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 December 30, 2021, and U.S. Provisional Application No. 63 / 133,733, filed January 4, 2021, the entire contents of each of which are incorporated herein by reference. U.S. Patent Application No. 17 / 566,282, filed December 30, 2021, claims the benefit of U.S. Provisional Application No. 63 / 133,733, filed January 4, 2021.

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

[0003] Digital video capabilities may be incorporated into a wide range of devices, including digital televisions, digital direct broadcast systems, wireless broadcast systems, personal digital assistants (PDAs), laptop or desktop computers, tablet computers, e-book readers, digital cameras, digital recording devices, digital media players, video gaming devices, video game consoles, cellular or satellite radio telephones, so-called "smartphones," video teleconferencing devices, video streaming devices, and the like. 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 to such standards. By implementing such video coding techniques, video devices may more efficiently transmit, receive, encode, decode, and / or store digital video information.

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

[0005] In general, this disclosure describes techniques for filtering decoded pictures, which may have distortions. 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 of ITU-T H.266 / Versatile Video Coding (VVC), or subsequent generation video coding standards, and any other video codecs. In one example, a neural network filtering unit may receive boundary strength values ​​calculated by a deblocking filter and use the boundary strength values ​​to further filter the deblocked video data, for example, using one or more neural network models.

[0006] In one example, a method for filtering decoded video data includes the steps of receiving, by a neural network filtering unit of a video decoding device, data for a decoded picture of the video data; receiving, by the neural network filtering unit, data from one or more other units of the video decoding device, where the data from the one or more other units differs from the data for the decoded picture, and where receiving the data from the one or more other units of the video decoding device includes receiving boundary strength data from a deblocking unit of the video decoding device; determining, by the neural network filtering unit, one or more neural network models to be used to filter a portion of the decoded picture; and filtering, by the neural network filtering unit, 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 video decoding device.

[0007] In another example, a device for filtering decoded video data includes a memory configured to store a decoded picture of the video data and one or more processors implemented in a circuit, 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 differs from data for the decoded picture, and where 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.

[0008] In another example, a computer-readable storage medium storing instructions that, when executed, cause a processor of the video decoding device to execute a neural network filtering unit to receive data for a decoded picture of the video data; receive data from one or more other units of the video decoding device, where the data from the one or more other units of the video decoding device differs from the data for the decoded picture, the instructions causing the processor to receive data from the one or more other units of the video decoding device include instructions to receive boundary strength 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 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 video decoding device.

[0009] In another example, a device for filtering decoded video data comprises a filtering unit comprising 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, where the data from the one or more other units differs from the data for the decoded picture, and where the means for receiving data from the one or more other units of the video decoding device comprises means for receiving boundary strength 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 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 video decoding device.

[0010] The details of one or more examples are set forth in the accompanying drawings and the description below. Other features, objects, and advantages will become apparent from the description, drawings, and claims. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram illustrating an example video encoding and decoding system that may implement the techniques of this disclosure. [Diagram 2] FIG. 1 is a conceptual diagram illustrating a hybrid video coding framework. [Diagram 3] FIG. 1 is a conceptual diagram illustrating a hierarchical prediction structure using a group of pictures (GOP) size of 16. [Figure 4] FIG. 1 is a conceptual diagram illustrating a neural network-based filter having four layers. [Diagram 5] FIG. 2 is a conceptual diagram illustrating an example portion of a picture including a boundary, boundary samples, and interior samples. [Figure 6] 1 is a block diagram illustrating an example video encoder that may perform the techniques of this disclosure. [Figure 7] 1 is a block diagram illustrating an example video decoder that may perform the techniques of this disclosure. [Figure 8] 1 is a flowchart illustrating an example method for encoding a current block, in accordance with techniques of this disclosure. [Figure 9] 5 is a flowchart illustrating an example method for decoding a current block, in accordance with techniques of this disclosure. [Figure 10] 5 is a flowchart illustrating an example method for filtering decoded video data in accordance with techniques of this disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Video coding standards include ITU-T H.261, ISO / IEC MPEG-1 Visual, ITU-T H.262 or ISO / IEC MPEG-2 Visual, ITU-T H.263, ISO / IEC MPEG-4 Visual and ITU-T H.264 (also known as ISO / IEC MPEG-4 AVC), High Efficiency Video Coding (HEVC) or ITU-T H.265 including its range extensions Multiview Extension (MV-HEVC) and Scalable Extension (SHVC). Another exemplary video coding standard is Versatile Video Coding (VVC) or ITU-T H.266 developed by the ITU-T Video Coding Experts Group (VCEG) and the Joint Video Experts Team (JVET) of the ISO / IEC Motion Picture Experts Group (MPEG). Version 1 of the VVC specification, hereafter referred to as "VVC FDIS", is available at http: / / phenix.int-evry.fr / jvet / doc_end_user / documents / 19_Teleconference / wg11 / JVET-S2001-v17.zip.

[0013] 1 is a block diagram illustrating an example video encoding and decoding system 100 that may perform the techniques of this disclosure. The techniques of this disclosure are generally directed to coding (encoding and / or decoding) video data. In general, video data includes any data for processing video. Thus, video data may include raw uncoded video, encoded video, decoded (e.g., reconstructed) video, and video metadata, such as signaling data.

[0014] 1, system 100 includes a source device 102 that provides encoded video data to be decoded and displayed by a destination device 116, in this example. Specifically, source device 102 provides the video data to destination device 116 via a 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 therefore may be referred to as wireless communication devices.

[0015] In the example of FIG. 1, source device 102 includes a video source 104, memory 106, video encoder 200, and output interface 108. Destination device 116 includes an input interface 122, a video decoder 300, memory 120, and a display device 118. According to this disclosure, the video encoder 200 of source device 102 and the video decoder 300 of destination device 116 may be configured to apply a technique for filtering using multiple neural network models. Thus, 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, the source device and destination device 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] The system 100 as shown in FIG. 1 is only an example. In general, any digital video encoding and / or decoding device may perform techniques for filtering using multiple neural network models. The source device 102 and the destination device 116 are only examples of coding devices, such that the source device 102 generates coded video data for transmission to the destination device 116. This disclosure refers to devices that perform coding (encoding and / or decoding) of data as "coding" devices. Thus, the video encoder 200 and the video decoder 300 represent examples of coding devices, specifically, video encoders and video decoders, respectively. In some examples, the source device 102 and the destination device 116 may operate in a substantially symmetrical manner, such that each of the source device 102 and the destination device 116 includes video encoding and decoding components. Thus, the system 100 may support unidirectional or bidirectional video transmission between the source device 102 and the destination device 116, for example, video streaming, video playback, video broadcasting, or video telephony.

[0017] In general, video source 104 represents a source of video data (i.e., raw, uncoded video data) and provides a continuous series of pictures (also called "frames") of the video data to video encoder 200, which encodes the data for the pictures. Video source 104 of 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, video source 104 may generate computer graphics-based data as source video, or a combination of live, archived, and computer-generated video. In each case, video encoder 200 encodes the captured, pre-captured, or computer-generated video data. Video encoder 200 may reorder the pictures from the order in which they were received (sometimes called "display order") into a coding order for coding. Video encoder 200 may generate a bitstream including the encoded video data. The source device 102 may then output the encoded video data via the output interface 108 onto a computer-readable medium 110 for receipt and / or retrieval by, for example, an input interface 122 of the destination device 116 .

[0018] The memory 106 of the source device 102 and the memory 120 of the destination device 116 represent general-purpose memories. In some examples, the memories 106, 120 may store raw video data, e.g., raw video from the video source 104 and raw decoded video data from the video decoder 300. Additionally or alternatively, the memories 106, 120 may store software instructions executable by, e.g., the video encoder 200 and the video decoder 300, respectively. Although the memories 106 and 120 are shown separately from the video encoder 200 and the video decoder 300 in this example, it should be understood that the video encoder 200 and the video decoder 300 may also include internal memories for functionally similar or equivalent purposes. Additionally, the memories 106, 120 may store encoded video data, e.g., the output from the video encoder 200 and the input to the video decoder 300. In some examples, a portion of the memory 106, 120 may be allocated as one or more video buffers, for example, for storing 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. In one example, the computer-readable medium 110 represents a communication medium that allows the source device 102 to transmit encoded video data directly to the destination device 116 in real time, for example, via a radio frequency network or a computer-based network. The output interface 108 may modulate a transmission signal including the encoded video data and the input interface 122 may demodulate a received transmission signal according to a communication standard such as a wireless communication protocol. 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, source device 102 may output the encoded data from output interface 108 to storage device 112. Similarly, destination device 116 may access the encoded data from storage device 112 via input interface 122. Storage device 112 may include any of a variety of distributed or locally accessed data storage media, such as a hard drive, a Blu-ray disc, a DVD, a 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, source device 102 may output the encoded video data to a file server 114 or another intermediate storage device, which may store the encoded video data generated by source device 102. Destination device 116 may access the stored video data from file server 114 via streaming or download.

[0022] The file server 114 may be any type of server device capable of storing encoded video data and transmitting the encoded video data to the destination device 116. The file server 114 may represent a web server (e.g., for a website), a server configured to provide file transfer protocol services (such as 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 additionally 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), HTTP Dynamic Streaming, etc.

