Abstract: Disclosed are a coding management method and apparatus based on High Efficiency Video Coding (HEVC). The method includes: obtaining a calculated correlation result for a HEVC basic unit before and after division, the correlation result including a spatial correlation result for the basic unit before the division and N basic units generated after the division, and N being an integer greater than 1; and judging whether or not to perform the division on the basic unit according to the calculated correlation result.

Abstract: A method comprising: encoding video media content into at least a first representation and a second representation, wherein the first representation comprises a switchable inter-coded picture, wherein the switchable picture has a first characteristic that no pictures preceding the switchable picture in decoding order are used as reference pictures for any non-switchable pictures following the switchable picture in decoding order; and the second representation comprises one or more decoder reset pictures aligned with the switchable pictures of the first representation, wherein the frame rate of the second representation is smaller than or equal to the frame rate of the first representation and the resolutions of the first and the second representation are equal.

Abstract: Systems and methods for deep neural network (DNN)-based cross component prediction are provided. A method includes inputting a reconstructed luma block of an image or video into a DNN; and predicting, by the DNN, a reconstructed chroma block of the image or video based on the reconstructed luma block that is input. Luma and chroma reference information and side information may also be input into the DNN to predict the reconstructed chroma block. The various inputs may also be generated using processes such as downsampling and transformation.

Abstract: A method for deblocking at least one boundary of a coding unit, wherein the boundary forms a first side and a second side of the coding unit, wherein a video picture comprises the coding unit, and wherein the first and second sides use a same reference picture. The method includes obtaining a first motion vector component in the first side; obtaining a second motion vector component in the second side; determining whether an absolute difference between the first motion vector component and the second motion vector component is equal to or larger than a predetermined threshold that is less than 1 sample; and as a result of determining that the absolute difference between the first motion vector component and the second motion vector component is equal to or larger than the predetermined threshold, applying deblocking to the vertical or horizontal boundary between the first side and the second side.

Abstract: An image encoding/decoding method and apparatus for predicting a second color component block using a first color component block are provided. An image decoding method of the present invention comprises deriving a prediction parameter using the first color component block, and predicting the second color component block using the derived prediction parameter.

Abstract: An image decoding method performed by a decoding apparatus, according to the present document, comprises the steps of: acquiring syntax elements for a first transform coefficient through an n-th transform coefficient of a current block, wherein the syntax elements are syntax elements according to a first residual data coding structure of TSRC; and acquiring syntax elements for an n+1st transform coefficient through a last transform coefficient of the current block, wherein the syntax elements are syntax elements according to a second residual data coding structure of the TSRC, wherein the number of context-coded syntax elements for the first transform coefficient through the n-th transform coefficient is equal to the maximum number of context-coded bins of the current block, and the syntax elements according to the second residual data coding structure include coefficient level information and a sign flag for a transform coefficient.

Abstract: An image decoding method performed by a decoding apparatus according to the present disclosure includes receiving a bitstream including residual information; deriving quantized transform coefficients for a current block based on the residual information included in the bitstream; deriving residual samples for the current block based on the quantized transform coefficients; and generating a reconstructed picture based on the residual samples for the current block.

Abstract: Video processing methods and apparatuses for coding a current block and a adjacent block comprise receiving input data of the current and adjacent blocks in a current picture, determines the current and adjacent blocks are both coded in a BDPCM or RDPCM mode, performing a deblocking filtering operation on an edge between the current and adjacent blocks by de-activating deblocking filtering for a first color component and activating deblocking filtering for a second color component, and encoding or decoding the current and adjacent blocks. Each current pixel in a BDPCM coded block is predicted by one or more neighboring pixels of the current pixel. RDPCM is applied to process quantized residues of a RDPCM coded block according to a prediction direction of the RDPCM coded block.

Abstract: A video coding device, comprising a sequence of filters that are configurable by one or more primary parameters and one or more secondary parameters, and a filter controller configured to adjust the one or more secondary parameters based on the one or more primary parameters and based on a strength criterion of the sequence of filters.

