 200 may signal values ​​for syntax elements in the bitstream. In general, signaling refers to generating values ​​in the bitstream. As described above, the source device 102 may transport the bitstream to the destination device 116 in substantially real time, or not in real time, such as when storing the syntax elements in the storage device 112 for later retrieval by the destination device 116.

[0056] Figure 2 is a conceptual diagram illustrating the hybrid video coding framework. Video coding standards from H.261 onward are based on the so-called hybrid video coding principle shown in Figure 2. The term "hybrid" refers to a combination of two means for reducing redundancy in a video signal: transform coding with prediction and quantization of predictive residuals. Prediction and transform reduce redundancy in the video signal through decorrelation, while quantization reduces the data in the transformed coefficient representation by removing only details that are ideally irrelevant, thereby reducing their precision. This hybrid video coding design principle is also used in two recent standards, ITU-T H.265 / HEVC and ITU-T H.266 / VVC.

[0057] As shown in Figure 2, a modern hybrid video coder 130 typically performs block segmentation, motion compensation or interpicture prediction, intrapicture prediction, transformation, quantization, entropy coding, and post / in-loop filtering. In the example in Figure 2, the video coder 130 includes an adder unit 134, a transformer unit 136, a quantization unit 138, an entropy coding unit 140, an inverse quantization unit 142, an inverse transformer unit 144, an adder unit 146, a loop filter unit 148, a decoded picture buffer (DPB) 150, an intra-prediction unit 152, an inter-prediction unit 154, and a motion estimation unit 156.

[0058] Generally, when a video coder 130 encodes video data, it may receive input video data 132. Block partitioning is used to divide the received picture (image) of the video data into smaller blocks for the operation of the prediction and conversion processes. Early video coding standards used a fixed block size, typically 16x16 samples. Recent standards such as HEVC and VVC use a tree-based partitioning structure to perform flexible partitioning.

[0059] The motion estimation unit 156 and the inter-picture prediction unit 154 can predict the input video data 132 from, for example, previously decoded data of the DPB 150. Motion compensation or inter-picture prediction utilizes the redundancy that exists (and therefore "inter") between pictures in a video sequence. According to block-based motion compensation used in all modern video codecs, the prediction is taken from one or more previously decoded pictures, i.e., reference pictures. The corresponding area for generating the inter-picture prediction is indicated by motion information, which includes motion vectors and reference picture indices.

[0060] The addition unit 134 may calculate residual data as the difference between the input video data 132 and the predicted data from the intra-prediction unit 152 or the inter-prediction unit 154. The addition unit 134 provides the residual block to the transformation unit 136, which applies one or more transformations to the residual block to generate a transformation block. The quantization unit 138 quantizes the transformation block to form quantized transformation coefficients. The entropy coding unit 140 entropy encodes the quantized transformation coefficients, as well as other syntax elements such as motion information or intra-prediction information, to generate an output bitstream 158.

[0061] Meanwhile, to reconstruct the residual blocks, the inverse quantization unit 142 inverse quantizes the quantized transformation coefficients, and the inverse transformation unit 144 inverse transforms the transformation coefficients. The addition unit 146 combines the residual blocks with the prediction blocks (sample by sample) to generate decoded blocks of video data. The loop filter unit 148 applies one or more filters (for example, at least one of a neural network-based filter, a neural network-based loop filter, a neural network-based post-loop filter, an adaptive in-loop filter, or a predefined adaptive in-loop filter) to the decoded blocks to generate filtered and decoded blocks.

[0062] According to the techniques of the present disclosure, the neural network filtering unit of the loop filtering unit 148 may receive data for the decoded picture of the video data from the additive unit 146 and from one or more other units of the hybrid video coder 130, such as the transform unit 136, the quantization unit 138, the intra-prediction unit 152, the inter-prediction unit 154, the motion estimation unit 156, and / or one or more other filtering units within the loop filtering unit 148. For example, the neural network filtering unit may receive data from the deblocking filtering unit (also called the “deblocking unit”) of the loop filtering unit 148. The neural network filtering unit may receive, for example, a boundary intensity value that represents whether a particular boundary should be filtered for deblocking, and, if so, to what extent the boundary should be filtered. For example, the boundary intensity value may correspond to the number of samples on either side of the boundary to be modified and / or the extent to which the samples should be modified.

[0063] In other examples, in addition to or as an alternative to boundary intensity values, the neural network filtering unit may receive any or all of the following: coding unit (CU) segmental data, prediction unit (PU) segmental data, transformation unit (TU) segmental data, deblocking filtering data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture. The deblocking filtering data may further include one or more of whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking. The data representing the distance between the decoded picture and the reference picture may be represented as the POC difference between the picture order count (POC) values ​​of the picture.

[0064] A neural network filtering unit may determine one or more neural network models to be used to filter at least a portion of the decoded picture. The neural network filtering unit may further filter at least a portion of the decoded picture using the determined one or more neural network models and data including boundary intensity data from other units. For example, the neural network filtering unit may provide additional data as one or more additional input planes to a convolutional neural network (CNN).

[0065] Blocks of video data, such as CTU or CU, can actually contain multiple color components, for example, a luminance or "luma" component, a blue-hue chrominance or "chroma" component, and a red-hue chrominance (chroma) component. The luma component can have a greater spatial resolution than the chroma component, and one of the chroma components can have a greater spatial resolution than the other. Alternatively, the luma component can have a greater spatial resolution than the chroma component, and the two chroma components can have equal spatial resolution to each other. For example, in a 4:2:2 format, the luma component may be twice the size of the chroma component horizontally and equal in size vertically. As another example, in a 4:2:0 format, the luma component may be twice the size of the chroma component horizontally and vertically. The various behaviors described above can generally be applied individually to each of the luma and chroma components (however, some coding information, such as motion information or intra-prediction direction, may be determined for the luma component and inherited by the corresponding chroma component).

[0066] Figure 3 is a conceptual diagram showing a hierarchical prediction structure 166 using 16 picture group (GOP) sizes. In recent video codecs, a hierarchical prediction structure within picture groups (GOPs) is applied to improve coding efficiency.

[0067] Referring again to Figure 2, intra-picture prediction leverages the spatial redundancy present within the picture (and therefore "intra") by deriving predictions about blocks from already coded / decoded, spatially adjacent (reference) samples. Directional angle prediction, DC prediction, and plane or planar prediction are used in recent video codecs, including AVC, HEVC, and VVC.

[0068] Hybrid video coding standards apply a block transform to the predictive residuals (regardless of whether the predictive residuals originate from interpicture or intrapicture predictions). Early standards, including H.261, H.262, and H.263, use the discrete cosine transform (DCT). HEVC and VVC apply additional transform kernels other than the DCT to account for different statistics in a given video signal.

[0069] Quantization aims to reduce the precision of an input value or set of input values ​​in order to decrease the amount of data required to represent the value. In hybrid video coding, quantization is typically applied to individual transformed residual samples, i.e., to the transformation coefficients, resulting in integer coefficient levels. In recent video coding standards, the step size is derived from so-called quantization parameters (QPs) that control fidelity and bitrate. Larger step sizes reduce the bitrate but can also degrade quality, resulting in, for example, video pictures exhibiting blocking artifacts and blurred details.

[0070] Context-Adaptive Binary Arithmetic Coding (CABAC) is a form of entropy coding used in modern video codecs, such as AVC, HEVC, and VVC, due to its high efficiency.

[0071] Post- / in-loop filtering is a filtering process (or a combination of such processes) applied to a reconstructed picture to reduce coding artifacts. The input to the filtering process is typically a reconstructed picture, which is a combination of the reconstructed residual signal (including quantization errors) and the prediction. As shown in Figure 2, the reconstructed picture after in-loop filtering is stored and used as a reference for interpicture prediction of subsequent pictures. Coding artifacts are largely determined by QP, and therefore QP information is generally 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, adaptive loop filtering (ALF) was introduced as a third filter. The ALF filtering process is as follows:

number

number

number

[0072] Figure 4 is a conceptual diagram showing a neural network-based filter 170 with four layers. Various studies have shown that embedding neural networks (NNs) in the hybrid video coding framework, for example, Figure 2, can improve compression efficiency. Neural networks are used in intra-prediction and inter-prediction modules to improve prediction efficiency. In recent years, NN-based in-loop filtering has also become a noteworthy research topic. The filtering process is sometimes applied as post-loop filtering. In this case, the filtering process is applied only to the output picture, and the unfiltered picture is used as a reference picture.

[0073] In addition to existing filters such as deblocking filters, sample-adaptive offsets (SAO), and / or adaptive loop filtering (ALF), NN-based filters 170 may be applied. NN-based filters may also be applied exclusively if they are designed to replace all existing filters. As an addition or replacement, NN-based filters such as NN-based filter 170 may be designed to complement, enhance, or replace any or all of the other filters.

[0074] As shown in Figure 4, the NN-based filtering process may take the reconstructed sample as input, with the intermediate output being the residual sample, which is then added back to the input to refine the input sample. The NN filter may take all color components (e.g., Y, U, and V, or Y, Cb, and Cr, i.e., luminance, blue chrominance, and red chrominance) as input to leverage intercomponent correlations. Different components may share the same filter (including network structure and model parameters), or each component may have its own unique filter.

[0075] The filtering process can also be generalized as follows: R'(i,j)=R(i,j)+NN_filter_residual_ouput(R) The model structure and model parameters of a NN-based filter can be predefined and stored in the encoder and decoder. The filter can also be signaled in the bitstream.

[0076] The disclosure acknowledges that, in some cases, when a video codec (such as the video encoder 200 or video decoder 300 in Figure 1) applies neural network (NN)-based filtering as an additional module, the video codec may generate different kinds of information that can be used by NN-based filters to further improve filtering performance.

[0077] Generally, according to the techniques of the present disclosure, the video encoder 200 and the video decoder 300 may include respective filtering units configured to perform NN-based filtering. When the filtering unit performs the NN-based filtering process, it may use information generated by other units (e.g., block segmentation information, motion information, deblocking filter information, or other such information).

[0078] The filtering unit may use any information generated by other units or modules that is available when applying an NN filter. Examples of such units or modules that may generate information that can be used by the filtering unit include intra-prediction units, inter-prediction units, transformation units, quantization units, loop filtering units (e.g., deblocking filter units, sample-adaptive offset (SAO) units, adaptive loop filter (ALF) units, etc.), preprocessing units (e.g., motion-compensated time filtering units), and / or other NN-based modules or units that coexist with the NN filtering unit or module.