[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 a wireless channel (e.g., a Wi-Fi connection), a wired connection (e.g., a digital subscriber line (DSL), a cable modem, etc.), or a combination of both suitable for accessing the encoded video data stored on the file server 114. The input interface 122 may be configured to operate according to any one or more of the various protocols discussed above for retrieving or receiving media data from the file server 114 or other such protocols for retrieving media data.

[0024] The output interface 108 and the 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 in which the output interface 108 and the input interface 122 comprise wireless components, the output interface 108 and the input interface 122 may be configured to transfer data, such as encoded video data, according to a cellular communication standard, such as 4G, 4G-LTE (Long Term Evolution), LTE Advanced, 5G, etc. In some examples in which the output interface 108 comprises a wireless transmitter, the output interface 108 and the 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™), the Bluetooth™ standard, etc. In some examples, the source device 102 and / or the destination device 116 may include respective system-on-chip (SoC) devices. For example, the source device 102 may include a SoC device for performing functions attributed to the video encoder 200 and / or the output interface 108, and the destination device 116 may include a SoC device for performing functions attributed to the video decoder 300 and / or the input interface 122.

[0025] The techniques of this disclosure may be applied to video coding supporting any of a variety of multimedia applications, such as over-the-air television broadcast, 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 the computer-readable medium 110 (e.g., a communication medium, a storage device 112, a file server 114, etc.). The encoded video bitstream may include signaling information defined by the video encoder 200 and also used by the video decoder 300, such as syntax elements having values ​​that describe characteristics and / or processing of video blocks or other coded units (e.g., slices, pictures, groups of pictures, sequences, etc.). The display device 118 displays decoded pictures of the decoded video data to a user. The display device 118 may represent any of a variety of display devices, such as a liquid crystal display (LCD), a plasma display, an organic light emitting diode (OLED) display, or another type of display device.

[0027] 1, in some examples, the video encoder 200 and the video decoder 300 may each be integrated with an audio encoder and / or an audio decoder and may include an appropriate MUX-DEMUX unit, or other hardware and / or software, to process multiplexed streams that include both audio and video in a common data stream. Where applicable, the MUX-DEMUX unit may conform to the ITU H.223 multiplexer protocol or other protocols, such as the User Datagram Protocol (UDP).

[0028] The video encoder 200 and the video decoder 300 may each be implemented as any of a variety of suitable encoder and / or decoder circuits, such as one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), discrete logic, software, hardware, firmware, or any combination thereof. When the techniques are implemented partially in software, a device may store instructions for the software on a suitable non-transitory computer-readable medium and execute the instructions in hardware using one or more processors to perform the techniques of this disclosure. Each of the video encoder 200 and the video decoder 300 may be included in one or more encoders or decoders, any of which may be integrated as part of a combined encoder / decoder (CODEC) in the respective device. A device including the video encoder 200 and / or the video decoder 300 may comprise an integrated circuit, a microprocessor, and / or a wireless communication device such as a cellular phone.

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

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

[0031] This disclosure may generally refer to coding (e.g., encoding and decoding) a picture to include the process of encoding or decoding data for a picture. Similarly, this disclosure may refer to coding of a block of a picture, e.g., predictive and / or residual coding, to include the process of encoding or decoding data for the block. A coded video bitstream generally includes a set of values ​​for syntax elements that represent coding decisions (e.g., coding modes) and partitioning of a picture into blocks. Thus, references to coding a picture or a block should generally be understood as coding values ​​for the syntax elements that form the picture or block.

[0032] HEVC defines various blocks, including coding units (CUs), prediction units (PUs), and transform units (TUs). According to HEVC, a video coder (such as the video encoder 200) partitions coding tree units (CTUs) into CUs according to a quadtree structure. That is, the video coder partitions CTUs and CUs into four equal non-overlapping squares, and each node of the quadtree has either zero or four child nodes. A node without child nodes may be called a "leaf node", and a CU of such a leaf node may include one or more PUs and / or one or more TUs. The video coder may further partition PUs and TUs. For example, in HEVC, a residual quadtree (RQT) represents a partition of TUs. In HEVC, a PU represents inter-predicted data, and a TU represents residual data. An intra-predicted CU includes intra-prediction information, such as an intra-mode indication.

[0033] As another example, the video encoder 200 and the video decoder 300 may be configured to operate according to VVC. According to VVC, a video coder (such as the video encoder 200) partitions a picture into multiple coding tree units (CTUs). The video encoder 200 may partition the CTUs according to a tree structure, such as a quad-tree binary tree (QTBT) structure or a multi-type tree (MTT) structure. The QTBT structure eliminates the concept of multiple partition types, such as the distinction between CUs, PUs, and TUs in HEVC. The QTBT structure includes two levels, a first level partitioned according to a quad-tree partition and a second level partitioned according to a binary tree partition. 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 the MTT partitioning structure, blocks may be partitioned using quad tree (QT) partitioning, binary tree (BT) partitioning, and one or more types of triple tree (TT) (also called ternary tree (TT)) partitioning. Triple tree or ternary tree partitioning is a partitioning in which a block is divided into three sub-blocks. In some examples, triple tree or ternary tree partitioning divides a block into three sub-blocks without splitting the original block through the center. Partition types in MTT (e.g., QT, BT, and TT) may be symmetric or asymmetric.

[0035] In some examples, 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, 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] Video encoder 200 and video decoder 300 may be configured to use quadtree partitioning, QTBT partitioning, MTT partitioning, or other partition structures per HEVC. For purposes of illustration, the description of the techniques of this disclosure is presented with respect to QTBT partitioning. However, it should be understood that the techniques of this disclosure may also be applied to video coders configured to use quadtree partitioning, or other types of partitioning.

[0037] In some examples, the CTU includes a coding tree block (CTB) of luma samples, two corresponding CTBs of chroma samples for a picture with three sample arrays, or a CTB of samples for a picture coded using three separate color planes and syntax structures used to code a monochrome picture or sample. The CTB may be an N×N block of samples for some value of N such that the division of the components into the CTB is partitioned. The components may be an array or a single sample of that array from one of the three arrays (luma and two chromas) for a 4:2:0, 4:2:2, or 4:4:4 color format picture, or an array or a single sample of that array for a monochrome format picture. In some examples, the coding block is an M×N block of samples for some value of M and N such that the division of the CTB into coding blocks is partitioned.

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

[0039] In some examples, a tile may be partitioned into multiple bricks, each of which may include one or more CTU rows within the tile. A tile that is not partitioned into multiple bricks may also be referred to as a brick. However, a brick that is a true subset of a tile may not be referred to as a tile.

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

[0041] This disclosure may use "NxN" and "N by N" interchangeably to refer to the sample dimensions of a block (such as a CU or other video block) in terms of vertical and horizontal dimensions, e.g., 16x16 samples or 16 by 16 samples. Generally, a 16x16 CU has 16 samples in the vertical direction (y=16) and 16 samples in the horizontal direction (x=16). Similarly, an NxN CU generally has N samples in the vertical direction and N samples in the horizontal direction, where N represents a non-negative integer value. Samples within a CU may be arranged in rows and columns. Furthermore, a CU does not necessarily have to have the same number of samples in the horizontal direction as in the vertical direction. For example, a CU may comprise NxM samples, where M is not necessarily equal to N.

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

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

[0044] Some examples of VVC also provide an affine motion compensation mode, which may be considered an inter-prediction mode. In an affine motion compensation mode, the video encoder 200 may determine two or more motion vectors that represent 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 predictive block. Some examples of VVC provide 67 intra prediction modes, including various orientation modes, as well as a planar mode and a DC mode. In general, the video encoder 200 selects an intra prediction mode that describes neighboring samples relative to a current block (e.g., a block of a CU) from which to predict samples of the current block. Such samples may generally be above, above and to the left, 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 scan order (left to right, top to bottom).

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

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

[0048] As mentioned above, following any transformation to generate transform coefficients, the video encoder 200 may perform quantization of the transform coefficients. Quantization generally refers to a process in which transform coefficients are quantized to possibly reduce the amount of data used to represent the transform coefficients, achieving further compression. By performing a quantization process, the video encoder 200 may reduce the bit depth associated with some or all of the transform 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 transform coefficients and generate a one-dimensional vector from the two-dimensional matrix including the quantized transform coefficients. The scan may be designed to place transform coefficients of higher energy (and therefore lower frequency) at the front of the vector and transform coefficients of lower energy (and therefore higher frequency) at the rear of the vector. In some examples, the video encoder 200 may utilize a predefined scan order for scanning the quantized transform coefficients to generate a serialized vector and then entropy encode the quantized transform coefficients of the vector. In other examples, the video encoder 200 may perform an adaptive scan. After scanning the quantized transform coefficients to form the one-dimensional vector, the video encoder 200 may entropy encode the one-dimensional vector, e.g., according to context-adaptive binary arithmetic coding (CABAC). The video encoder 200 may also entropy encode values ​​for syntax elements describing metadata associated with the encoded video data for use by the video decoder 300 in decoding the video data.

[0050] To perform CABAC, the video encoder 200 may assign a context in a context model to a symbol to be transmitted. The context may relate, for example, to whether neighboring values ​​of the symbol are zeroed out or not. The probability determination may be based on the context assigned to the symbol.