Abstract: The disclosure discloses a method for processing a video signal and an apparatus therefor. Specifically, a method of processing a video signal based on inter prediction includes constructing a first merge candidate list of a current block using a spatial merge candidate and temporal merge candidate of the current block, constructing a second merge candidate list by adding a history-based merge candidate indicating motion information of a block coded prior to the current block to the first merge candidate list, obtaining a merge index indicating a merge candidate applied to the current block within the second merge candidate list, and generating a prediction block of the current block using motion information of a merge candidate indicated by the merge index.

Abstract: An encoder includes circuitry and memory. In both of a first type of residual coding where an orthogonal transform is applied and a second type of residual coding where the orthogonal transform is skipped, wherein when a restriction on a number of CABAC processes allows CABAC coding of a set of coefficient information flags, the circuitry: encodes the coefficient information flags by CABAC; and otherwise, the circuitry: skips the CABAC encoding of the coefficient information flags; and the circuitry encodes a remainder value of the coefficient with Golomb-Rice code when the coefficient information flags are encoded; and otherwise the circuitry encodes a value of the coefficient with the Golomb-Rice code, wherein in the second type of residual coding, the circuitry encodes absolute value flags each relating to an absolute value of the coefficient after encoding the coefficient information flags and before encoding the remainder value of the coefficient.

Abstract: Interpolation between explicitly signaled CPB (or HRD) parameters at selected bit rates is used to achieve a good compromise between CPB parameter transmission capacity and CPB parametrization effectiveness and may be, particularly, made in an effective manner.

Abstract: An image decoding method according to the present document may comprise the steps of: deriving an intra prediction mode of a chroma block as a cross-component linear model (CCLM) mode on the basis of intra prediction mode information; updating the intra prediction mode of the chroma block on the basis of an intra prediction mode of a luma block corresponding to the chroma block; when the chroma block is not square, remapping the updated intra prediction mode to a wide-angle intra prediction mode; and determining an LFNST set including LFNST matrices on the basis of the remapped intra prediction mode.

Abstract: Video data may be palette decoded. Data defining a palette table may be received. The palette table may comprise index values corresponding to respective colors. Palette index prediction data may be received and may comprise data indicating index values for at least a portion of a palette index map mapping pixels of the video data to color indices in the palette table. The palette index prediction data may comprise run value data associating run values with index values for at least a portion of a palette index map. A run value may be associated with an escape color index. The palette index map may be generated from the palette index prediction data at least in part by determining whether to adjust an index value of the palette index prediction data based on a last index value. The video data may be reconstructed in accordance with the palette index map.

Abstract: Devices, systems and methods for sub-block based prediction are described. In a representative aspect, a method for video encoding includes partitioning, based on a first rule, a luma component of a block of video data into a first set of sub-blocks. The method also includes partitioning, based on a second rule, a first chroma component of the block of video data into a second set of sub-blocks. The first and the second set of sub-blocks include different numbers of sub-blocks. The method also includes performing a subsequent motion prediction based on the first and the second set of sub-blocks.

Abstract: A mechanism is provided that implements video coding and decoding such that only a specific partial image region on a screen can be independently decoded. A video decoding apparatus (31) according to an aspect of the present invention configures, in intra prediction, inter prediction, loop filter processing, or the like, a partial image region in a picture, handles a region outside the partial image region in a similar manner to a region outside the picture, and does not apply such restriction to a non-partial image region other than the partial image region in the picture.

Abstract: Aspects of the disclosure provide a method, an apparatus, and a non-transitory computer-readable storage medium for video decoding. The apparatus can include processing circuitry. The processing circuitry is configured to decode first neural network update information in a coded bitstream for a first neural network in the video decoder. The first neural network is configured with first pretrained parameters. The first neural network update information corresponds to a first block in an image to be reconstructed and indicates a first replacement parameter corresponding to a first pretrained parameter in the first pretrained parameters. The processing circuitry is configured to update the first neural network in the video decoder based on the first replacement parameter. The processing circuitry can decode the first block based on the updated first neural network for the first block.

Abstract: A decoding method for decoding a block of an image is disclosed that comprises: determining a split mode for said block in a set of split modes; splitting said block into at least two sub-blocks responsive to said split mode; decoding each of the at least two sub-blocks; wherein said set of split modes comprises at least one split mode for asymmetrically splitting said block into the at least two sub-blocks.