[0079] The video encoder 200 and / or video decoder 300 may include multiple NN-based filtering units, for example, as shown in Figure 4, one of which performs NN-based filtering before another (current) NN-based filtering unit. In such a case, the current NN-based filtering unit may use information generated by one or more previous NN-based filtering units when performing NN filtering.

[0080] An NN-based filtering unit, in various examples, may use any or all of the following information when performing NN-based filtering: partition information for CU, PU, ​​and / or TU; deblocking filtering information (e.g., boundary intensity values ​​for the deblocking filtering process, long or short filters, strong or weak filters, etc.); quantization parameters (QP) used for the current picture / block and / or reference picture; intra and / or interprediction mode information; the distance between the current picture and the reference picture used to predict the current picture (e.g., the difference in Picture Order Count (POC) values); and / or coded block motion information. Boundary intensity values ​​are sometimes called boundary filtering intensity. Generally, boundary intensity values ​​or boundary filtering intensity values ​​may represent whether a particular block boundary should be deblocked and, if so, the degree of deblocking that should be applied. For example, a relatively strong deblocking filter may modify more values ​​of samples on both sides of a block boundary to a greater extent than a relatively weak deblocking filter.

[0081] In some examples, when an NN-based filtering unit uses information from other units or modules, the NN-based filtering unit may provide some similar functionality provided by those other units or modules. In such examples, the NN-based filtering unit may modify elements of the other units or modules to improve cooperation between the NN-based filtering unit and the other units or modules. For example, the NN-based filtering unit may interface with a deblocking filter. In such an example, the deblocking filter unit may generate boundary intensity information but not perform the actual filtering. The NN-based filtering unit may receive boundary intensity information from the deblocking filter unit and provide the received boundary intensity information as input to the NN-based filter.

[0082] An NN-based filtering unit can use information received from other units or modules in various ways. For example, an NN-based filtering unit can use the information as an additional input plane to a convolutional neural network (CNN). As another example, an NN-based filtering unit can use the information to modify or adjust the output of an NN-based filter. For example, after applying an NN-based filter to a picture to form a filtered picture, the video encoder 200 or video decoder 300 can further adjust the filtered picture based on other information such as QP.

[0083] Information from other units or modules may be transformed to better suit the NN-based filtering unit. For example, the NN-based filtering unit may convert values ​​between integer and floating-point values, scale values ​​to a range better suited to the NN filter (for example, the boundary intensity values ​​of the deblocking filter may be scaled to the same range as the input pixels), or scale values ​​to any other range (the range may be predefined or signaled in the bitstream).

[0084] Figure 5 is a conceptual diagram showing an exemplary portion of picture 180, including boundaries, boundary samples, and internal samples. In detail, the portion of picture 180 includes vertical boundaries 182A-182D (vertical boundary 182) and horizontal boundaries 184A-184C (horizontal boundary 184). As shown in the example in Figure 5, two adjacent boundary samples (marked "N" in Figure 5 and shaded in gray) define the respective boundaries 182 and 184 between the two boundary samples (represented by solid black lines in Figure 5). Internal (i.e., non-boundary) samples are marked "M" in Figure 5 and are unshaded. Boundaries can be CU boundaries, PU boundaries, and / or TU boundaries. An NN-based filtering unit may use the internal sample / boundary sample and boundary location information shown in Figure 5 when performing NN-based filtering.

[0085] For example, a NN-based filtering unit may use the partition information of CU, PU, ​​and TU as one or more additional input planes to a CNN-based filter. First, the video encoder 200 and / or video decoder 300 may convert the partition information (about CU, PU, ​​and / or TU) into a plane by setting the boundary samples to a different value (e.g., a predefined value N) from the internal samples (e.g., M), as shown in Figure 5. In one example, the video encoder 200 and video decoder 300 may set the values ​​N=1 and M=0.

[0086] The video encoder 200 and video decoder 300 may generate multiple partitioning planes, for example, one each for the CU partition, PU partition, and / or TU partition. In some examples, a plane, for example, one for the CU partition and another for the PU and TU partitions, may be combined. Different color components may have different partitioning planes when a “dual-tree” partitioning is enabled, where the lumen and chroma components may be partitioned differently (and / or two chroma components may be partitioned differently from each other). A NN-based filter may use any or all of these various planes as input planes to a CNN-based filter. Various examples of dealing with multiple partitioning planes include using the partitioning planes as separate input planes to a CNN-based filter, and combining multiple partitioning planes into a single plane (for example, for each pixel sample at position (i,j)). combined (i,j)=MAX(Plane a (i,j),Plane bThis includes (i,j), ...), or combinations of separate piecewise planes and / or combined piecewise planes (for example, combining the CU and TU piecewise planes for each color component into a single plane, and using multiple combined planes for each color as inputs to a CNN-based filter). That is, in one example, in order to combine planes to form a combined input plane, for each input plane position (i,j), the video encoder 200 and video decoder 300 may set the value of the combined input plane position (i,j) to be equal to the maximum value at multiple input plane positions (i,j).

[0087] After creating a plane, the values ​​of the plane may be transformed as needed in various examples before being used as input to a CNN-based filter. For example, the values ​​may be converted between integers and floating points, scaled to have the same range as the input pixel values, and / or scaled to any other range that may be predefined or signaled in the bitstream.

[0088] As described above, in some examples, the boundary strength calculation logic of a deblocking filter can be used to derive boundary strength parameters. NN-based filtering units can use the boundary strength parameters as an additional input plane to CNN-based filters (e.g., VVC boundary strength calculation for a DB filter). When a CNN filter is applied, the actual filtering process of the deblocking filter may be disabled.

[0089] First, the deblocking filtering unit may derive boundary intensity values ​​for edges that are eligible for deblocking filtering. Transformations may be applied as needed for each example of the techniques of this disclosure (e.g., conversion between integer and floating-point types, scaling values ​​to have the same range as the input pixels or any other range deemed suitable for the CNN filter to be used, etc.).

[0090] The NN-based filter processing unit, or another unit of the video codec, can convert the boundary strength values into a plane that can be used together with other input planes as an input to the CNN-based filter. An example of such a conversion is the same as the conversion described above with respect to FIG. 5, where boundary samples may be set to the boundary strength values and non-boundary samples may be set to 0. In the case of VVC, the range of boundary samples is [0, 2].

[0091] Since the boundary strengths of different color components can be calculated separately, the horizontal and vertical boundaries can also be calculated separately. For a picture or a coded region, a plurality of boundary strength planes can be generated. Similar to the above description, in one example, the NN-based filter processing unit can choose to use a single input plane or multiple input planes. When multiple planes are used, different methods can be applied to organize the planes. Some examples include using the planes as separate input planes to the CNN-based filter, combining multiple boundary strength planes into one plane, or a combination of these examples.

[0092] As an example of combining two planes, for each sample position (i, j), Plane combined (i, j) = MAX(Plane A (i, j), Plane B (i, j)). As another example, given two planes A and B, Plane combined (i, j) = Plane A (i, j) + Plane B (i, j). As another example, given two planes A and B, assuming R B is the range of values in plane B, for each sample position (i, j), Plane combined (i, j) = R B * Plane A (i, j) + Plane B (i, j). In this example, the effect is mainly due to Plane A and Plane BThis can be considered equivalent to using it as a smelter. The techniques described above can be applied multiple times to synthesize three or more planes. Also, the techniques described above can be used at different stages. For example, with planes A, B, and C, one of the techniques described above can be used to obtain the composite plane AB, and then the other technique can be used to synthesize AB with C to obtain ABC.

[0093] To combine the techniques described above, in one example, the boundary intensity planes of the vertical and horizontal planes may be synthesized using one of the various techniques described above, and then the boundary intensity planes of different color components may be provided to a CNN-based filter as separate input planes. As described above, the plane values ​​may be transformed as needed (e.g., conversion between integers and floating points and / or scaling to a specific range that can be predefined or signaled in the bitstream).

[0094] In some examples, information about long / short filters can be used as an additional or alternative input plane to a CNN-based filter. Similar to using boundary strength, information may be generated about which CNN-based filter to use, whether to use a long or short deblocking filter, and multiple planes can be used as separate planes or synthesized before being used as CNN filter inputs.

[0095] In some examples, strong / weak filter information can be used as an additional or alternative input plane to a CNN-based filter. Similar to using boundary strength, information may be generated about which CNN-based filter to use, whether to use a strong or weak deblocking filter, and multiple planes can be used as separate planes or combined before being used as CNN filter inputs.

[0096] The various techniques described above can be combined in various ways. For example, the following planes may be generated and used in a CNN filtering process: boundary strength (value range: 0, 1, 2), long / short and strong / weak filters (value: 2 for long & strong filters, 1 for short & strong filters, 0 for short & weak filters (in VVC, the strong filter condition must be met in order to have a long filter)). As with the other examples described above, the generated planes may be used as separate input planes to the CNN filter, or some / all of the planes may be combined together.

[0097] Downsampling / upsampling may occur to feed a picture or coded region into a CNN filter. For example, lumern and chroma components have different resolutions in YUV420, YUV422 color format video, etc. In this case, downsampling / upsampling of the color components may be necessary to create an input plane for the CNN filter. Some techniques include upsampling the chroma component to have the same resolution as the lumern component, downsampling the lumern component to have the same resolution as the chroma component, or converting one lumern pixel plane into several smaller pixel planes that have the same size as the chroma plane.

[0098] When downsampling / upsampling of a color plane is required, the corresponding information plane introduced in this disclosure may also be downsampled / upsampled. Downsampling / upsampling can follow the same rules as the corresponding pixel plane. For example, when converting one lumen pixel plane to several smaller pixel planes to match the size with chroma, the video encoder 200 or video decoder 300 may maintain only one downsampled plane instead of maintaining the entire plane as the lumen pixel does.

[0099] Figure 6 is a block diagram showing an exemplary video encoder 200 capable of performing the techniques of this disclosure. Figure 6 is provided for illustrative purposes and should not be considered a limitation of the techniques that are more broadly illustrated and described in this disclosure. For illustrative purposes, this disclosure describes the video encoder 200 in the context of video coding standards such as the ITU-T H.265 / HEVC video coding standard and the VVC video coding standard under development. However, the techniques of this disclosure are not limited to these video coding standards and are generally applicable to other video coding and decoding standards.