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

[0052] In this manner, video encoder 200 may generate a bitstream including syntax elements that describe encoded video data, e.g., partitions of a picture into blocks (e.g., CUs) and predictive and / or residual information for the blocks. Finally, video decoder 300 may receive the bitstream and decode the encoded video data.

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

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

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

[0056] Figure 2 is a conceptual diagram illustrating a hybrid video coding framework. Video coding standards from H.261 onwards are based on the so-called hybrid video coding principle, shown in Figure 2. The term hybrid refers to the combination of two means for reducing redundancy in a video signal, namely transform coding with prediction and quantization of the prediction residual. Prediction and transform reduce redundancy in a video signal by decorrelation, while quantization reduces the data of the transform coefficient representation by reducing its precision, ideally removing only irrelevant details. 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, modern hybrid video coders 130 generally perform block partitioning, motion compensation or inter-picture prediction, intra-picture prediction, transform, quantization, entropy coding, and post / in-loop filtering. In the example of Figure 2, video coder 130 includes a summing unit 134, a transform unit 136, a quantization unit 138, an entropy coding unit 140, an inverse quantization unit 142, an inverse transform unit 144, a summing 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] In general, a video coder 130 may receive input video data 132 when encoding the video data. Block partitioning is used to divide a received picture of video data into smaller blocks for the operation of prediction and transformation processes. Early video coding standards used a fixed block size, typically 16×16 samples. More recent standards, such as HEVC and VVC, use a tree-based partitioning structure to provide flexible partitioning.

[0059] The motion estimation unit 156 and the inter prediction unit 154 may predict the input video data 132, for example, from previously decoded data of the DPB 150. Motion compensation or inter picture prediction exploits the redundancy that exists between pictures of a video sequence (hence "inter"). According to block-based motion compensation used in all modern video codecs, predictions are obtained from one or more previously decoded pictures, i.e., reference pictures. The corresponding area for generating the inter prediction is indicated by motion information including a motion vector and a reference picture index.

[0060] Summation unit 134 may calculate residual data as a difference between the input video data 132 and predicted data from intra prediction unit 152 or inter prediction unit 154. Summation unit 134 provides the residual block to transform unit 136, which applies one or more transforms to the residual block to generate a transform block. Quantization unit 138 quantizes the transform block to form quantized transform coefficients. Entropy coding unit 140 entropy codes the quantized transform 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 block, inverse quantization unit 142 inverse quantizes the quantized transform coefficients, and inverse transform unit 144 inverse transforms the transform coefficients. Summing unit 146 combines the residual block with the predictive block (sample by sample) to generate a decoded block of video data. Loop filter unit 148 applies one or more filters (e.g., at least one of a neural network-based filter, a neural network-based loop filter, a neural network-based post-loop filter, an adaptive in-loop filter, or a predefined adaptive in-loop filter) to the decoded block to generate a filtered decoded block.

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

[0063] In another example, in addition to or as an alternative to the boundary strength value, the neural network filtering unit may receive any or all of coding unit (CU) partition data, prediction unit (PU) partition data, transform unit (TU) partition data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a 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 expressed as a picture order count (POC) difference between the POC values ​​of the pictures.

[0064] The 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 strength 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] A block of video data, such as a CTU or CU, may actually include multiple color components, e.g., a luminance or "luma" component, a blue-phase chrominance or "chroma" component, and a red-phase chrominance (chroma) component. The luma component may have a greater spatial resolution than the chroma components, and one of the chroma components may have a greater spatial resolution than the other chroma component. Alternatively, the luma component may have a greater spatial resolution than the chroma components, and the two chroma components may have equal spatial resolution to each other. For example, in a 4:2:2 format, the luma component may be twice as large as the chroma components in the horizontal direction and equal to the chroma components in the vertical direction. As another example, in a 4:2:0 format, the luma component may be twice as large as the chroma components in the horizontal and vertical directions. The various operations described above may generally be applied to each of the luma and chroma components separately (although 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] 3 is a conceptual diagram illustrating a hierarchical prediction structure 166 using a group of pictures (GOP) size of 16. In recent video codecs, a hierarchical prediction structure inside a group of pictures (GOP) is applied to improve coding efficiency.

[0067] Referring again to Figure 2, intra-picture prediction exploits spatial redundancy present within a picture (hence "intra") by deriving a prediction for a block from spatially neighboring (reference) samples that have already been coded / decoded. 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 prediction residual (regardless of whether the prediction residual comes from inter-picture or intra-picture prediction). Early standards, including H.261, H.262, and H.263, use the discrete cosine transform (DCT). In HEVC and VVC, additional transform kernels other than the DCT are applied to account for different statistics in a particular video signal.

[0069] Quantization aims to reduce the precision of an input value or a set of input values ​​in order to reduce 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 transform coefficients, resulting in integer coefficient levels. In recent video coding standards, the step size is derived from a so-called quantization parameter (QP), which controls the fidelity and bit rate. A larger step size reduces the bit rate, but may also degrade the 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 recent 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 of the filtering process is generally a reconstructed picture, which is a combination of a reconstructed residual signal (including quantization error) and a prediction. As shown in FIG. 2, the reconstructed picture after in-loop filtering is stored and used as a reference for inter-picture prediction of a subsequent picture. The coding artifacts are determined to a large extent by the QP, and therefore the QP information is generally used in the design of the filtering process. In HEVC, the in-loop filter includes deblocking filtering and sample adaptive offset (SAO) filtering. In the VVC standard, an adaptive loop filter (ALF) is introduced as the third filter. The filtering process of the ALF is as follows:

number

number

number

[0072] FIG. 4 is a conceptual diagram showing a neural network-based filter 170 with four layers. Various studies have shown that, for example, embedding a neural network (NN) in the hybrid video coding framework of FIG. 2 can improve compression efficiency. Neural networks have been used in intra-prediction and inter-prediction modules to improve prediction efficiency. In recent years, NN-based in-loop filtering has also been a hot research topic. The filtering process may be 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] The NN-based filter 170 may be applied in addition to existing filters, such as a deblocking filter, sample adaptive offset (SAO), and / or adaptive loop filtering (ALF). The NN-based filter may also be applied exclusively, where the NN-based filter is designed to replace all of the existing filters. Additionally or alternatively, a NN-based filter such as the 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 samples as input, and the intermediate output is the residual sample, which is added back to the input to refine the input sample. The NN filter may use all color components (e.g., Y, U, and V, or Y, Cb, and Cr, i.e., luminance, blue-phase chrominance, and red-phase chrominance) as inputs to exploit inter-component correlation. 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 the NN-based filters may be predefined and stored in the encoder and decoder. The filters may also be signaled in the bitstream.

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

[0077] In general, in accordance with the techniques of this disclosure, the video encoder 200 and the video decoder 300 may include respective filter processing units configured to perform NN-based filtering. The filter processing units may use information generated by other units (e.g., block partition information, motion information, deblocking filter information, or other such information) when performing the NN-based filtering process.

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

[0079] The video encoder 200 and / or the video decoder 300 may include multiple NN-based filtering units, one of which performs NN-based filtering before another (current) NN-based filtering unit, e.g., as shown in FIG 4. 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 the NN filtering.

[0080] The NN-based filtering unit, in various examples, may use any or all of the following information when performing NN-based filtering: partition information of CU, PU, ​​and / or TU, deblocking filtering information (e.g., boundary strength value of the deblocking filtering process, long or short filter, strong or weak filter, etc.), quantization parameter (QP) used for the current picture / block and / or reference picture, intra and / or inter prediction mode information, distance between the current picture and the reference picture used to predict the current picture (e.g., picture order count (POC) value difference), and / or motion information of the coded block. The boundary strength value may also be referred to as boundary filtering strength. In general, the boundary strength value or boundary filtering strength value may represent whether a particular block boundary should be deblocked and, if so, the degree of deblocking to be applied. For example, a relatively strong deblocking filter may modify more values ​​of samples on both sides of the block boundary to a greater extent than a relatively weak deblocking filter.

[0081] In some examples, when the NN-based filtering unit uses information from other units or modules, the NN-based filtering unit may provide some similar functions provided by the 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 examples, the deblocking filter unit may generate boundary strength information but not perform actual filtering. The NN-based filtering unit may receive boundary strength information from the deblocking filter unit and provide the received boundary strength information as an input to the NN-based filter.

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

[0083] Information from other units or modules may be transformed to be more suitable for 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 more suitable for a NN filter (e.g., the boundary strength values ​​of a deblocking filter may be scaled to be in 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] FIG. 5 is a conceptual diagram illustrating an example portion of a picture 180 including boundaries, boundary samples, and interior samples. In particular, the portion of the picture 180 includes vertical boundaries 182A-182D (vertical boundaries 182) and horizontal boundaries 184A-184C (horizontal boundaries 184). As shown in the example of FIG. 5, two adjacent boundary samples (labeled with "N" and shaded gray in FIG. 5) define respective boundaries 182, 184 (represented by a solid black line in FIG. 5) between the two boundary samples. An interior (i.e., non-border) sample is labeled with "M" and unshaded in FIG. 5. The boundary may be a CU boundary, a PU boundary, and / or a TU boundary. The NN-based filtering unit may use the information of the interior / boundary samples and boundary locations illustrated in FIG. 5 when performing the NN-based filtering.