Abstract: A method includes receiving a block comprising pixels; encoding the pixels by: arranging the pixels in a sequence; generating a delta encoding of the pixels, the delta encoding comprising (a) a base value and (b) delta values having non-zero delta values and zero delta values, each delta value representing a difference between a corresponding pixel in the sequence and a previous pixel in the sequence; generating a symbol mask indicating whether each of the delta values is zero or non-zero; determining, based on magnitudes of the non-zero delta values, a symbol width for encoding each of the non-zero delta values; generating a sequence of symbols that respectively encode the non-zero delta values using the symbol width; generating a compression of the block by collating the symbol mask, the symbol width, and the sequence of symbols.

Abstract: A decoding method performed by a decoding device according to the present document comprises: a step for determining the prediction mode of a current block on the basis of information on a prediction mode acquired from a bitstream; a step for deriving movement information on the current block on the basis of the prediction mode; a step for generating prediction samples of the current block on the basis of the movement information; and a step for generating reconstructed samples on the basis of the prediction samples, wherein the step for determining the prediction mode may include a step for acquiring a regular merge flag from the bitstream on the basis of a combined inter-picture merge and intra-picture prediction (CIIP) available flag that indicates whether or not a CIIP is available.

Abstract: Methods and systems for canvas size scalability across the same or different bitstream layers of a video coded bitstream are described. Offset parameters for a conformance window, a reference region of interest (ROI) in a reference layer, and a current ROI in a current layer are received. The width and height of a current ROI and a reference ROI are computed based on the offset parameters and they are used to generate a width and height scaling factor to be used by a reference picture resampling unit to generate an output picture based on the current ROI and the reference ROI.

Abstract: An image decoding method includes: deriving an L0 motion vector and a L1 motion vector of the current block; deriving prediction samples of the current block based on the L0 motion vector and the L1 motion vector; and generating reconstructed samples of the current block based on the prediction samples. Deriving the prediction samples includes applying bi-directional optical flow (BDOF) to the current block based on whether the condition for applying BDOF to the current block is satisfied, and the application condition of the BDOF includes a condition whereby the values of L0 luma weighted prediction flag information and L1 luma weighted prediction flag information are both zero, where the a value of each of the L0 luma weighted prediction flag information and L1 luma weighted prediction flag information being 0 represents that a weight factor for each of a L0 and L1 prediction luma components does not exist, respectively.

Abstract: Coding techniques for 360-degree video are described. An encoder selects a projection format and maps the 360-degree video to a 2D planar video using the selected projection format. The encoder encodes the 2D planar video in a bitstream and further signals, in the bitstream, parameters identifying the projection format. The parameters identifying the projection format may be signaled in a video parameter set, sequence parameter set, and/or picture parameter set of the bitstream. Different projection formats that may be signaled include formats using geometries such as equirectangular, cubemap, equal-area, octahedron, icosahedron, cylinder, and user-specified polygon. Other parameters that may be signaled include different arrangements of geometric faces or different encoding quality for different faces. Corresponding decoders are also described. In some embodiments, projection parameters may further include relative geometry rotation parameters that define an orientation of the projection geometry.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. The processing circuitry determines that a non-interleaved separate tree structure is used for coding different color components of coding tree units (CTUs) in a bitstream. The processing circuitry decodes a first color component of a plurality of CTUs from a first portion of the bitstream, and decodes a second color component of the plurality of CTUs from a second portion of the bitstream, the second portion is located after the first portion in the bitstream.

Abstract: A versatile video coding (VVC) method includes obtaining a plurality of video sources; encoding the plurality of video sources into a bitstream including a plurality of independent layers corresponding to the plurality of video sources; generating signaling information on the plurality of independent layers and integrating the signaling information with the bitstream; and transferring the bitstream for decoding processing, wherein the signaling information is to be used in the decoding process to enable a single decoder instance to decode the plurality of independent layers similar to a single-layer bitstream. The signaling information includes at least a video parameter set (VPS), and the VPS includes a flag inbl_one_pic_per_poc_flag equal to 1, which specifies that the bitstream contains independent layers and there is one and only one coded picture with a particular picture order count (POC) value in a same coded video sequence (CVS) among all layers.