[0100] In the example in Figure 6, the video encoder 200 includes a video data memory 230, a mode selection unit 202, a residual generation unit 204, a conversion processing unit 206, a quantization unit 208, an inverse quantization unit 210, an inverse conversion processing unit 212, a reconstruction unit 214, a filter unit 216, a decoded picture buffer (DPB) 218, and an entropy coding unit 220. Any or all of the video data memory 230, mode selection unit 202, residual generation unit 204, conversion processing unit 206, quantization unit 208, inverse quantization unit 210, an inverse conversion processing unit 212, a reconstruction unit 214, a filter unit 216, a DPB 218, and an entropy coding unit 220 may be implemented in one or more processors or processing circuits. For example, the units of the video encoder 200 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. Furthermore, the video encoder 200 may include additional or alternative processors or processing circuits to perform these and other functions.

[0101] The video data memory 230 can store video data to be encoded by the components of the video encoder 200. The video encoder 200 can receive video data stored in the video data memory 230 from, for example, a video source 104 (Figure 1). The DPB 218 can act as a reference picture memory that stores reference video data for use in predicting subsequent video data by the video encoder 200. The video data memory 230 and DPB 218 can be formed by any of various memory devices, such as dynamic random access memory (DRAM) including synchronous DRAM (SDRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM), or other types of memory devices. The video data memory 230 and DPB 218 can be provided by the same memory device or separate memory devices. In various examples, the video data memory 230 may be on-chip with the other components of the video encoder 200, as shown in the figure, or it may be off-chip relative to those components.

[0102] In this disclosure, references to the video data memory 230 should not be interpreted as being limited to internal memory of the video encoder 200, or external memory of the video encoder 200, unless otherwise specifically described. Rather, references to the video data memory 230 should be understood as reference memory that stores video data received by the video encoder 200 for encoding (e.g., video data for the current block to be encoded). Memory 106 in Figure 1 may also provide temporary storage for outputs from various units of the video encoder 200.

[0103] The various units in Figure 6 are illustrated to help understand the operations performed by the video encoder 200. The units may be implemented as fixed-function circuits, programmable circuits, or a combination thereof. Fixed-function circuits refer to circuits that provide a specific function and are preset for the operations they may perform. Programmable circuits refer to circuits that can be programmed to perform a variety of tasks and offer flexible functionality in the operations they may perform. For example, a programmable circuit may execute software or firmware that operates the programmable circuit in a manner defined by software or firmware instructions. Fixed-function circuits may execute software instructions (e.g., to receive or output parameters), but the type of operation performed by a fixed-function circuit is generally immutable. In some examples, one or more units may be different circuit blocks (fixed-function or programmable), and in some examples, one or more units may be integrated circuits.

[0104] The video encoder 200 may include a programmable core formed from an arithmetic logic unit (ALU), an elementary function unit (EFU), digital circuits, analog circuits, and / or programmable circuits. In an example where the operation of the video encoder 200 is performed using software executed by the programmable circuits, memory 106 (Figure 1) may store instructions (e.g., object code) of the software that the video encoder 200 receives and executes, or another memory (not shown) within the video encoder 200 may store such instructions.

[0105] The video data memory 230 is configured to store the received video data. The video encoder 200 can retrieve a picture of the 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 may be raw video data to be encoded.

[0106] 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 additional functional units for performing 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.

[0107] The mode selection unit 202 generally coordinates multiple coding paths to test combinations of coding parameters and the resulting rate distortion (RD) values ​​for such combinations. The coding parameters may include the division of the CTU to the CU, the prediction mode for the CU, the transformation type for the residual data of the CU, and quantization parameters for the residual data of the CU. The mode selection unit 202 may ultimately select a combination of coding parameters that has a better rate distortion value than other tested combinations.

[0108] The video encoder 200 divides the picture retrieved from the video data memory 230 into a series of CTUs, and may encapsulate one or more CTUs within a slice. The mode selection unit 202 may divide the picture's CTUs according to a tree structure such as the HEVC QTBT structure or quadtree structure described above. As described above, the video encoder 200 may form one or more CUs from dividing the CTUs according to the tree structure. Such CUs are sometimes commonly referred to as "video blocks" or "blocks".

[0109] In general, the mode selection unit 202 also controls its components (e.g., motion estimation unit 222, motion compensation unit 224, and intra-prediction unit 226) to generate a predictive block for the current block (e.g., the current CU, or in HEVC, the overlapping portion of PU and TU). For intra-prediction of the current block, the motion estimation unit 222 may perform a motion search to identify one or more exactly matching reference blocks in one or more reference pictures (e.g., one or more previously coded pictures stored in DPB 218). Specifically, the motion estimation unit 222 may calculate a value representing how similar a potential reference block is to the current block, for example, according to the sum of absolute differences (SAD), sum of squared differences (SSD), mean absolute difference (MAD), mean squared difference (MSD), etc. The motion estimation unit 222 may generally perform these calculations using sample-by-sample differences between the current block and the reference blocks under consideration. The motion estimation unit 222 can identify the reference block with the lowest value resulting from these calculations, which indicates the reference block that most closely matches the current block.

[0110] 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 the position of the current block in the current picture. The motion estimation unit 222 may then provide the motion vectors to the motion compensation unit 224. For example, in the case of unidirectional interpretation, the motion estimation unit 222 may provide a single motion vector, but in the case of bidirectional interpretation, the motion estimation unit 222 may provide two motion vectors. The motion compensation unit 224 may then use the motion vectors to generate predicted blocks. For example, the motion compensation unit 224 may use the motion vectors to extract data for the reference blocks. As another example, if the motion vectors have fractional sample accuracy, the motion compensation unit 224 may interpolate values ​​for the predicted blocks according to one or more interpolation filters. Furthermore, in the case of bidirectional interpretation, the motion compensation unit 224 may extract data for the two reference blocks identified by each motion vector and synthesize the extracted data, for example, by sample-wise averaging or weighted averaging.

[0111] As another example, in the case of intra-prediction or intra-prediction coding, the intra-prediction unit 226 may generate a prediction block from samples adjacent to the current block. For example, in directional mode, the intra-prediction unit 226 may generally generate a prediction block by mathematically synthesizing the values ​​of adjacent samples and populating these calculated values ​​in a defined direction across the current block. As another example, in DC mode, the intra-prediction unit 226 may calculate the average of adjacent samples for the current block and generate a prediction block in which each sample of the prediction block should include this resulting average.

[0112] The mode selection unit 202 provides the prediction block to the residual generation unit 204. The residual generation unit 204 receives a raw, uncoded version of the current block from the video data memory 230 and 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 the residual block for the current block. In some examples, the residual generation unit 204 may also determine the difference between sample values ​​in the residual block to generate the residual block using residual difference 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.

[0113] In an example where the mode selection unit 202 divides a CU into PUs, each PU may be associated with a lumar prediction unit and a corresponding chroma prediction unit. The video encoder 200 and video decoder 300 may support PUs of various sizes. As shown above, the size of a CU may refer to the size of the lumar coding block of the CU, and the size of a PU may refer to the size of the lumar prediction unit of the PU. Assuming that the size of a particular CU is 2N × 2N, the video encoder 200 may support PU sizes of 2N × 2N or N × N for intra-prediction, and symmetric PU sizes of 2N × 2N, 2N × N, N × 2N, N × N, or similar for inter-prediction. The video encoder 200 and video decoder 300 may also support asymmetric divisions for PU sizes of 2N × nU, 2N × nD, nL × 2N, and nR × 2N for inter-prediction.

[0114] In cases where the mode selection unit 202 does not further subdivide the CU into PUs, each PU may be associated with a ruma coding block and a corresponding chroma coding block. As described above, the size of the CU may refer to the size of the ruma coding block within the CU. The video encoder 200 and video decoder 300 may support CU sizes of 2N×2N, 2N×N, or N×2N.

[0115] In some examples, such as intra-block copy mode coding, affine mode coding, and other video coding techniques like linear model (LM) mode coding, the mode selection unit 202 generates a predicted block for the current block being coded via the respective unit associated with the coding technique. In some examples, such as palette mode coding, the mode selection unit 202 does not need to generate a predicted block; instead, it may generate syntax elements indicating how to reconstruct the block based on the selected palette. In such modes, the mode selection unit 202 may provide these syntax elements to be coded to the entropy coding unit 220.

[0116] As described above, the residual generation unit 204 receives video data for the current block and the corresponding predicted 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 predicted block and the current block.

[0117] The transformation processing unit 206 applies one or more transformations to the residual block to generate a block of transformation coefficients (referred to herein as the “transformation coefficient block”). The transformation processing unit 206 may apply various transformations to the residual block to form the transformation coefficient block. For example, the transformation processing unit 206 may apply a discrete cosine transform (DCT), a direction transform, a Carunenlobe transform (KLT), or a conceptually similar transformation to the residual block. In some examples, the transformation processing unit 206 may perform multiple transformations on the residual block, such as a rotation transform, a linear transformation, and a quadratic transformation. In some examples, the transformation processing unit 206 does not apply any transformations to the residual block.

[0118] The quantization unit 208 can quantize the transformation coefficients in the transformation coefficient block to produce a quantized transformation coefficient block. The quantization unit 208 can quantize the transformation coefficients of the transformation coefficient block according to the quantization parameter (QP) value associated with the current block. The video encoder 200 can adjust the degree of quantization applied to the transformation coefficient block associated with the current block by adjusting the QP value associated with the CU (for example, via the mode selection unit 202). Quantization may result in a loss of information, and therefore the quantized transformation coefficients may have lower precision than the original transformation coefficients generated by the transformation processing unit 206.

[0119] The inverse quantization unit 210 and the inverse transformation processing unit 212 can reconstruct the residual block from the transformed coefficient block by applying inverse quantization and inverse transformation, respectively. The reconstruction unit 214 can generate a reconstructed block corresponding to the current block (which may be with some distortion) based on the reconstructed residual block and the predicted block generated by the mode selection unit 202. For example, the reconstruction unit 214 can generate a reconstructed block by adding a sample from the reconstructed residual block to a corresponding sample from the predicted block generated by the mode selection unit 202.

[0120] The filter unit 216 may perform one or more filtering operations on the reconfigured block. For example, the filter unit 216 may perform a deblocking operation to reduce blocking artifacts along the edges of the CU. When performing a deblocking operation, the filter unit 216 (or its deblocking filter unit) may first calculate boundary intensity values. The deblocking filter unit of the filter unit 216 may then use the boundary intensity values ​​to represent coefficients that should generally be used for filtering intensity and deblocking functions and / or deblocking decision functions. C Other deblocking parameters, such as beta (β), can also be determined. The operation of filter unit 216 may be skipped in some examples.