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

[0086] The video encoder 200 and the video decoder 300 may generate multiple partition planes, e.g., one for the CU partition, one for the PU partition, and / or one for the TU partition. In some examples, the planes may be composited, e.g., one plane for the CU partition and another plane for the PU and TU partitions. If “dual tree” partitioning is enabled, in which the luma and chroma components may be partitioned differently (and / or the two chroma components may be partitioned differently from each other), different color components may have different partition planes. The NN-based filter may use any or all of these various planes as input planes to the CNN-based filter. Various examples of working with multiple partition planes include using the partition planes as separate input planes to the CNN-based filter, compositing multiple partition planes into one plane (e.g., for each pixel sample at location (i,j), Plane combined (i,j) = MAX(Plane a (i,j),Plane b(i,j),...), or a combination of separate partition planes and / or composited partition planes (e.g., compositing the CU partition plane and the TU partition plane of each color component into one plane and using multiple composite planes for each color as input to a CNN-based filter). That is, in one example, to composite planes to form a composite input plane, for each input plane position (i,j), video encoder 200 and video decoder 300 may set a value at position (i,j) of the composite input plane equal to the maximum of the values ​​at position (i,j) of the multiple input planes.

[0087] After creating the plane, the values ​​of the plane may be converted as necessary in various examples before being used as input to the CNN-based filter. For example, the values ​​may be converted between integer and floating point, the values ​​may be scaled to have the same range as the input pixel values, and / or the values ​​may be 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 the deblocking filter may be used to derive the boundary strength parameter. The NN-based filter processing unit may use the boundary strength parameter as an additional input plane to the CNN-based filter (e.g., the VVC boundary strength calculation of the DB filter). When the CNN filter is applied, the actual filtering process of the deblocking filter may be disabled.

[0089] First, the deblocking filtering unit may derive boundary strength values ​​for edges that qualify for deblocking filtering. Conversions may be applied as necessary per the examples of the techniques of this disclosure (e.g., converting between integer and floating-point value 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 filtering unit, or another unit of the video codec, may convert the boundary strength value into a plane that can be used with other input planes as input to the CNN-based filter. An example of such a conversion is similar to the conversion described above with respect to FIG. 5, where boundary samples may be set to the boundary strength value and non-boundary samples may be set to 0. For VVC, the range of boundary samples is [0,2].

[0091] The boundary strengths of different color components may be calculated separately, so that horizontal and vertical boundaries may also be calculated separately. Multiple boundary strength planes may be generated for a picture or coded region. Similar to the above description, in one example, the NN-based filter processing unit may choose to use a single input plane or multiple input planes. When multiple planes are used, different methods may be applied to organize the planes. Some examples include using 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), combined (i,j) = MAX(Plane A (i,j), Plane B As another example, given two planes A and B, Plane combined (i,j)=Plane A (i,j)+Plane B As another example, given two planes A and B, R B Let be the range of values ​​in plane B. For each sample position (i,j), combined (i,j)=R B *Plane A (i,j)+Plane B (i,j). In this example, the effect is Plane A Mainly due to Plane Bas a refinement. To combine three or more planes, the techniques described above may be applied multiple times. Also, the techniques described above may be used at different stages. For example, for planes A, B, and C, one technique described above may be used to obtain a combined plane AB, and the other technique described above may be used to combine 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 any of the various techniques described above, and then the boundary intensity planes of the different color components may be provided as separate input planes to the CNN-based filter. As described above, the plane values ​​may be converted as necessary (e.g., converted between integer and floating point and / or scaled to a specific range that may be predefined or signaled in the bitstream).

[0094] In some examples, the long / short filter information may be used as an additional or alternative input plane to the CNN-based filter. Similar to using boundary strengths, information may be generated for the CNN-based filter to be used that uses a long or short deblocking filter, and the multiple planes may be used as separate planes or may be combined before use as CNN filter inputs.

[0095] In some examples, the strong / weak filter information may be used as an additional or alternative input plane to the CNN-based filter. Similar to using boundary strengths, information may be generated for the CNN-based filter to be used that uses a strong or weak deblocking filter, and the multiple planes may be used as separate planes or may be 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 can be generated and used in the CNN filter process: boundary strength (value range: 0, 1, 2), long / short and strong / weak filters (values: 2 for long & strong filters, 1 for short & strong filters, 0 for short & weak filters (in VVC, to have a long filter, the strong filter condition must be met)). 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 composited together.

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

[0098] When downsampling / upsampling of a color plane is required, the corresponding information plane introduced in this disclosure may also be downsampled / upsampled. The downsampling / upsampling may follow the same rules as the corresponding pixel plane. When converting one luma pixel plane into several smaller pixel planes to match the size with chroma, in one example, the video encoder 200 or the video decoder 300 may only keep one downsampled plane instead of keeping all of the planes as luma pixels do.

[0099] 6 is a block diagram illustrating an example video encoder 200 that may perform the techniques of this disclosure. FIG. 6 is provided for purposes of explanation and should not be considered a limitation of the techniques as broadly illustrated and described in this disclosure. For purposes of explanation, this disclosure describes video encoder 200 in the context of video coding standards such as the ITU-T H.265 / HEVC video coding standard and the developing VVC video coding standard. However, the techniques of this disclosure are not limited to these video coding standards and are generally applicable to other video encoding and decoding standards.

[0100] In the example of Figure 6, the video encoder 200 includes a video data memory 230, a mode selection unit 202, a residual generation unit 204, a transform processing unit 206, a quantization unit 208, an inverse quantization unit 210, an inverse transform processing unit 212, a reconstruction unit 214, a filter unit 216, a decoded picture buffer (DPB) 218, and an entropy coding unit 220. Any or all of the video data memory 230, the mode selection unit 202, the residual generation unit 204, the transform processing unit 206, the quantization unit 208, an inverse quantization unit 210, an inverse transform 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 in a processing circuit. 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, an ASIC, or an FPGA. Further, video encoder 200 may include additional or alternative processors or processing circuitry for performing these and other functions.

[0101] The video data memory 230 may store video data to be encoded by the components of the video encoder 200. The video encoder 200 may receive video data stored in the video data memory 230, for example, from the video source 104 (FIG. 1). The DPB 218 may 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 the DPB 218 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 video data memory 230 and the DPB 218 may be provided by the same memory device or separate memory devices. In various examples, the video data memory 230 may be on-chip with other components of the video encoder 200, as shown, or may be off-chip relative to those components.

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

[0103] The various units in FIG. 6 are illustrated to aid in understanding the operations performed by the video encoder 200. The units may be implemented as fixed-function circuits, programmable circuits, or a combination thereof. A fixed-function circuit refers to a circuit that provides a specific function and is preset for the operations that may be performed. A programmable circuit refers to a circuit that may be programmed to perform various tasks and provides flexible functionality in the operations that may be performed. For example, a programmable circuit may execute software or firmware that causes the programmable circuit to operate in a manner defined by the software or firmware instructions. Although a fixed-function circuit may execute software instructions (e.g., to receive a parameter or output a parameter), the type of operation that the fixed-function circuit performs is generally invariant. 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 an integrated circuit.

[0104] The video encoder 200 may include an arithmetic logic unit (ALU), an elementary function unit (EFU), digital circuits, analog circuits, and / or a programmable core formed from programmable circuits. In examples in which the operations of the video encoder 200 are performed using software executed by programmable circuits, the memory 106 (FIG. 1) may store instructions for the software (e.g., object code) 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 may retrieve pictures 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. By way of 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, etc.

[0107] The mode selection unit 202 typically coordinates multiple encoding passes to test combinations of encoding parameters and resulting rate-distortion (RD) values ​​for such combinations. The encoding parameters may include partitioning of the CTU into CUs, prediction modes for the CUs, transform types for residual data of the CUs, quantization parameters for residual data of the CUs, etc. The mode selection unit 202 may finally select a combination of encoding parameters that has a better rate-distortion value than the other tested combinations.

[0108] Video encoder 200 may partition a picture retrieved from video data memory 230 into a series of CTUs and encapsulate one or more CTUs within a slice. Mode selection unit 202 may partition the CTUs of a picture according to a tree structure, such as the QTBT structure or quadtree structure of HEVC described above. As described above, video encoder 200 may form one or more CUs from partitioning the CTUs according to the tree structure. Such a CU may also be generally referred to as a “video block” or a “block.”

[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 prediction block for a current block (e.g., a current CU, or in HEVC, an overlapping portion of a PU and a TU). In the case of inter prediction of the current block, the motion estimation unit 222 may perform motion search to identify one or more closely matching reference blocks in one or more reference pictures (e.g., one or more previously coded pictures stored in the DPB 218). Specifically, the motion estimation unit 222 may calculate a value representing how similar a potential reference block is to the current block according to, for example, a sum of absolute differences (SAD), a sum of squared differences (SSD), a mean absolute difference (MAD), a mean squared difference (MSD), etc. The motion estimation unit 222 may generally perform these calculations using a sample-by-sample difference between the current block and the reference block under consideration. Motion estimation unit 222 may identify the reference block having 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 a current block in a current picture. The motion estimation unit 222 may then provide the motion vectors to the motion compensation unit 224. For example, in the case of unidirectional inter prediction, the motion estimation unit 222 may provide a single motion vector, while in the case of bidirectional inter prediction, the motion estimation unit 222 may provide two motion vectors. The motion compensation unit 224 may then generate a predictive block using the motion vectors. For example, the motion compensation unit 224 may use the motion vectors to retrieve data of the reference block. As another example, in the case of a motion vector having fractional sample precision, the motion compensation unit 224 may interpolate values ​​for the predictive block according to one or more interpolation filters. Furthermore, in the case of bidirectional inter prediction, the motion compensation unit 224 may retrieve data for the two reference blocks identified by the respective motion vectors and combine the retrieved data, for example, by sample-wise averaging or weighted averaging.