Abstract: Video processing methods include receiving input data of a current block in a current slice, determine determining whether one or more components of the current block satisfy one or more predefined criteria during partitioning, and applying a mode constraint to the current block only if the one or more components of the current block satisfy the one or more predefined criteria, wherein the mode constraint restricts all blocks within the current block to be processed by a same prediction mode when the current block is split into a plurality of blocks. The methods adaptively split the current block into one or more blocks, and pare one or more prediction mode syntax elements of a first block in the current block according to a constrained mode of the current block. The methods further encode the current block with the mode constraint.

Abstract: Disclosed are techniques for compressing data of an image. Intermediate pixels may be determined. Each location of the image may be associated with a block of a plurality of blocks of a first size and a block of a plurality of blocks of a second size. For each block of the first size and of the second size, a first cost for a first mode and a second cost for a second mode may be determined in parallel using the intermediate pixels. A final mode and a final block size may be selected for each location of the image using the first cost and the second cost for each of a respective block of the first size and a respective block of the second size associated with a corresponding location. Final pixels may be determined, and a representation of the image may be obtained based on the final pixels.

Abstract: A method of three-dimensional (3D)-Tree coding for neural network model compression, is performed by at least one processor, and includes reshaping a four-dimensional (4D) parameter tensor of a neural network into a 3D parameter tensor of the neural network, the 3D parameter tensor comprising a convolution kernel size, an input feature size, and an output feature size, partitioning the 3D parameter tensor along a plane that is formed by the input feature size and the output feature size into 3D coding tree units (CTU3Ds), partitioning each of the CTU3Ds into a plurality of 3D coding units (CU3Ds) recursively until a predetermined depth, using a quad-tree, and constructing a 3D tree for each of the plurality of CU3Ds, wherein the 3D tree for each of the plurality of CU3Ds is a 3D-Unitree.

Abstract: Systems and methods are described for video coding using affine motion prediction. In an example method, motion vector gradients are determined from respective motion vectors of a plurality of neighboring sub-blocks neighboring a current block. An estimate of at least one affine parameter for the current block is determined based on the motion vector gradients. An affine motion model is determined based at least in part on the estimated affine parameter(s), and a prediction of the current block is generated using the affine motion model. The estimated parameter(s) may be used in the affine motion model itself. Alternatively, the estimated parameter(s) may be used in a prediction of the affine motion model. In some embodiments, only neighboring sub-blocks above and/or to the left of the current block are used in estimating the affine parameter(s).

Abstract: An encoder which encodes a video including a plurality of pictures includes circuitry and memory. Using the memory, the circuitry performs: encoding a first picture among the plurality of pictures; and performing (i) a first operation for encoding a parameter set for a second picture which follows the first picture in coding order among the plurality of pictures after encoding the first picture, and encoding the second picture after encoding the parameter set, or (ii) a second operation for encoding the second picture without encoding the parameter set after encoding the first picture. The circuitry performs the first operation when the second picture is a determined picture, in the performing of the first operation or the second operation.

Abstract: A method and apparatus for performing intra prediction for encoding or decoding adds multiple prediction modes to those of prior intra prediction schemes. A horizontal mode, a vertical mode, and a diagonal mode are added. Reference pixels for each of the added modes can come from multiple pixel positions away from a block to be encoded or decoded. Reference pixels to the left and above a block are reconstructed from those already coded. Reference pixels from right of, and below, a block are estimated or extrapolated and can be based on other pixels around the block. An index can be sent in a bitstream indicating which prediction was used.

Abstract: A method and apparatus for decoding multiple semantically independent picture parts into a single video picture includes decoding unique picture order count values for each coded picture, coded slice, or coded tile in a coded video sequence, with multiple decoded pictures, cycles, and tiles belonging to a same access unit representing a frame of the video. A value representing the amount of pictures, cycles, or tiles, is then assigned to each access unit for assigning sequential access unit count values to the access units. As a result, each access unit, which represents multiple pictures, slices, or tiles to be combined into a single frame, is decoded for display processing.