[0121] The filter unit 216 may be configured to perform various techniques of the Disclosure, for example, to determine one or more of the neural network models (NN models) 232 that should be used to filter the decoded picture and / or to determine whether to apply NN model filtering. The mode selection unit 202 may perform an RD calculation using both the filtered and unfiltered pictures to determine the RD cost for determining whether to perform NN model filtering, and then provide the entropy coding unit 220 with data representing, for example, whether to perform NN model filtering, one or more of the NN models 232 that should be used for the current picture, etc.

[0122] In detail, the filter unit 216 may receive the decoded (reconstructed) picture from the reconstruction unit 214. The filter unit 216 may also acquire (e.g., receive) additional data from one or more other units, such as the mode selection unit 202, the motion estimation unit 222, the motion compensation unit 224, the intra prediction unit 226, the transformation processing unit 206, the quantization unit 208, and other filtering units (e.g., separate from or contained within the filter unit 216). For example, the filter unit 216 may perform both NN-based filtering and other types of filtering such as deblocking filtering, SAO filtering, and ALF filtering. Thus, the filter unit 216 may acquire deblocking parameters for blocking the current picture, such as boundary intensity values. The filter unit 216 may provide boundary intensity values ​​(and / or other received data) to the NN filtering unit of the filter unit 216.

[0123] The NN filtering unit may use additional data (e.g., boundary intensity values ​​and / or other data received from other units of the video encoder 200) to select an NN model from NN model 232 to be used to perform NN-based filtering, and then perform the actual NN-based filtering. For example, the NN filtering unit of filter unit 216 may provide the additional data (e.g., boundary intensity values) to one or more selected NN models from NN model 232 in the form of an additional input layer. In some examples, filter unit 216 may modify the additional data, for example, by converting the representation format (e.g., between floating-point and decimal) or by changing the range of additional values ​​to correspond to the input sample range.

[0124] The video encoder 200 stores the reconstructed blocks in the DPB 218. For example, in cases where the operation of the filter unit 216 is not required, the reconstruction unit 214 may store the reconstructed blocks in the DPB 218. In cases where the operation of the filter unit 216 is required, the filter unit 216 may store the filtered and reconstructed blocks in the DPB 218. The motion estimation unit 222 and the motion compensation unit 224 may retrieve a reference picture formed from the reconstructed (and possibly filtered) blocks from the DPB 218 to interpret blocks of the picture to be encoded later. In addition, the intraprediction unit 226 may use the reconstructed blocks in the DPB 218 of the current picture to intrapret other blocks in the current picture.

[0125] In general, the entropy coding unit 220 can entropy code syntax elements received from other functional components of the video encoder 200. For example, the entropy coding unit 220 can entropy code quantized transformation coefficient blocks from the quantization unit 208. As another example, the entropy coding unit 220 can entropy code prediction syntax elements from the mode selection unit 202 (e.g., motion information for inter-prediction or intra-mode information for intra-prediction). The entropy coding unit 220 can perform one or more entropy coding operations on syntax elements, which are another example of video data, to generate entropy coded data. For example, the entropy coding unit 220 may perform context-adaptive variable-length coding (CAVLC) operation, CABAC operation, variable-to-variable (V2V) length coding operation, syntax-based context-adaptive binary arithmetic coding (SBAC) operation, probability interval partitioned entropy (PIPE) coding operation, exponential Golomb 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 in which syntax elements are not entropically coded.

[0126] The video encoder 200 may output a bitstream containing entropy-encoded syntax elements required to reconstruct a slice or block of a picture. Specifically, the entropy encoding unit 220 may output a bitstream.

[0127] The behavior described above is described in relation to blocks. Such descriptions should be understood as behavior for rumacoding blocks and / or chromacoding blocks. As described above, in some examples, the rumacoding block and chromacoding block are the ruma and chroma components of the CU. In some examples, the rumacoding block and chromacoding block are the ruma and chroma components of the PU.

[0128] In some cases, actions performed for a rumacoding block do not need to be repeated for a chromacoding block. For example, actions to identify the motion vector (MV) and reference picture for a rumacoding block do not need to be repeated to identify the MV and reference picture for a chromacoding block. Rather, the MV for the rumacoding block may be scaled to determine the MV for the chromacoding block, and the reference picture may be the same. In another example, the intra-prediction process may be the same for both rumacoding and chromacoding blocks.

[0129] Figure 7 is a block diagram showing an exemplary video decoder 300 capable of performing the techniques of this disclosure. Figure 7 is provided for illustrative purposes and is not intended to limit the techniques that are broadly illustrated and described in this disclosure. For illustrative purposes, this disclosure describes a video decoder 300 using VVC and HEVC (ITU-T H.265) techniques. However, the techniques of this disclosure may be performed by video coding devices configured according to other video coding standards.

[0130] In the example in Figure 7, 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 transformation processing unit 308, a reconstruction unit 310, a filter unit 312, and a decoded picture buffer (DPB) 314. Any or all of the CPB memory 320, entropy decoding unit 302, prediction processing unit 304, inverse quantization unit 306, inverse transformation processing unit 308, reconstruction unit 310, filter unit 312, and DPB 314 may be implemented in one or more processors or 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. Furthermore, the video decoder 300 may include additional or alternative processors or processing circuits to perform these and other functions.

[0131] The prediction processing unit 304 includes a motion compensation unit 316 and an intra-prediction unit 318. The prediction processing unit 304 may include additional units for performing predictions according to other prediction modes. For example, the prediction processing unit 304 may include a pallet unit, an intra-block copy unit (which may form part of the motion compensation unit 316), an affine unit, a linear model (LM) unit, and the like. In other examples, the video decoder 300 may include more, fewer, or different functional components.

[0132] The CPB memory 320 may store video data, such as an encoded video bitstream, to be decoded by the components of the video decoder 300. The video data stored in the CPB memory 320 may be retrieved, for example, from a computer-readable medium 110 (Figure 1). The CPB memory 320 may include a CPB that stores encoded video data (e.g., syntax elements) from the encoded video bitstream. The CPB memory 320 may also store video data other than syntax elements of the encoded picture, such as temporary data representing outputs from various units of the video decoder 300. The DPB 314 generally stores the decoded picture, which the video decoder 300 may output and / or use as reference video data when decoding subsequent data or pictures from the encoded video bitstream. The CPB memory 320 and DPB 314 may be formed by any of a variety of memory devices, such as dynamic random access memory (DRAM) including synchronous DRAM (SDRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM), or other types of memory devices. The CPU memory 320 and DPB 314 may be provided by the same memory device or by separate memory devices. In various examples, the CPB memory 320 may be on-chip together with the other components of the video decoder 300, or it may be off-chip relative to those components.

[0133] As an addition or alternative, in some examples, the video decoder 300 may retrieve coded video data from memory 120 (Figure 1). That is, memory 120 may store data as described above with respect to the CPB memory 320. Similarly, memory 120 may store instructions to be executed by the video decoder 300 when some or all of the functions of the video decoder 300 are implemented in software to be executed by the processing circuit of the video decoder 300.

[0134] The various units shown in Figure 7 are illustrated to help understand the operations performed by the video decoder 300. The units may be implemented as fixed-function circuits, programmable circuits, or a combination thereof. Similar to Figure 6, fixed-function circuits refer to circuits that provide a specific function and are preset for the operations they may perform. Programmable circuits refer to circuits that can be programmed to perform various tasks and offer flexible functionality in the operations they may perform. For example, a programmable circuit may execute software or firmware that operates the programmable circuit in a manner defined by software or firmware instructions. Fixed-function circuits may execute software instructions (e.g., to receive or output parameters), but the type of operation performed by a fixed-function circuit is generally immutable. In some examples, one or more units may be different circuit blocks (fixed-function or programmable), and in some examples, one or more units may be integrated circuits.

[0135] The video decoder 300 may include a programmable core formed from an ALU, EFU, digital circuitry, analog circuitry, and / or programmable circuitry. In an example where the operation of the video decoder 300 is performed by software running on the programmable circuitry, on-chip memory or off-chip memory may store software instructions (e.g., object code) that the video decoder 300 receives and executes.

[0136] The entropy decoding unit 302 can receive video data encoded from the CPB and reconstruct the syntax elements by entropy decoding the video data. The prediction processing unit 304, the inverse quantization unit 306, the inverse transformation processing unit 308, the reconstruction unit 310, and the filter unit 312 can generate the decoded video data based on the syntax elements extracted from the bitstream.

[0137] Generally, the video decoder 300 reconstructs the picture block by block. The video decoder 300 can perform the reconstruction operation individually for each block (where the block currently being reconstructed, i.e., decoded, is sometimes called the "current block").

[0138] The entropy decoding unit 302 can entropy decode the quantized transformation coefficients of the quantized transformation coefficient block, as well as syntax elements that define transformation information such as quantization parameters (QP) and / or transformation mode indications. The inverse quantization unit 306 may use the QP associated with the quantized transformation coefficient block to determine the degree of quantization and, similarly, the degree of inverse quantization that the inverse quantization unit 306 should apply. The inverse quantization unit 306 may, for example, perform a bitwise left shift operation to inverse quantize the quantized transformation coefficients. The inverse quantization unit 306 may thereby form a transformation coefficient block containing the transformation coefficients.

[0139] After the inverse quantization unit 306 has formed a transformation coefficient block, the inverse transformation processing unit 308 may apply one or more inverse transformations to the transformation coefficient block to generate a residual block associated with the current block. For example, the inverse transformation processing unit 308 may apply an inverse DCT, an inverse integer transformation, an inverse Carunenlebe transform (KLT), an inverse rotation transform, an inverse direction transform, or another inverse transformation to the transformation coefficient block.

[0140] Furthermore, the prediction processing unit 304 generates prediction blocks according to the prediction information syntax elements entropy-decoded by the entropy decoding unit 302. For example, if the prediction information syntax elements indicate that the current block is interpredicted, the motion compensation unit 316 may generate a prediction block. In this case, the prediction information syntax elements may indicate a reference picture in the DPB 314 from which the reference block should be extracted, as well as a motion vector that identifies the location of the reference block in the reference picture relative to the location of the current block in the current picture. The motion compensation unit 316 can generally perform the interprediction process in substantially the same manner as described with respect to the motion compensation unit 224 (Figure 6).