[0111] As another example, for intra prediction or intra predictive coding, the intra prediction unit 226 may generate a predictive block from samples neighboring the current block. For example, for a directional mode, the intra prediction unit 226 may generally mathematically combine values ​​of neighboring samples and populate these calculated values ​​in a defined direction across the current block to generate a predictive block. As another example, for a DC mode, the intra prediction unit 226 may calculate an average of the neighboring samples for the current block and generate a predictive block to include this resulting average for each sample of the predictive block.

[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 receives the prediction block from the mode selection unit 202. The residual generation unit 204 calculates sample-by-sample differences between the current block and the prediction block. The resulting sample-by-sample differences define a residual block for the current block. In some examples, the residual generation unit 204 may also determine differences between sample values ​​in the residual block to generate the residual block using residual differential pulse code modulation (RDPCM). In some examples, the residual generation unit 204 may be formed using one or more subtractor circuits that perform binary subtraction.

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

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

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

[0116] As described above, the residual generation unit 204 receives video data for a current block and a corresponding predictive 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 sample-by-sample differences between the predictive block and the current block.

[0117] Transform processing unit 206 applies one or more transforms to the residual block to generate a block of transform coefficients (referred to herein as a "transform coefficient block"). Transform processing unit 206 may apply various transforms to the residual block to form the transform coefficient block. For example, transform processing unit 206 may apply a discrete cosine transform (DCT), a directional transform, a Karhunen-Loeve transform (KLT), or a conceptually similar transform to the residual block. In some examples, transform processing unit 206 may perform multiple transforms, e.g., a primary transform and a secondary transform, such as a rotation transform, on the residual block. In some examples, transform processing unit 206 does not apply a transform to the residual block.

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

[0119] The inverse quantization unit 210 and the inverse transform processing unit 212 may apply inverse quantization and inverse transform, respectively, to the quantized transform coefficient block to reconstruct a residual block from the transform coefficient block. The reconstruction unit 214 may generate a reconstructed block that corresponds to the current block (possibly with some distortion) based on the reconstructed residual block and the predictive block generated by the mode selection unit 202. For example, the reconstruction unit 214 may add samples of the reconstructed residual block to corresponding samples from the predictive block generated by the mode selection unit 202 to generate the reconstructed block.

[0120] Filter unit 216 may perform one or more filter operations on the reconstructed blocks. For example, filter unit 216 may perform a deblocking operation to reduce blockiness artifacts along the edges of a CU. When performing a deblocking operation, filter unit 216 (or its deblocking filter unit) may first calculate a boundary strength value. The deblocking filter unit of filter unit 216 may then use the boundary strength value to generally represent the filtering strength as well as coefficients to be used in the deblocking function and / or deblocking decision function t C and beta (β). The operation of the filter unit 216 may be skipped in some examples.

[0121] The filter unit 216 may be configured to perform various techniques of this disclosure, e.g., to determine one or more of the neural network models (NN models) 232 to 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 an RD cost for determining whether to perform NN model filtering, and then provide data to the entropy encoding unit 220 indicative of, e.g., whether to perform NN model filtering, one or more of the NN models 232 to use for the current picture, etc.

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

[0123] The NN filtering unit may use the additional data (e.g., boundary strength values ​​and / or other data received from other units of the video encoder 200) to select a NN model from the NN models 232 to be used to perform the NN-based filtering, as well as to perform the actual NN-based filtering. For example, the NN filtering unit of the filter unit 216 may provide the additional data (e.g., boundary strength values) to the selected one or more NN models of the NN models 232 in the form of an additional input layer. In some examples, the filter unit 216 may modify the additional data, for example, by converting the representation format (such as between floating point and decimal) or modifying the range of the 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 examples 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 examples 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 reference pictures formed from the reconstructed (and possibly filtered) blocks from the DPB 218 to inter predict blocks of a later-encoded picture. In addition, the intra prediction unit 226 may use the reconstructed blocks in the DPB 218 of the current picture to intra predict other blocks in the current picture.

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

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

[0127] The operations described above are described with respect to blocks. Such descriptions should be understood as being operations for luma coding blocks and / or chroma coding blocks. As described above, in some examples, the luma coding blocks and chroma coding blocks are luma and chroma components of a CU. In some examples, the luma coding blocks and chroma coding blocks are luma and chroma components of a PU.

[0128] In some examples, operations performed with respect to luma coding blocks do not need to be repeated for chroma coding blocks. As an example, operations for identifying motion vectors (MVs) and reference pictures for luma coding blocks do not need to be repeated to identify MVs and reference pictures for chroma coding blocks. Rather, the MVs for the luma coding blocks may be scaled to determine the MVs for the chroma coding blocks, and the reference pictures may be the same. As another example, the intra prediction process may be the same for luma coding blocks and chroma coding blocks.

[0129] 7 is a block diagram illustrating an example video decoder 300 that may perform techniques of this disclosure. FIG. 7 is provided for purposes of illustration and is not intended to limit the techniques as broadly illustrated and described in this disclosure. For purposes of illustration, this disclosure describes a video decoder 300 according to 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 of FIG. 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 transform 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, the entropy decoding unit 302, the prediction processing unit 304, the inverse quantization unit 306, the inverse transform processing unit 308, the reconstruction unit 310, the filter unit 312, and the 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. Additionally, the video decoder 300 may include additional or alternative processors or processing circuits for performing 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 prediction according to other prediction modes. By way of example, the prediction processing unit 304 may include a palette unit, an intra block copy unit (which may form part of the motion compensation unit 316), an affine unit, a linear model (LM) unit, etc. In other examples, the video decoder 300 may include more, fewer, or different functional components.

[0132] The CPB memory 320 may store video data, such as an encoded video bitstream, to be decoded by components of the video decoder 300. The video data stored in the CPB memory 320 may be obtained, for example, from the computer-readable medium 110 (FIG. 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 a coded picture, such as temporary data representing output from various units of the video decoder 300. The DPB 314 generally stores decoded pictures that the video decoder 300 may output and / or use as reference video data when decoding subsequent data or pictures of the encoded video bitstream. The CPB memory 320 and the DPB 314 may be formed by any of a variety of 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 the DPB 314 may be provided by the same memory device or separate memory devices. In various examples, the CPB memory 320 may be on-chip with other components of the video decoder 300 or off-chip relative to those components.

[0133] Additionally or alternatively, in some examples, video decoder 300 may retrieve coded video data from memory 120 (FIG. 1). That is, memory 120 may store data such as those described above with respect to CPB memory 320. Similarly, memory 120 may store instructions to be executed by video decoder 300 when some or all of the functionality of video decoder 300 is implemented in software to be executed by processing circuitry of video decoder 300.

[0134] The various units shown in FIG. 7 are illustrated to aid in understanding the operations performed by the video decoder 300. The units may be implemented as fixed function circuits, programmable circuits, or a combination thereof. As with FIG. 6, a fixed function circuit refers to a circuit that provides a specific function and is preset for the operations that may be performed. A programmable circuit refers to a circuit that may be programmed to perform various tasks and provides flexible functionality in the operations that may be performed. For example, a programmable circuit may execute software or firmware that causes the programmable circuit to operate in a manner defined by the software or firmware instructions. Although a fixed function circuit may execute software instructions (e.g., to receive a parameter or output a parameter), the type of operation that the fixed function circuit performs is generally invariant. 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 ALUs, EFUs, digital circuits, analog circuits, and / or programmable circuits. In examples in which the operations of the video decoder 300 are performed by software executing on programmable circuits, on-chip or off-chip memory may store instructions of the software (e.g., object code) that the video decoder 300 receives and executes.

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

[0137] In general, the video decoder 300 reconstructs a picture on a block-by-block basis. The video decoder 300 may perform a reconstruction operation on each block individually (wherein the block currently being reconstructed, i.e., decoded, may be referred to as the “current block”).

[0138] The entropy decoding unit 302 may entropy decode the quantized transform coefficients of the quantized transform coefficient block, as well as syntax elements defining transform information, such as a quantization parameter (QP) and / or a transform mode indication. The inverse quantization unit 306 may use the QP associated with the quantized transform coefficient block to determine 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 transform coefficients. The inverse quantization unit 306 may thereby form a transform coefficient block including the transform coefficients.

[0139] After the inverse quantization unit 306 forms the transform coefficient block, the inverse transform processing unit 308 may apply one or more inverse transforms to the transform coefficient block to generate a residual block associated with the current block. For example, the inverse transform processing unit 308 may apply an inverse DCT, an inverse integer transform, an inverse Karhunen-Loeve transform (KLT), an inverse rotational transform, an inverse transform, or another inverse transform to the transform coefficient block.