[0141] As another example, if the prediction information syntax element indicates that the current block is intra-predicted, the intra-prediction unit 318 may generate a predicted block according to the intra-prediction mode indicated by the prediction information syntax element. Again, the intra-prediction unit 318 may generally perform the intra-prediction process in substantially the same manner as described with respect to the intra-prediction unit 226 (Figure 6). The intra-prediction unit 318 may retrieve adjacent sample data for the current block from the DPB 314.

[0142] The reconstruction unit 310 may reconstruct the current block using the predicted block and the residual block. For example, the reconstruction unit 310 may reconstruct the current block by adding a sample from the residual block to the corresponding sample from the predicted block.

[0143] The filter unit 312 may perform one or more filtering operations on the reconstructed block. For example, the filter unit 312 may perform a deblocking operation to reduce blocking artifacts along the edges of the reconstructed block. The operations of the filter unit 312 are not necessarily performed in all examples. For example, the video decoder 300 may explicitly or implicitly decide whether to use the NN model 322 to perform neural network model filtering using, for example, one or all of the various techniques described herein. Furthermore, the video decoder 300 may explicitly or implicitly decide one or more of the NN models 322 and / or grid size for the current picture to be decoded and filtered. Thus, when filtering is switched on, the filter unit 312 may use one or more of the NN models 322 to filter a portion of the current decoded picture.

[0144] In some examples, the filter unit 312 may perform a deblocking operation to reduce blocking artifacts along the edges of the CU, PU, ​​or TU. When performing a deblocking operation, the filter unit 312 (or its deblocking filter unit) may first calculate boundary intensity values. The deblocking filter unit of the filter unit 312 may then use the boundary intensity values ​​to represent coefficients that should generally be used for filtering intensity and the deblocking function and / or deblocking decision function. C Other deblocking parameters, such as beta (β), can also be determined. The operation of filter unit 312 may be skipped in some examples.

[0145] The filter unit 312 may be configured to perform various techniques of the Disclosure, for example, to determine one or more of the neural network models (NN models) 322 that should be used to filter the decoded picture and / or to determine whether to apply NN model filtering. The entropy decoding unit 302 may decode data indicating whether to perform boundary filtering on a particular picture, slice, tile, or block of other units.

[0146] The filter unit 312 may receive the decoded (reconstructed) picture from the reconstruction unit 310. The filter unit 312 may also acquire (e.g., receive) additional data from one or more other units, such as the prediction processing unit 304, the motion compensation unit 316, the intra-prediction unit 318, the inverse transformation processing unit 308, the inverse quantization unit 306, and other filtering units (e.g., separate from or contained within the filter unit 312). For example, the filter unit 312 may perform both NN-based filtering and other types of filtering such as deblocking filtering, SAO filtering, and ALF filtering. Thus, the filter unit 312 may acquire deblocking parameters for blocking the current picture, such as boundary intensity values. The filter unit 312 may provide boundary intensity values ​​(and / or other received data) to the NN filtering unit of the filter unit 312.

[0147] The NN filtering unit may use additional data (e.g., boundary intensity values ​​and / or other data received from other units of the video decoder 300) to select an NN model from NN model 322 to be used to perform NN-based filtering, and then perform the actual NN-based filtering. For example, the NN filtering unit of filter unit 312 may provide the additional data (e.g., boundary intensity values) to one or more selected NN models from NN model 322 in the form of an additional input layer. In some examples, filter unit 312 may modify the additional data, for example, by converting the representation format (e.g., between floating-point and decimal) or by changing the range of additional values ​​to correspond to the input sample range.

[0148] The video decoder 300 may store the reconstructed (and filtered) blocks in the DPB 314. For example, in an example where the filter unit 312 does not operate, the reconstruction unit 310 may store the reconstructed blocks in the DPB 314. In an example where the filter unit 312 operates, the filter unit 312 may store the refined, filtered, and reconstructed blocks in the DPB 314. As described above, the DPB 314 may provide the prediction processing unit 304 with reference information such as the current picture for intra-prediction and samples of previously decoded pictures for subsequent motion compensation. Furthermore, the video decoder 300 may output the decoded pictures from the DPB 314 for later presentation on a display device such as the display device 118 in Figure 1.

[0149] Figure 8 is a flowchart illustrating an exemplary method for encoding the current block using the technique of this disclosure. The current block may include the current CU. While the video encoder 200 (Figures 1 and 3) is described, it should be understood that other devices may be configured to perform a similar method to that shown in Figure 8.

[0150] In this example, the video encoder 200 first predicts the current block (350). For example, the video encoder 200 may form a predicted block for the current block. The video encoder 200 may then compute the residual block for the current block (352). To compute the residual block, the video encoder 200 may compute the difference between the original uncoded block and the predicted block for the current block. The video encoder 200 may then transform and quantize the coefficients of the residual block (354). The video encoder 200 may then scan the quantized transformed coefficients of the residual block (356). During or following the scan, the video encoder 200 may entropy encode the coefficients (358). For example, the video encoder 200 may encode the coefficients using CAVLC or CABAC. The video encoder 200 may then output the entropy encoded data of the block (360).

[0151] The video encoder 200 may also encode the current block and then decode the current block to use the decoded version of the current block as reference data for data to be coded later (for example, in inter-prediction mode or intra-prediction mode). Thus, the video encoder 200 may inversely quantize and inversely transform the coefficients to reconstruct the residual block (362). The video encoder 200 may combine the residual block with the prediction block to form a decoded block (364). The video encoder 200 may thus decode all blocks of the current picture to form a fully decoded picture. The video encoder 200 may further filter the decoded picture, including the decoded blocks, according to any of the various techniques of this disclosure (366). The video encoder 200 may then store the decoded picture in the DPB 218 (368).

[0152] Figure 9 is a flowchart illustrating an exemplary method for decoding the current block using the technique of this disclosure. The current block may include the current CU. While the video decoder 300 (Figures 1 and 4) is described, it should be understood that other devices may be configured to perform a similar method to that shown in Figure 9.

[0153] The video decoder 300 may receive entropy-encoded data for the current block, such as entropy-encoded prediction information and entropy-encoded data of the coefficients of the 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 to reconstruct the coefficients of the residual block (372). The video decoder 300 may predict the current block, for example, using an intra-prediction mode or inter-prediction mode as indicated by the prediction information for the current block, in order to compute a prediction block for the current block (374). The video decoder 300 may then back-scan the reconstructed coefficients to create a block of quantized transformation coefficients (376). The video decoder 300 may then inverse-quantize and inverse-transform the quantized transformation coefficients to generate a residual block (378). The video decoder 300 may finally decode the current block by combining the prediction block and the residual block (380). The video decoder 300 may also filter the decoded video data using, for example, one or more NN models as described above, in accordance with the techniques of the present disclosure (382). The video decoder 300 may further store the (filtered) decoded video data in, for example, the DPB 314 (384).

[0154] Figure 10 is a flowchart illustrating an exemplary method for filtering decoded video data using the technique of the present disclosure. The method of Figure 10 may be performed by a video encoder 200 or a video decoder 300. For example, the method of Figure 10 may be performed by a neural network (NN) filtering unit of a filtering unit 216 of a video encoder 200, for example, during step 366 of the method of Figure 8. As another example, the method of Figure 10 may be performed by an NN filtering unit of a filtering unit 312 of a video decoder 300, for example, during step 382 of the method of Figure 9. For illustrative purposes, the method of Figure 10 will be described in relation to a video decoder 300, and more specifically, with respect to an NN filtering unit of a filtering unit 312 of a video decoder 300.

[0155] First, the NN filtering unit of the filter unit 312 receives the decoded video data (400). The decoded video data may be at least a portion of the picture, for example, a set of blocks, tiles, slices, one or more slices, one or more tiles, subpictures, or the entire picture.

[0156] Although not shown in the example in Figure 10, other filtering units of the filtering unit 312, such as the deblocking filter and / or SAO filter, ALF filter, and / or another NN filtering unit, may first filter the decoded video data. Therefore, the received and decoded video data may have been previously filtered (e.g., deblocked, SAO filtered, ALF filtered, and / or NN filtered) prior to its reception by the NN filtering unit performing the method in Figure 10 as described herein. Thus, the term “decoded video data” should be understood to include filtered, decoded video data (e.g., which may include deblocked, decoded video data).

[0157] Therefore, at least a portion may include multiple blocks, including deblocked edges, which are deblocked by, for example, the deblocking filter of the filter unit 312. The deblocking filter can calculate boundary intensity values ​​for the boundaries between blocks. Boundary intensity values ​​generally represent whether and to what extent samples near the block boundaries are modified by the deblocking filter.

[0158] The NN filtering unit of filter unit 312 may receive additional data from one or more other units of the video decoder 300 (402). For example, the NN filtering unit of filter unit 312 may receive boundary intensity values ​​from the deblocking filter of filter unit 312. The NN filtering unit of filter unit 312 may, additionally or alternatively, receive other data from other units, such as coding unit (CU) segmentation data, prediction unit (PU) segmentation data, transformation unit (TU) segmentation data, deblocking filtering data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between the decoded picture and one or more reference pictures (e.g., POC distance), or motion information about one or more decoded blocks of the decoded picture.

[0159] Next, the NN filtering unit of the filter unit 312 may determine one or more NN models from the neural network (NN) models 322 to be used to filter at least a portion of the current picture (404). Then, the NN filtering unit of the filter unit 312 may filter at least a portion of the current picture using the received additional data and the determined one or more NN models (406). In some examples, the NN filtering unit of the filter unit 312 may modify the additional data, for example, by adjusting the range of values ​​of the additional data to fit the range of input sample values, and / or by converting the values ​​of the additional data to a different format, such as integers or floating-point numbers. The NN filtering unit of the filter unit 312 may convert the additional data to one or more input planes, as well as the luminance plane and / or chrominance plane to be filtered.

[0160] Thus, the method in Figure 10 represents an example of a method for filtering decoded video data, comprising the steps of: receiving data for a decoded picture of video data by a neural network filtering unit of a video decoding device; receiving data from one or more other units of the video decoding device by the neural network filtering unit, wherein the data from one or more other units is different from the data for the decoded picture, and the step of receiving data from one or more other units includes receiving boundary intensity data from a deblocking unit; determining one or more neural network models to be used to filter a portion of the decoded picture by the neural network filtering unit; and filtering a portion of the decoded picture by the neural network filtering unit using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0161] Some examples of the techniques used in this disclosure are summarized in the following clauses.