[0140] Further, prediction processing unit 304 generates a prediction block according to the prediction information syntax element entropy decoded by entropy decoding unit 302. For example, if the prediction information syntax element indicates that the current block is inter-predicted, motion compensation unit 316 may generate a prediction block. In this case, the prediction information syntax element may indicate a reference picture in DPB 314 from which to retrieve a reference block, 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. Motion compensation unit 316 may generally perform an inter-prediction process in a manner substantially similar to that described with respect to motion compensation unit 224 (FIG. 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 predictive block according to the intra prediction mode indicated by the prediction information syntax element. Again, the intra prediction unit 318 may generally perform an intra prediction process in a manner substantially similar to that described with respect to the intra prediction unit 226 (FIG. 6). The intra prediction unit 318 may retrieve data of neighboring samples for the current block from the DPB 314.

[0142] The reconstruction unit 310 may reconstruct the current block using the predictive block and the residual block. For example, the reconstruction unit 310 may add samples of the residual block to corresponding samples of the predictive block to reconstruct the current block.

[0143] The filter unit 312 may perform one or more filter operations on the reconstructed block. For example, the filter unit 312 may perform a deblocking operation to reduce blockiness 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 use the NN models 322 to explicitly or implicitly determine whether to perform neural network model filtering, e.g., using any or all of the various techniques described herein. In addition, the video decoder 300 may explicitly or implicitly determine one or more of the NN models 322 and / or a grid size for the current picture to be decoded and filtered. Thus, the filter unit 312 may use one or more of the NN models 322 to filter a portion of the current decoded picture when filtering is switched on.

[0144] In some examples, filter unit 312 may perform a deblocking operation to reduce blockiness artifacts along the edges of a CU, PU, ​​or TU. When performing a deblocking operation, filter unit 312 (or its deblocking filter unit) may first calculate a boundary strength value. The deblocking filter unit of filter unit 312 may then use the boundary strength value to generally represent the filtering strength as well as coefficients to be used in the deblocking function and / or deblocking decision function t C and beta (β). The operation of the filter unit 312 may be skipped in some examples.

[0145] The filter unit 312 may be configured to perform various techniques of this disclosure, for example, to determine one or more of the neural network models (NN models) 322 to 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 of blocks of a particular picture, slice, tile, or other unit.

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

[0147] The NN filtering unit may use the additional data (e.g., boundary strength values ​​and / or other data received from other units of the video decoder 300) to select an NN model from the NN models 322 to be used to perform the NN-based filtering, as well as to perform the actual NN-based filtering. For example, the NN filtering unit of the filter unit 312 may provide the additional data (e.g., boundary strength values) to the selected one or more NN models of the NN models 322 in the form of an additional input layer. In some examples, the filter unit 312 may modify the additional data, for example, by converting the representation format (such as between floating point and decimal) or modifying the range of the 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 examples where the operations of the filter unit 312 are not performed, the reconstruction unit 310 may store the reconstructed blocks in the DPB 314. In examples where the operations of the filter unit 312 are performed, the filter unit 312 may store the refined, filtered, and reconstructed blocks in the DPB 314. As described above, the DPB 314 may provide reference information to the prediction processing unit 304, such as samples of the current picture for intra prediction and previously decoded pictures for subsequent motion compensation. Additionally, 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 of FIG. 1.

[0149] 8 is a flowchart illustrating an example method for encoding a current block according to the techniques of this disclosure. The current block may include a current CU. Although described with respect to video encoder 200 (FIGS. 1 and 3), it should be understood that other devices may be configured to perform a method similar to that of FIG.

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

[0151] Video encoder 200 may also decode the current block after encoding it to use the decoded version of the current block as reference data for later coded data (e.g., in inter-prediction or intra-prediction modes). Accordingly, video encoder 200 may inverse quantize and inverse transform the coefficients to reconstruct the residual block (362). Video encoder 200 may combine the residual block with the predictive block to form a decoded block (364). Video encoder 200 may decode all blocks of the current picture in this manner, thereby forming a fully decoded picture. Video encoder 200 may further filter the decoded picture including the decoded block according to any of the various techniques of this disclosure (366). Video encoder 200 may then store the decoded picture in DPB 218 (368).

[0152] 9 is a flowchart illustrating an example method for decoding a current block according to the techniques of this disclosure. The current block may include a current CU. Although described with respect to the video decoder 300 (FIGS. 1 and 4), it should be understood that other devices may be configured to perform a method similar to that of FIG.

[0153] The video decoder 300 may receive entropy coded data for the current block, such as the entropy coded prediction information and the entropy coded data of the coefficients of the residual block corresponding to the current block (370). The video decoder 300 may entropy decode the entropy coded 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, e.g., using an intra prediction mode or an inter prediction mode as indicated by the prediction information for the current block, to compute a predictive block for the current block (374). The video decoder 300 may then inverse scan the reconstructed coefficients to create a block of quantized transform coefficients (376). The video decoder 300 may then inverse quantize and inverse transform the quantized transform coefficients to generate a residual block (378). The video decoder 300 may finally decode the current block by combining the predictive block and the residual block (380). The video decoder 300 may also filter the decoded video data (382), e.g., using one or more NN models as described above, in accordance with the techniques of this disclosure. The video decoder 300 may further store the (filtered) decoded video data, e.g., in the DPB 314 (384).

[0154] FIG. 10 is a flowchart illustrating an example method of filtering decoded video data according to the techniques of this disclosure. The method of FIG. 10 may be performed by the video encoder 200 or the video decoder 300. For example, the method of FIG. 10 may be performed by a neural network (NN) filtering unit of the filter unit 216 of the video encoder 200, for example, during step 366 of the method of FIG. 8. As another example, the method of FIG. 10 may be performed by a NN filtering unit of the filter unit 312 of the video decoder 300, for example, during step 382 of the method of FIG. 9. For example and explanation purposes, the method of FIG. 10 is described with respect to the video decoder 300, and in particular, the NN filtering unit of the filter unit 312 of the video decoder 300.

[0155] Initially, the NN filtering unit of filter unit 312 receives decoded video data (400). The decoded video data may be at least a portion of a picture, such as a set of blocks, a tile, a slice, one or more slices, one or more tiles, a subpicture, or the entire picture.

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

[0157] Thus, at least a portion may include a number of blocks, including deblocked edges, that have been deblocked, for example, by a deblocking filter of filter unit 312. The deblocking filter may calculate boundary strength values ​​for boundaries between the blocks. The boundary strength values ​​may generally indicate 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 strength values ​​from a 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) partition data, prediction unit (PU) partition data, transform unit (TU) partition data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a distance between the decoded picture and one or more reference pictures (e.g., POC distance), or motion information for one or more decoded blocks of the decoded picture.

[0159] The NN filtering unit of the filter unit 312 may then determine one or more NN models of the neural network (NN) models 322 to be used to filter at least a portion of the current picture (404). The NN filtering unit of the filter unit 312 may then 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 a range of values ​​of the additional data to fit a range of input sample values ​​and / or by converting values ​​of the additional data to a different format, such as integer or floating point. The NN filtering unit of the filter unit 312 may convert the additional data into one or more input planes, as well as the luminance and / or chrominance planes to be filtered.

[0160] In this manner, the method of FIG. 10 represents one example of a method for filtering decoded video data including the steps of receiving, by a neural network filtering unit of the video decoding device, data for a decoded picture of the video data; receiving, by the neural network filtering unit, data from one or more other units of the video decoding device, where the data from the one or more other units is different from the data for the decoded picture, and where receiving the data from the one or more other units includes receiving boundary strength data from a deblocking unit; determining, by the neural network filtering unit, one or more neural network models to be used to filter a portion of the decoded picture; and filtering, by the neural network filtering unit, 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 video decoding device.

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

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

[0163] Clause 2: The method of clause 1, wherein the step of receiving data from the one or more other units includes receiving data from one or more of an intra prediction unit of the video decoding device, an inter prediction unit of the video decoding device, a transform 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 filter processing 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: The method of any of clauses 2 and 3, wherein the loop filter unit includes at least one of a deblocking filtering unit, a sample adaptive offset (SAO) filtering unit, or an adaptive loop filtering (ALF) unit.

[0166] Clause 5: The method of any one of clauses 1 to 4, wherein the step of receiving data includes receiving one or more of coding unit (CU) partition data, prediction unit (PU) partition data, transform unit (TU) partition data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a 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 filter processing data includes one or more of a boundary strength value, whether a long or short filter was used for deblocking, or whether a strong or weak filter was used for deblocking.

[0168] Clause 7: The method of any of clauses 5 and 6, wherein the intra prediction data includes an intra prediction mode.

[0169] Clause 8: Any of the methods of clauses 5 to 7, wherein the data representing the distance includes data representing a difference between a Picture Order Count (POC) value of the decoded picture and a POC value of a reference picture used to predict a block of the decoded picture.

[0170] Clause 9: The method of any of clauses 1 to 8, further comprising the step of performing, by the filtering unit, functions attributed to one or more of the other units.

[0171] Clause 10: The method of any of clauses 1 to 9, wherein 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 includes providing data from the 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: The method of any of clauses 1 to 10, wherein 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 includes adjusting outputs of the one or more neural network models using data from the one or more other units of the video decoding device.

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

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

[0175] Clause 14: The method of any of clauses 12 and 13, wherein adjusting the data includes scaling values ​​of the data to be within a range of values ​​suitable for one or more neural network models.

[0176] Clause 15: The method of any of clauses 1-14, wherein the step of receiving data includes receiving partition 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 includes setting values ​​at positions in the input plane collocated with positions of boundary samples that define partition boundaries in the decoded picture as indicated by the partition data to first values, setting values ​​at positions in the input plane collocated with positions of interior samples that are non-boundary samples to second values, and filtering the portion of the decoded picture using the input plane as an 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 comprises one and the second value comprises zero.

[0178] Clause 17: The method of any of clauses 15 and 16, wherein the partitioning data includes coding unit (CU) partitioning data, and the input plane includes a first partitioning plane, and the method further includes the steps of receiving prediction unit (PU) partitioning data, forming a second input plane using the PU partitioning data, receiving transform unit (TU) partitioning data, and forming a third input plane using the TU partitioning data, and wherein 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 includes filtering a portion of the 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: The method of any of clauses 1-14, wherein the step of receiving data includes receiving deblocking filter 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 includes transforming the deblocking filter data for the decoded picture into one or more input planes for at least one of the one or more neural network models, and using the one or more input planes as inputs to the at least one of the one or more neural network models to filter the portion of the decoded picture.

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

[0181] Clause 20: The method of any of clauses 10 or 15-19, further comprising the step of upsampling or downsampling data in the input plane.

[0182] Clause 21: The method of any of clauses 1-20, 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 determining step includes determining according to a rate-distortion calculation.

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

[0185] Clause 24: The device of clause 23, wherein the one or more means comprise one or more processors implemented in circuitry.

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

[0187] Clause 26: The device of clause 23, wherein the device comprises one or more of 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 a memory configured to store the video data.

[0189] Clause 28: A computer-readable storage medium storing instructions that, when executed, cause a processor to perform any of the methods of clauses 1 to 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 the video decoding device, means for determining one or more neural network models to be used for filtering a portion of a decoded picture of the video data, and means for filtering the portion of the decoded picture using the one or more neural network models and data from the one or more other units of the video decoding device.

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

[0192] Clause 31: The method of clause 30, wherein the step of receiving data from the one or more other units of the video decoding device further comprises receiving data from one or more of an intra prediction unit of the video decoding device, an inter prediction unit of the video decoding device, a transform 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 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) filtering unit or an adaptive loop filtering (ALF) unit.

[0194] Clause 33: The method of clause 32, wherein the step of receiving data further includes receiving one or more of coding unit (CU) partitioning data, prediction unit (PU) partitioning data, transform unit (TU) partitioning data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a 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 filter 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, wherein the intra prediction data includes an intra prediction mode.

[0197] Clause 36: The method of clause 33, wherein the data representing the distance comprises data representing a difference between a Picture Order Count (POC) value of the decoded picture and a POC value of a reference picture used to predict a block of the decoded picture.

[0198] Clause 37: The method of clause 30, wherein 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 includes providing data from the 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 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 includes adjusting outputs of the one or more neural network models using data from the one or more other units of the video decoding device.

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

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

[0202] Clause 41: The method of clause 39, wherein adjusting the data includes scaling values ​​of the data to be 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 receiving partition 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 includes setting values ​​at positions in the input plane collocated with positions of boundary samples that define partition boundaries in the decoded picture as indicated by the partition data to a first value, setting values ​​at positions in the input plane collocated with positions of interior samples that are non-boundary samples to a second value, and filtering the portion of the decoded picture using the input plane as an 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 comprises one and the second value comprises zero.

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

[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 determining the one or more neural network models comprises determining the one or more neural network models according to a rate-distortion calculation.

[0209] Clause 48: A device for filtering decoded video data comprising: a memory configured to store a decoded picture of the video data; and one or more processors implemented in a circuit, wherein 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 the decoded picture; 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.

[0210] Clause 49: The device of clause 48, wherein to receive data from one or more other units of the device, the one or more processors are further configured to execute the neural network filtering unit to receive data from one or more of an intra prediction unit of the device, an inter prediction unit of the device, a transform processing unit of the device, a quantization unit of the device, a loop filter unit of the device, a pre-processing unit of the device, or a second neural network filtering unit of the device.

[0211] Clause 50: The device of clause 48, wherein to receive data from one or more other units of the device, the one or more processors are further configured to execute a neural network filtering unit to receive one or more of coding unit (CU) partition data, prediction unit (PU) partition data, transform unit (TU) partition data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture.

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

[0214] Clause 53: The device of clause 48, wherein the one or more processors are configured to execute the neural network filtering unit to condition the data from the one or more other units of the device prior to 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 device.

[0215] Clause 54: The device of clause 48, wherein to filter a portion of a decoded picture using the one or more neural network models and data from one or more other units of the device, the one or more processors are configured to execute a neural network filtering unit to convert deblocking filter data for the decoded picture from the 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 inputs to the at least one of the one or more neural network models.

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

[0217] Clause 56: The device of clause 48, wherein the device comprises one or more of a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

[0218] Clause 57: A computer-readable storage medium having instructions stored thereon that, when executed, cause a processor of a video decoding device to perform a neural network filtering unit to receive data for a decoded picture of the video data; receive data from one or more other units of the video decoding device, where the data from the one or more other units of the video decoding device is different from the data for the decoded picture, and the instructions to cause the processor to receive data from the one or more other units of the video decoding device include instructions to cause the processor to receive boundary strength 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 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 video decoding device.

[0219] Clause 58: A device for filtering decoded video data, comprising: 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, where the data from the one or more other units is different from the data for the decoded picture, and the means for receiving data from the one or more other units of the video decoding device comprises means for receiving boundary strength 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 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 video decoding device.

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

[0221] Clause 60: The method of clause 59, wherein the step of receiving data from the one or more other units of the video decoding device further comprises receiving data from one or more of an intra prediction unit of the video decoding device, an inter prediction unit of the video decoding device, a transform 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 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) filtering unit or an adaptive loop filtering (ALF) unit.

[0223] Clause 62: The method of any of clauses 59 to 61, wherein the step of receiving data further comprises receiving one or more of coding unit (CU) partitioning data, prediction unit (PU) partitioning data, transform unit (TU) partitioning data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a 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 filter 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: The method of any of clauses 62 and 63, wherein the intra prediction data includes an intra prediction mode.

[0226] Clause 65: Any of the methods of clauses 62 to 64, wherein the data representing the distance comprises data representing a difference between a Picture Order Count (POC) value of the decoded picture and a POC value of a reference picture used to predict a block of the decoded picture.

[0227] Clause 66: The method of any of clauses 59 to 65, wherein 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 the video decoding device includes providing data from the 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: The method of any of clauses 59 to 66, wherein 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 comprises adjusting the output of the one or more neural network models using data from the one or more other units of the video decoding device.

[0229] Clause 68: The method of any of clauses 59-67, further comprising conditioning data from one or more other units of the video decoding device prior to filtering the portion of the decoded picture.

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

[0231] Clause 70: The method of any of clauses 68 and 69, wherein adjusting the data includes scaling values ​​of the data to be within a range of values ​​suitable for one or more neural network models.

[0232] Clause 71: The method of any of clauses 59-70, wherein the step of receiving data includes receiving partition 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 includes setting values ​​at positions in the input plane collocated with positions of boundary samples that define partition boundaries in the decoded picture as indicated by the partition data to first values, setting values ​​at positions in the input plane collocated with positions of interior samples that are non-boundary samples to second values, and filtering the portion of the decoded picture using the input plane as an 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 comprises one and the second value comprises zero.

[0234] Clause 73: The method of any of clauses 71 and 72, wherein the partitioning data comprises coding unit (CU) partitioning data, and the input plane comprises a first partitioning plane, and the method further comprises the steps of receiving prediction unit (PU) partitioning data, forming a second input plane using the PU partitioning data, receiving transform unit (TU) partitioning data, and forming a third input plane using the TU partitioning data, and wherein 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 comprises filtering a portion of the 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: The method of any of clauses 59 to 73, wherein the step of filtering the portion of the decoded picture using the one or more neural network models and data from one or more other units of the video decoding device includes the steps of converting deblocking filter data for the decoded picture from the deblocking unit into one or more input planes for at least one of the one or more neural network models, and filtering the portion of the decoded picture using the one or more input planes as inputs to the at least one of the one or more neural network models.

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

[0237] Clause 76: The method of any of clauses 59 to 75, wherein determining the one or more neural network models comprises determining the one or more neural network models according to a rate-distortion calculation.

[0238] Clause 77: A device for filtering decoded video data comprising: a memory configured to store a decoded picture of the video data; and one or more processors implemented in a circuit, the one or more processors 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 the decoded picture; the one or more processors 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.

[0239] Clause 78: The device of clause 77, wherein to receive data from one or more other units of the device, the one or more processors are further configured to execute the neural network filtering unit to receive data from one or more of an intra prediction unit of the device, an inter prediction unit of the device, a transform processing unit of the device, a quantization unit of the device, a loop filter unit of the device, a pre-processing unit of the device, or a second neural network filtering unit of the device.

[0240] Clause 79: The device of any of clauses 77 and 78, wherein to receive data from one or more other units of the device, the one or more processors are further configured to execute a neural network filtering unit to receive one or more of coding unit (CU) partition data, prediction unit (PU) partition data, transform unit (TU) partition data, deblocking filtering data, quantization parameter (QP) data, intra prediction data, inter prediction data, data representing a distance between the decoded picture and one or more reference pictures, or motion information for one or more decoded blocks of the decoded picture.