[0162] Clause 1: A method for filtering decoded video data, comprising: a filtering unit of a video decoding device receiving data from one or more other units of the video decoding device; the filtering unit determining one or more neural network models to be used to filter a portion of the decoded picture of the video data; and the filtering unit filtering a portion of the decoded picture using one or more neural network models and data from one or more other units of the video decoding device.

[0163] Clause 2: The method of Clause 1, wherein the step of receiving data from one or more other units includes receiving data from one or more of the following: an intra-prediction unit of the video decoding device, an inter-prediction unit of the video decoding device, a conversion processing unit of the video decoding device, a quantization unit of the video decoding device, a loop filter unit of the video decoding device, a pre-processing unit of the video decoding device, or a second filtering unit of the video decoding device.

[0164] Clause 3: The method of Clause 2, wherein the filtering unit includes a first neural network-based filtering unit.

[0165] Clause 4: Any method of Clauses 2 and 3, wherein the loop filter unit includes at least one of the following: a deblocking filter unit, a sample adaptive offset (SAO) filter unit, or an adaptive loop filter (ALF) unit.

[0166] Clause 5: Any method of Clauses 1 to 4, wherein the step of receiving data includes receiving one or more of the following: coding unit (CU) segmented data, prediction unit (PU) segmented data, transformation unit (TU) segmented data, deblocking filter data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture.

[0167] Clause 6: The method of Clause 5, wherein the deblocking filtering data includes one or more of the following: boundary intensity values, whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking.

[0168] Clause 7: Intra-predictive data is obtained by any method of Clauses 5 and 6, including the intra-predictive mode.

[0169] Clause 8: Any method of Clauses 5-7, wherein the data representing distance includes data representing the difference between the picture order count (POC) value of the decoded picture and the POC value of the reference picture used to predict the blocks of the decoded picture.

[0170] Clause 9: Any method of Clauses 1 to 8, further comprising the step of having a filtering unit perform a function attributable to one or more of the other units.

[0171] Clause 10: Any method of Clauses 1 to 9, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of providing data from one or more other units of the video decoding device as one or more additional input planes to a convolutional neural network (CNN).

[0172] Clause 11: Any method of Clauses 1 to 10, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of adjusting the output of one or more neural network models using data from one or more other units of a video decoding device.

[0173] Clause 12: Any method of Clauses 1 to 11, further comprising the step of adjusting data from one or more other units of the video decoding device prior to filtering a portion of the decoded picture.

[0174] Clause 13: The method of Clause 12, wherein the step of adjusting the data includes the step of converting the values ​​of the data between integer representation and floating-point representation.

[0175] Clause 14: Any method of Clauses 12 and 13, wherein the step of adjusting the data includes a step of scaling the values ​​of the data so that they are within a range of values ​​suitable for one or more neural network models.

[0176] Clause 15: Any method of Clauses 1 to 14, wherein the step of receiving data includes the step of receiving piecewise data for a decoded picture, and the step of filtering a portion of the decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of setting the values ​​at the positions and collated input planes of boundary samples that define piecewise boundaries in the decoded picture as indicated by the piecewise data to a first value, setting the values ​​at the positions and collated input planes of internal samples that are non-boundary samples to a second value, and filtering a portion of the decoded picture using the input plane as input to at least one of the one or more neural network models.

[0177] Clause 16: The method of Clause 15, wherein the first value includes 1 and the second value includes 0.

[0178] Clause 17: Any method of Clauses 15 and 16, wherein the segmented data includes coding unit (CU) segmented data, the input plane includes a first segmented plane, and the method further includes the steps of receiving prediction unit (PU) segmented data, forming a second input plane using the PU segmented data, receiving transformation unit (TU) segmented data, and forming a third input plane using the TU segmented data, and the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device, the step of filtering a portion of a decoded picture using the first input plane, the second input plane, and the third input plane as inputs to at least one of the one or more neural network models.

[0179] Clause 18: Any method of Clauses 1 to 14, wherein the step of receiving data includes the step of receiving deblocking filter data for a decoded picture, and the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of the video decoding device includes the steps of transforming the deblocking filter data for a decoded picture into one or more input planes for at least one of the one or more neural network models, and filtering a portion of a decoded picture using the one or more input planes as inputs to at least one of the one or more neural network models.

[0180] Clause 19: The method of Clause 18, wherein the deblocking filter data includes one or more of boundary intensity data, long or short filter data, or strong or weak filter data.

[0181] Clause 20: Any method of Clause 10 or 15-19, further comprising the step of upsampling or downsampling data on an input plane.

[0182] Clause 21: Any method of Clauses 1 to 20, further comprising the steps of encoding the current picture and decoding the current picture to form a decoded picture.

[0183] Clause 22: The method of Clause 21, wherein the determination step includes a step of determination according to rate strain calculation.

[0184] Clause 23: A device for filtering decoded video data, comprising one or more means for performing any of the methods described in Clauses 1 to 22.

[0185] Clause 24: The device of Clause 23, wherein one or more means comprises one or more processors implemented in a circuit.

[0186] Clause 25: The device of Clause 23, further comprising a display configured to display decoded video data.

[0187] Clause 26: A device under Clause 23, comprising one or more of the following: a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

[0188] Clause 27: The device of Clause 23, further comprising memory configured to store video data.

[0189] Clause 28: A computer-readable storage medium storing instructions that, when executed, cause a processor to perform any of the methods described in Clauses 1 through 22.

[0190] Clause 29: A device for filtering decoded video data, comprising a filtering unit comprising: means for receiving data from one or more units other than the filtering unit of a video decoding device; means for determining one or more neural network models to be used to filter a portion of the decoded picture of the video data; and means for filtering a portion of the decoded picture using one or more neural network models and data from one or more other units of the video decoding device.

[0191] Clause 30: A method for filtering decoded video data, comprising: a neural network filtering unit of a video decoding device receiving data for a decoded picture of video data; a neural network filtering unit receiving data from one or more other units of the video decoding device, wherein the data from one or more other units is different from the data for the decoded picture, and the step of receiving data from one or more other units of the video decoding device includes a step of receiving boundary intensity data from a deblocking unit of the video decoding device; a neural network filtering unit determining one or more neural network models to be used to filter a portion of the decoded picture; and a neural network filtering unit filtering a portion of the decoded picture using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0192] Clause 31: The method of Clause 30, wherein the step of receiving data from one or more other units of the video decoding device further includes the step of receiving data from one or more of the intra-prediction unit of the video decoding device, the inter-prediction unit of the video decoding device, the conversion processing unit of the video decoding device, the quantization unit of the video decoding device, the loop filter unit of the video decoding device, the pre-processing unit of the video decoding device, or the second neural network filtering unit of the video decoding device.

[0193] Clause 32: The method of Clause 31, wherein the loop filter unit includes at least one of a sample adaptive offset (SAO) filter unit or an adaptive loop filter (ALF) unit.

[0194] Clause 33: The method of Clause 32, wherein the step of receiving data further includes receiving one or more of the following: coding unit (CU) segmented data, prediction unit (PU) segmented data, transformation unit (TU) segmented data, deblocking filter data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture.

[0195] Clause 34: The method of Clause 33, wherein the deblocking filtering data includes one or more of whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking.

[0196] Clause 35: The method of Clause 33, including intra-prediction mode, for intra-prediction data.

[0197] Clause 36: The method of Clause 33, wherein the data representing distance includes data representing the difference between the picture order count (POC) value of the decoded picture and the POC value of the reference picture used to predict the blocks of the decoded picture.

[0198] Clause 37: The method of Clause 30, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of providing data from one or more other units of the video decoding device as one or more additional input planes to a convolutional neural network (CNN).

[0199] Clause 38: The method of Clause 30, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of adjusting the output of one or more neural network models using data from one or more other units of a video decoding device.

[0200] Clause 39: The method of Clause 30, further comprising the step of adjusting data from one or more other units of the video decoding device prior to filtering a portion of the decoded picture.

[0201] Clause 40: The method of Clause 39, wherein the step of adjusting the data includes a step of converting the values ​​of the data between integer representation and floating-point representation.

[0202] Clause 41: The method of Clause 39, wherein the step of adjusting the data includes the step of scaling the values ​​of the data so that they are within a range of values ​​suitable for one or more neural network models.

[0203] Clause 42: The method of Clause 30, wherein the step of receiving data includes the step of receiving piecewise data for a decoded picture, and the step of filtering a portion of the decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of setting the values ​​at the positions of boundary samples in a collated input plane that define piecewise boundaries in the decoded picture as indicated by the piecewise data to a first value, the step of setting the values ​​at the positions of internal samples that are non-boundary samples in a collated input plane to a second value, and the step of filtering a portion of the decoded picture using the input plane as input to at least one of the one or more neural network models.

[0204] Clause 43: The method of Clause 42, wherein the first value includes 1 and the second value includes 0.

[0205] Clause 44: The method of Clause 42, wherein the segmented data includes coding unit (CU) segmented data, the input plane includes a first segmented plane, and the method further includes the steps of receiving prediction unit (PU) segmented data, forming a second input plane using the PU segmented data, receiving transformation unit (TU) segmented data, and forming a third input plane using the TU segmented data, and the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device, the step of filtering a portion of a decoded picture using the first input plane, the second input plane and the third input plane as inputs to at least one of the one or more neural network models.

[0206] Clause 45: The method of Clause 30, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the steps of: transforming deblocking filter data for a decoded picture from a deblocking unit into one or more input planes for at least one of the one or more neural network models; and filtering a portion of the decoded picture using the one or more input planes as inputs to at least one of the one or more neural network models.

[0207] Clause 46: The method of Clause 30, further comprising the steps of encoding the current picture and decoding the current picture to form a decoded picture.

[0208] Clause 47: The method of Clause 46, wherein the step of determining one or more neural network models includes the step of determining one or more neural network models according to rate-distortion calculations.

[0209] Clause 48: A device for filtering decoded video data, comprising a memory configured to store decoded pictures of video data, and one or more processors implemented in a circuit, wherein one or more processors are configured to perform a neural network filtering unit to receive data from one or more other units of the device, the data from one or more other units of the device being different from the data for the decoded pictures, and to receive data from one or more other units of the device, one or more processors are configured to perform a neural network filtering unit to receive boundary intensity data from a deblocking unit of the device, to receive data from one or more other units of the device, to determine one or more neural network models to be used to filter a portion of the decoded pictures, and to filter a portion of the decoded pictures using one or more neural network models and data including boundary intensity data from one or more other units of the device.