[0241] Clause 80: The device of any of clauses 77 to 79, wherein the one or more processors are configured to execute a neural network filtering unit to provide data from the one or more other units of the device as one or more additional input planes to a convolutional neural network (CNN) 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: The device of any of clauses 77 to 80, wherein the one or more processors are configured to execute a neural network filtering unit to adjust the output of the one or more neural network models using data from the one or more other units of the device to filter a portion of a decoded picture using the one or more neural network models and data from the one or more other units of the device.

[0243] Clause 82: The device of any of clauses 77 to 81, wherein the one or more processors are configured to execute the neural network filtering unit to condition the data from the one or more other units of the device prior to 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 device.

[0244] Clause 83: The device of any of clauses 77 to 82, wherein, to filter a portion of a decoded picture using the one or more neural network models and data from one or more other units of the device, the one or more processors are configured to execute a neural network filtering unit to convert deblocking filter data for the decoded picture from the 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 inputs to the at least one of the one or more neural network models.

[0245] Clause 84: The device of any of clauses 77 to 83, further comprising a display configured to display decoded pictures of the video data.

[0246] Clause 85: The device of any of clauses 77 to 84, wherein the device comprises one or more of a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box.

[0247] It should be appreciated that, depending on the example, some acts or events of any of the techniques described herein may be performed in a different sequence, or may be added, combined, or omitted entirely (e.g., not all acts or events described are necessary to the practice of the techniques). Furthermore, in some examples, acts or events may be performed simultaneously rather than sequentially, e.g., through multi-threaded processing, interrupt processing, 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 on or transmitted via a computer-readable medium as one or more instructions or code and executed by a hardware-based processing unit. A computer-readable medium may include a computer-readable storage medium corresponding to a tangible medium, such as a data storage medium, or a communication medium including any medium that facilitates transfer of a computer program from one place to another, for example according to a communication protocol. Thus, a computer-readable medium may generally correspond to (1) a tangible computer-readable storage medium that is non-transitory, or (2) a communication medium such as a signal or carrier wave. A 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, code and / or data structures for implementation of the techniques described in this disclosure. A computer program product may include a computer-readable medium.

[0249] By way of example and not limitation, such computer-readable storage media may comprise 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 may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer. Also, any connection is properly referred to as a computer-readable medium. 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, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but instead cover non-transitory tangible storage media. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically and discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer readable media.

[0250] The 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 circuitry. Thus, the terms "processor" and "processing circuitry" as used herein may refer to any of the above structures or any other structures suitable for implementing the techniques described herein. In addition, in some aspects, the functionality described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or may be incorporated into a composite codec. Also, the techniques may be fully implemented in one or more circuits or logic elements.

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

[0252] Various examples have been described. These and other examples are within the scope of the following claims. [Explanation of symbols]

[0253] 100 Video encoding and decoding system, system 102 Source Device 104 Video Sources 106 Memory 108 Output Interface 110 Computer-readable medium 112 Storage Devices 114 File Server 116 Destination Device 118 Display Devices 120 Memory 122 Input Interface 130 Hybrid Video Coder, Video Coder 132 input video data 134 Addition Unit 136 Conversion Units 138 quantization units 140 Entropy Coding Units 142 Inverse Quantization Unit 144 Reverse conversion unit 146 Addition Unit 148 Loop Filter Unit 150 Decoded Picture Buffer (DPB), DPB 152 intra prediction units 154 Inter Prediction Units 156 Motion Estimation Unit 158 output bitstream 166 Hierarchical 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 Encoder 202 Mode Selection Unit 204 Residual Generation Unit 206 Conversion Processing Unit 208 Quantization Units 210 Inverse Quantization Unit 212 Inverse Transformation Processing Unit 214 Reconstruction Unit 216 Filter unit 218 Decoded Picture Buffer (DPB), DPB 220 Entropy Coding Unit 222 Motion Estimation Unit 224 Motion Compensation Unit 226 intra prediction units 230 Video Data Memory 232 Neural network model (NN model), NN model 300 Video Decoder 302 Entropy Decoding Unit 304 Prediction Processing Unit 306 Inverse Quantization Unit 308 Inverse Transformation Processing Unit 310 Reconstruction Unit 312 Filter unit 314 Decoded Picture Buffer (DPB), DPB 316 Motion Compensation Unit 318 Intra Prediction Units 320 Coded Picture Buffer (CPB) memory, CPB memory 322 Neural Network (NN) Model, NN Model

Claims

1. 1. A method for filtering decoded video data, comprising the steps of: receiving data for a decoded picture of the video data by a neural network filtering unit of the video decoding device; receiving, by the neural network filtering unit, data from one or more other units of the video decoding device, wherein the data from the one or more other units differs from the data for the decoded picture, and wherein receiving the data from the one or more other units of the video decoding device includes receiving boundary strength data from a deblocking unit of the video decoding device; determining, by the neural network filtering unit, one or more neural network models to be used for filtering the portion of the decoded picture; filtering, by the neural network filtering unit, 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 video decoding device; The method includes:

2. receiving the data from the one or more other units of the video decoding device, an intra prediction unit of the video decoding device; an inter prediction unit of the video decoding device; a transform processing unit of said video decoding device; a quantization unit of said video decoding device; a loop filter unit of the video decoding device; a pre-processing unit of said video decoding device; or a second neural network filtering unit of the video decoding device; receiving said data from one or more of: The method of claim 1 , wherein the loop filter unit includes at least one of a sample adaptive offset (SAO) filtering unit or an adaptive loop filtering (ALF) unit.

3. The step of receiving the data comprises: Coding unit (CU) division data, Prediction unit (PU) partition data, Conversion unit (TU) division data, Deblocking filtered data, Quantization parameter (QP) data, Intra prediction data, Inter prediction data, data representative of a distance between the decoded picture and one or more reference pictures; or motion information for one or more decoded blocks of the decoded picture and receiving one or more of: 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; the intra prediction data includes an intra prediction mode; 2. The method of claim 1, wherein the data representing the distance comprises data representing a difference between a Picture Order Count (POC) value of the decoded picture and a POC value of a reference picture used to predict a block of the decoded picture.

4. 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, providing the data from the one or more other units of the video decoding device as one or more additional input planes to a convolutional neural network (CNN); or combining a plurality of input planes into a composite input plane, the step including, for each position (i,j) of the plurality of input planes, setting a value of the position (i,j) of the composite input plane equal to a maximum of values ​​at the position (i,j) of the plurality of input planes; providing the composite input plane to a convolutional neural network (CNN); or adjusting outputs of the one or more neural network models using the data from the one or more other units of the video decoding device. The method of claim 1.

5. adjusting the data from the one or more other units of the video decoding device prior to filtering the portion of the decoded picture; adjusting the data, converting said data values ​​between integer and floating point representations; or Scaling the values ​​of the data to be within a range of values ​​suitable for the one or more neural network models.

2. The method of claim 1, comprising:

6. wherein the step of receiving data includes receiving partition data for the decoded picture, and wherein 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: setting a value at a location in the input plane collocated with a location of a boundary sample that defines a partition boundary in the decoded picture as indicated by the partition data to a first value; setting values ​​at locations in the input plane that are collocated with locations of interior samples that are non-boundary samples to a second value; filtering the portion of the decoded picture using the input plane as an input to at least one of the one or more neural network models; 2. The method of claim 1, comprising:

7. The method of claim 6 , wherein the first value comprises one and the second value comprises zero.

8. The partition data includes coding unit (CU) partition data, the input plane includes a first partition plane, and the method further comprises: receiving prediction unit (PU) partition data; forming a second input plane using the PU partition data; receiving transform unit (TU) partition data; forming a third input plane using the TU partition data; Further comprising: 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 filtering the portion of the 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. The method of claim 6.

9. 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, transforming deblocking filter data for the decoded picture from the deblocking unit into one or more input planes for at least one of the one or more neural network models; filtering the portion of the decoded picture using the one or more input planes as inputs to the at least one of the one or more neural network models; 2. The method of claim 1, comprising:

10. encoding a current picture; decoding the current picture to form the decoded picture; Further comprising: The method of claim 1 , wherein determining the one or more neural network models comprises determining the one or more neural network models according to a rate-distortion calculation.

11. The boundary strength data is indicates a boundary strength value of 0, or The method of claim 1 , wherein the boundary strength value indicates 1 or 2.

12. 1. A device for filtering decoded video data, comprising: a memory configured to store decoded pictures of the video data; and one or more processors implemented in a circuit, the one or more processors executing a neural network filtering unit to: receiving data from one or more other units of the device, the data from the one or more other units of the device being different from data for the decoded picture, and wherein to receive the data from the one or more other units of the device, the one or more processors are configured to execute the neural network filtering unit to receive boundary strength data from a deblocking unit of the device; determining one or more neural network models to be used to filter the portion of the decoded picture; filtering 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; A device configured to:

13. The device of claim 12, further configured to execute a method according to any one of claims 2 to 11.

14. and / or a display configured to display the decoded pictures of the video data. The device of claim 12 , 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. 12. A computer-readable storage medium having stored thereon instructions which, when executed, cause a processor of a video decoding device to execute a neural network filtering unit to perform the method of any one of claims 1 to 11.

Images