[0210] Clause 49: The device of Clause 48, wherein one or more processors are further configured to run a neural network filtering unit to receive data from one or more of the device's intra-prediction units, device inter-prediction units, device transformation units, device quantization units, device loop filtering units, device preprocessing units, or second neural network filtering units of the device, in order to receive data from one or more of the device's intra-prediction units, device inter-prediction units, device transformation units, device quantization units, device loop filtering units, device preprocessing units, or second neural network filtering units of the device.

[0211] Clause 50: The device of Clause 48, further configured to receive data from one or more other units of the device, by having one or more processors run a neural network filtering unit to receive one or more of the following: coding unit (CU) segmented data, prediction unit (PU) segmented data, transformation unit (TU) segmented data, deblocking filtering data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between a decoded picture and one or more reference pictures, or motion information about one or more decoded blocks of a decoded picture.

[0212] Clause 51: The device of Clause 48, wherein one or more processors are configured to run a neural network filtering unit to provide data from one or more other units of the device as one or more additional input planes to a convolutional neural network (CNN) in order to filter a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0213] Clause 52: The device of Clause 48, wherein one or more processors are configured to run a neural network filtering unit to adjust the output of one or more neural network models using data from one or more other units of the device in order to filter a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0214] Clause 53: The device of Clause 48, wherein one or more processors are configured to run a neural network filtering unit to coordinate the data from one or more other units of the device prior to filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0215] Clause 54: The device of Clause 48, wherein one or more processors are configured to perform a neural network filtering unit

[0216] Clause 55: The device of Clause 48, further comprising a display configured to display a picture of decoded video data.

[0217] Clause 56: A device under Clause 48, comprising one or more of the following: a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

[0218] Clause 57: A computer-readable storage medium storing instructions, wherein, when executed, the instructions cause a processor of a video decoding device to execute a neural network filtering unit to receive data for a decoded picture of video data, receive data from one or more other units of the video decoding device, wherein the instructions causing the processor to receive data from one or more other units of the video decoding device include instructions causing the processor to receive boundary intensity data from a deblocking unit of the video decoding device, determine one or more neural network models to be used to filter a portion of the decoded picture, and filter a portion of the decoded picture using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0219] Clause 58: A device for filtering decoded video data, comprising: means for receiving data for a decoded picture of video data; means for receiving data from one or more other units of the video decoding device, wherein the data from one or more other units is different from the data for a decoded picture, and the means for receiving data from one or more other units of the video decoding device comprises means for receiving boundary intensity data from a deblocking unit of the video decoding device; means for determining one or more neural network models to be used to filter a portion of the decoded picture; and means for filtering a portion of the decoded picture using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0220] Clause 59: A method for filtering decoded video data, comprising: a neural network filtering unit of a video decoding device receiving data for a decoded picture of video data; a neural network filtering unit receiving data from one or more other units of the video decoding device, wherein the data from one or more other units is different from the data for the decoded picture, and the step of receiving data from one or more other units of the video decoding device includes a step of receiving boundary intensity data from a deblocking unit of the video decoding device; a neural network filtering unit determining one or more neural network models to be used to filter a portion of the decoded picture; and a neural network filtering unit filtering a portion of the decoded picture using one or more neural network models and data including boundary intensity data from one or more other units of the video decoding device.

[0221] Clause 60: The method of Clause 59, wherein the step of receiving data from one or more other units of the video decoding device further includes the step of receiving data from one or more of the intra-prediction unit of the video decoding device, the inter-prediction unit of the video decoding device, the conversion processing unit of the video decoding device, the quantization unit of the video decoding device, the loop filter unit of the video decoding device, the pre-processing unit of the video decoding device, or the second neural network filtering unit of the video decoding device.

[0222] Clause 61: The method of Clause 60, wherein the loop filter unit includes at least one of a sample adaptive offset (SAO) filter unit or an adaptive loop filter (ALF) unit.

[0223] Clause 62: Any method of Clauses 59-61, wherein the step of receiving data further includes receiving one or more of the following: coding unit (CU) segmented data, prediction unit (PU) segmented data, transformation unit (TU) segmented data, deblocking filter data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture.

[0224] Clause 63: The method of Clause 62, wherein the deblocking filtering data includes one or more of whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking.

[0225] Clause 64: Intra-predictive data is obtained by any method of Clauses 62 and 63, including an intra-predictive mode.

[0226] Clause 65: Any method of Clauses 62-64, wherein the data representing distance includes data representing the difference between the picture order count (POC) value of the decoded picture and the POC value of the reference picture used to predict the blocks of the decoded picture.

[0227] Clause 66: Any method of Clauses 59 to 65, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of providing data from one or more other units of the video decoding device as one or more additional input planes to a convolutional neural network (CNN).

[0228] Clause 67: Any method of Clauses 59 to 66, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the step of adjusting the output of one or more neural network models using data from one or more other units of a video decoding device.

[0229] Clause 68: Any method of Clauses 59-67, further comprising the step of adjusting data from one or more other units of the video decoding device prior to filtering a portion of the decoded picture.

[0230] Clause 69: The method of Clause 68, wherein the step of adjusting the data includes the step of converting the values ​​of the data between integer representation and floating-point representation.

[0231] Clause 70: Any method of Clauses 68 and 69, wherein the step of adjusting the data includes the step of scaling the values ​​of the data so that they are within a range of values ​​suitable for one or more neural network models.

[0232] Clause 71: Any method of Clauses 59 to 70, wherein the step of receiving data includes the step of receiving piecewise data for a decoded picture, and the step of filtering a portion of the decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes setting the values ​​at the positions of boundary samples in a collated input plane that define piecewise boundaries in the decoded picture as indicated by the piecewise data to a first value, setting the values ​​at the positions of internal samples that are non-boundary samples in a collated input plane to a second value, and filtering a portion of the decoded picture using the input plane as input to at least one of the one or more neural network models.

[0233] Clause 72: The method of Clause 71, wherein the first value includes 1 and the second value includes 0.

[0234] Clause 73: Any method of Clauses 71 and 72, wherein the segmented data includes coding unit (CU) segmented data, the input plane includes a first segmented plane, and the method further includes the steps of receiving prediction unit (PU) segmented data, forming a second input plane using the PU segmented data, receiving transformation unit (TU) segmented data, and forming a third input plane using the TU segmented data, and the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device, the step of filtering a portion of a decoded picture using the first input plane, the second input plane, and the third input plane as inputs to at least one of the one or more neural network models.

[0235] Clause 74: Any method of Clauses 59 to 73, wherein the step of filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of a video decoding device includes the steps of: transforming deblocking filter data for the decoded picture from a deblocking unit into one or more input planes for at least one of the one or more neural network models; and filtering a portion of the decoded picture using the one or more input planes as inputs to at least one of the one or more neural network models.

[0236] Clause 75: Any method of Clauses 59 to 74, further comprising the steps of encoding the current picture and decoding the current picture to form a decoded picture.

[0237] Clause 76: Any method of Clauses 59 to 75, wherein the step of determining one or more neural network models includes the step of determining one or more neural network models according to rate-distortion calculations.

[0238] Clause 77: A device for filtering decoded video data, comprising a memory configured to store decoded pictures of video data, and one or more processors implemented in the circuit, wherein one or more processors are configured to perform a neural network filtering unit to receive data from one or more other units of the device, the data from one or more other units of the device being different from the data for the decoded pictures, and to receive data from one or more other units of the device, one or more processors are configured to perform a neural network filtering unit to receive boundary intensity data from a deblocking unit of the device, to receive data from one or more other units of the device, to determine one or more neural network models to be used to filter a portion of the decoded pictures, and to filter a portion of the decoded pictures using one or more neural network models and data including boundary intensity data from one or more other units of the device.

[0239] Clause 78: The device of Clause 77, wherein one or more processors are further configured to run a neural network filtering unit to receive data from one or more of the device's intra-prediction units, device inter-prediction units, device transformation units, device quantization units, device loop filtering units, device preprocessing units, or second neural network filtering units of the device, in order to receive data from one or more of the device's intra-prediction units, device inter-prediction units, device transformation units, device quantization units, device loop filtering units, device preprocessing units, or second neural network filtering units of the device.

[0240] Clause 79: Any device according to Clauses 77 and 78, wherein one or more processors are further configured to run a neural network filtering unit to receive one or more of the following: coding unit (CU) segmented data, prediction unit (PU) segmented data, transformation unit (TU) segmented data, deblocking filtering data, quantization parameter (QP) data, intra-prediction data, inter-prediction data, data representing the distance between a decoded picture and one or more reference pictures, or motion information about one or more decoded blocks of a decoded picture.

[0241] Clause 80: Any device according to Clauses 77-79, wherein one or more processors are configured to run a neural network filtering unit to provide data from one or more other units of the device as one or more additional input planes to a convolutional neural network (CNN) in order to filter a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0242] Clause 81: Any device according to Clauses 77-80, wherein one or more processors are configured to run a neural network filtering unit to adjust the output of one or more neural network models using data from one or more other units of the device in order to filter a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0243] Clause 82: Any device according to Clauses 77-81, wherein one or more processors are configured to run a neural network filtering unit to coordinate the data from one or more other units of the device prior to filtering a portion of a decoded picture using one or more neural network models and data from one or more other units of the device.

[0244] Clause 83: Any device according to Clauses 77 to 82, wherein one or more processors are configured to perform a neural network filtering unit to perform a deblocking filter for the decoded picture from a deblocking unit, which translates the deblocking filter data for the decoded picture from a deblocking unit into one or more input planes for at least one of the one or more neural network models, and to filter the portion of the decoded picture using the one or more input planes as input to at least one of the one or more neural network models.

[0245] Clause 84: Any device according to Clauses 77-83, further comprising a display configured to display a picture of decoded video data.

[0246] Clause 85: A device comprising one or more of the following: a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box, as defined in any of Clauses 77-84.

[0247] It should be noted that, depending on the example, some of the actions or events of any of the techniques described herein may be performed in different sequences, and may be added, merged, or excluded entirely (for example, not all actions or events described may be necessary for the practice of the technique). Furthermore, in some examples, the actions or events may be performed not sequentially, but concurrently, for example, through multithreading, interrupt handling, or multiple processors.

[0248] In one or more examples, the described functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include computer-readable storage media corresponding to tangible media such as data storage media, or communication media including any medium that facilitates the transfer of computer programs from one location to another, for example, according to a communication protocol. Thus, the computer-readable medium may generally correspond to (1) non-transient tangible computer-readable storage media, or (2) communication media such as signals or carrier waves. The data storage medium may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, codes and / or data structures for implementing the techniques described herein. A computer program product may include computer-readable media.

[0249] As an example, and not an limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer. Any connection is also appropriately referred to as computer-readable media. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of media. However, it should be understood that computer-readable storage media and data storage media do not include connections, carriers, signals, or other temporary media, but instead refer to non-temporary tangible storage media. The terms "disk" and "disc" as used herein include compact discs (CDs), laser discs, optical discs, digital multipurpose discs (DVDs), floppy disks, and Blu-ray discs. A disk typically reproduces data magnetically, while a disc reproduces data optically using a laser. Any combination of the above should also be included within the scope of computer-readable media.

[0250] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Therefore, the terms “processor” and “processing circuit” as used herein may refer to any of the above-described structures or any other structure suitable for implementing the techniques described herein. In addition, in some embodiments, the functions described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or incorporated into a composite codec. Furthermore, the techniques may be fully implemented in one or more circuits or logic elements.

[0251] The techniques of this disclosure can be implemented in a wide variety of devices or apparatus, including wireless handsets, integrated circuits (ICs), or sets of ICs (e.g., chipsets). While various components, modules, or units have been described in this disclosure to highlight the functional aspects of devices configured to perform the disclosed techniques, they do not necessarily require implementation by different hardware units. Rather, as described above, the various units may be combined in a codec hardware unit, or they may be provided by a set of interoperable hardware units, including one or more processors as described above, along with suitable software and / or firmware.

[0252] We have described various examples. These and other examples fall within the scope of the following claims. [Explanation of symbols]

[0253] 100 video encoding and decoding systems, systems 102 Source Device 104 Video Sources 106 memory 108 Output Interfaces 110 Computer-readable media 112 Storage Devices 114 File Server 116 Destination device 118 Display Devices 120 memory 122 Input Interfaces 130 Hybrid Video Coder, Video Coder 132 Input video data 134 Adding Units 136 Conversion Unit 138 Quantization Units 140 Entropy Coding Units 142 Inverse Quantization Unit 144 Inverse Conversion Unit 146 Adding Units 148 Loop Filter Unit 150 Decoded Picture Buffer (DPB), DPB 152 Intra Prediction Units 154 Interpretation Units 156 Motion Estimation Unit 158 output bitstreams 166-layer prediction structure 170 Neural network-based filters, NN-based filters 180 Pictures 182 vertical boundary, boundary 182A~182D Vertical boundary 184 horizontal boundary, boundary 184A~184C Horizontal boundary 200 video encoders 202 Mode Selection Unit 204 Residual Generation Unit 206 Conversion Processing Unit 208 Quantization Units 210 Inverse Quantization Unit 212 Inverse Transform Processing Unit 214 Reconfiguration Unit 216 Filter Unit 218 Decoded Picture Buffer (DPB), DPB 220 Entropy Coding Units 222 Motion Estimation Unit 224 Motion Compensation Unit 226 Intra Prediction Units 230 video data memory 232 Neural Network Models (NN Models), NN Models 300 video decoders 302 Entropy Decoding Unit 304 Prediction Processing Unit 306 Inverse Quantization Unit 308 Inverse Transformation Processing Unit 310 Reconfiguration Unit 312 Filter Unit 314 Decoded Picture Buffer (DPB), DPB 316 Motion Compensation Unit 318 Intra Prediction Units 320 Encoded Picture Buffer (CPB) memory, CPB memory 322 Neural Network (NN) Models, NN Models

Claims

1. A method for filtering decoded video data, The video decoding device's neural network filtering unit receives the decoded picture of the video data, The neural network filtering unit receives data from one or more other units of the video decoding device, wherein the step of receiving the data from one or more other units of the video decoding device is The steps include receiving boundary intensity data from the deblocking unit of the video decoding device, The intra-prediction unit of the video decoding device, Interpretation unit of the video decoding device, The conversion processing unit of the video decoding device, The quantization unit of the video decoding device, The loop filter unit of the aforementioned video decoding device, The preprocessing unit of the video decoding device, or Second neural network filter processing unit of the aforementioned video decoding device The step of receiving the data from one or more of the above Steps including, The neural network filtering unit determines one or more neural network models to be used to filter a portion of the decoded picture, The neural network filtering unit performs the steps of filtering the portion of the decoded picture using the one or more neural network models and the data including the boundary intensity data from one or more other units of the video decoding device. A method that includes this.

2. The method according to claim 1, wherein the loop filter unit includes at least one of a sample adaptive offset (SAO) filter unit or an adaptive loop filter (ALF) unit.

3. A method for filtering decoded video data, The video decoding device's neural network filtering unit receives the decoded picture of the video data, The neural network filtering unit receives data from one or more other units of the video decoding device, wherein the step of receiving the data from one or more other units of the video decoding device is Coding unit (CU) classification data, Prediction unit (PU) segmentation data, Conversion unit (TU) classification data, Deblocking filtered data, Quantization parameter (QP) data, Intra predictive data, Interpretation data, Data representing the distance between the decoded picture and one or more reference pictures, or Motion information for one or more decrypted blocks of the aforementioned decrypted picture A step including receiving one or more of the following, The neural network filtering unit determines one or more neural network models to be used to filter a portion of the decoded picture, The neural network filtering unit performs the steps of filtering the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the video decoding device. A method that includes this.

4. The deblocking filtering data includes one or more of the following: whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking. The intra prediction data includes an intra prediction mode, The method according to claim 3, wherein the data representing the distance includes data representing the difference between the picture order count (POC) value of the decoded picture and the POC value of a reference picture used to predict the blocks of the decoded picture.

5. The step of filtering the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the video decoding device is: The steps include providing the data from one or more other units of the video decoding device as one or more additional input planes to a convolutional neural network (CNN), or A step of combining multiple input planes into a combined input plane, the step of setting the value of the position (i,j) of the combined input plane equal to the maximum value at the position (i,j) of each of the multiple input planes, The process includes the step of providing the aforementioned composite input plane to a convolutional neural network (CNN), or The step of adjusting the output of one or more neural network models using the data from one or more other units of the video decoding device, The method according to any one of claims 1 to 4.

6. A method for filtering decoded video data, The video decoding device's neural network filtering unit receives the decoded picture of the video data, The neural network filtering unit receives data from one or more other units of the video decoding device, wherein the step of receiving the data from one or more other units of the video decoding device is The steps include receiving boundary intensity data from the deblocking unit of the video decoding device, The neural network filtering unit determines one or more neural network models to be used to filter a portion of the decoded picture, The neural network filtering unit performs the steps of filtering the portion of the decoded picture using the one or more neural network models and the data including the boundary intensity data from one or more other units of the video decoding device. Includes, The process further includes adjusting the data from one or more other units of the video decoding device prior to filtering the portion of the decoded picture, The step of adjusting the aforementioned data is, A step of converting the value of the aforementioned data between integer representation and floating-point representation, or Step 1: Scaling the values ​​of the data so that they are within a range of values ​​suitable for the one or more neural network models. Methods that include...

7. A method for filtering decoded video data, The video decoding device's neural network filtering unit receives the decoded picture of the video data, The neural network filtering unit receives data from one or more other units of the video decoding device, wherein the step of receiving the data from one or more other units of the video decoding device is The steps include receiving boundary intensity data from the deblocking unit of the video decoding device, The neural network filtering unit determines one or more neural network models to be used to filter a portion of the decoded picture, The neural network filtering unit performs the steps of filtering the portion of the decoded picture using the one or more neural network models and the data including the boundary intensity data from one or more other units of the video decoding device. Includes, The step of receiving the data includes the step of receiving segmental data for the decoded picture, and the step of filtering the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the video decoding device, The steps include setting the values ​​at the positions of boundary samples that define the partition boundaries in the decoded picture as indicated by the partition data and their positions in the collated input plane to a first value, The steps include setting the values ​​of the internal sample, which is a non-boundary sample, and the collated input plane, to a second value, The steps include: filtering the portion of the decoded picture using the input plane as input to at least one of the one or more neural network models; Methods that include...

8. The method according to claim 7, wherein the first value includes 1 and the second value includes 0.

9. The division data includes coding unit (CU) division data, the input plane includes a first division plane, and the method is The steps include receiving prediction unit (PU) classification data, The steps include forming a second input plane using the aforementioned PU classification data, The steps include receiving conversion unit (TU) classification data, The steps include forming a third input plane using the aforementioned TU classification data, and It further includes, The step of filtering the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the video decoding device includes the step of filtering the portion of the decoded picture using the first partition plane, the second input plane, and the third input plane as inputs to at least one of the one or more neural network models, The method according to claim 7.

10. The step of filtering the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the video decoding device is: The steps of: converting deblocking filter data for the decoded picture from the deblocking unit of the video decoding device into one or more input planes for at least one of the one or more neural network models; The steps of filtering the portion of the decoded picture by using the one or more input planes as input to at least one of the one or more neural network models, and The method according to any one of claims 1 to 9, including the method described in any one of claims 1 to 9.

11. A method for filtering decoded video data, The video decoding device's neural network filtering unit receives the decoded picture of the video data, A step of receiving data from one or more other units of the video decoding device by the neural network filtering unit, wherein the step of receiving the data from one or more other units of the video decoding device includes a step of receiving boundary intensity data from the deblocking unit of the video decoding device, The neural network filtering unit determines one or more neural network models to be used to filter a portion of the decoded picture, The neural network filtering unit performs the steps of filtering the portion of the decoded picture using the one or more neural network models and the data including the boundary intensity data from one or more other units of the video decoding device. Includes, The steps to encode the current picture, The steps include: decoding the current picture and forming the decoded picture; It further includes, A method comprising the step of determining the one or more neural network models, wherein the step of determining the one or more neural network models according to rate-distortion calculations.

12. The boundary intensity data mentioned above To indicate that the boundary intensity value is 0, or The method according to any one of claims 1, 6, or 7, wherein the boundary intensity value is 1 or 2.

13. A device for filtering decoded video data, A memory configured to store decoded pictures of video data, A device comprising one or more processors implemented in a circuit, wherein the one or more processors are further configured to perform a neural network filtering unit to perform the method according to any one of claims 1 to 12.

14. The system further comprises a display configured to display the decoded picture of the video data, and / or The device according to claim 13, wherein the device comprises one or more of a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

15. A computer-readable storage medium storing instructions, wherein, when an instruction is executed, it causes the processor of a video decoding device to execute a neural network filtering unit to perform the method according to any one of claims 1 to 11.

Images