Abstract: Methods and apparatus for processing of video are described. The processing may include video encoding, decoding or transcoding. One example video processing method includes performing a conversion between a video including a current picture including a current subpicture including a current slice and a bitstream of the video. The bitstream conforms to a format rule that disallows an active entry in a reference picture list of the current slice from including a first picture that precedes in a decoding order a second picture that includes a step-wise temporal sublayer access subpicture in response to conditions associated with at least the first picture and the current subpicture.

Abstract: A method and for reconstructing chroma blocks and a video decoding apparatus are disclosed. In accordance with one aspect of the present disclosure, provided is a method for reconstructing a chroma block of a target block to be reconstructed. The method includes decoding correlation information between first residual samples and second residual samples, the first residual sample, and prediction information of the chroma block from a bitstream, wherein the first residual samples are residual samples of a first chroma component and the second residual samples are residual samples of a second chroma component. The method further includes generating predicted samples of the first chroma component and predicted samples of the second chroma information on the basis of the prediction information, and deriving the second residual samples by applying the correlation information to the first residual samples.

Abstract: Embodiments of the disclosure provide a method and apparatus for processing video signals. An image signal decoding method according to an embodiment of the disclosure comprises the steps of: determining, on the basis of the height and width of a current block, an input length and output length of a non-separable transform; determining a non-separable transform matrix corresponding to the input length and output length of the non-separable transform; and applying the non-separable transform matrix to the current block, wherein, when the height and width of the current block are 4 each, the input length and output length of the non-separable transform are determined to be 8 and 16 respectively.

Abstract: Embodiments for video processing, including video coding, video decoding and video transcoding are described. One example method includes performing a conversion between a video having one or more layers having one or more video pictures having one or more subpictures and a bitstream of the video according to a rule, wherein the rule defines network abstraction layer (NAL) units to be extracted from a bitstream during a sub-bitstream extraction process to output a sub-bitstream, wherein the rule further specifies that one or more inputs to the sub-bitstream extraction process include a target output layer set (OLS) index (targetOlsIdx) that identifies an OLS index of a target OLS and is equal to an index to a list of OLSs specified by a video parameter set, and wherein the one or more inputs satisfy a set of conditions.

Abstract: One or more computing devices, systems, and/or methods for video encoding are provided. For example, a video file may be segmented into at least a first portion and a second portion. The first portion may be analyzed to determine that the first portion is associated with a first level of complexity, and the second portion may be analyzed to determine that the second portion is associated with a second level of complexity. A first bitrate associated with the first level of complexity may be determined, and a second bitrate associated with the second level of complexity may be determined. The first portion may be encoded at the first bitrate to generate a first encoded portion, and the second portion may be encoded at the second bitrate to generate a second encoded portion. The first encoded portion and the second encoded portion may be assembled to generate an optimized video file.

Abstract: The present specification discloses a method of decoding an image. The method of decoding an image according to the method includes: obtaining transform skip information of a current block from a bitstream; obtaining multiple transform selection information of the current block on the basis of the transform skip information from the bitstream; and performing inverse transform on the current block on the basis of the multiple transform selection information, wherein the multiple transform selection information is used to set each of a horizontal transform type and a vertical transform type.

Abstract: A video decoding method, a video encoding method, and related apparatuses. The video decoding method includes: determining a current video frame; obtaining, from video frames that have been decoded, a first quantity of blocks of a first size and a second quantity of blocks of a second size in a reference frame associated with the current video frame, the first size being less than the second size; determining, according to a relationship between the first quantity and the second quantity, a target resolution used for decoding the current video frame; and decoding the current video frame by using the target resolution. In this application, the technical problem of the relatively low video encoding and decoding efficiency caused by complex processing operations in the related art is resolved.

Abstract: A method and a device for encoding or decoding video data. It concerns more particularly the encoding according to a particular encoding mode using a decoder side motion vector derivation mode referenced as frame-rate up conversion mode or FRUC mode. In FRUC merge mode, the derivation process comprises a refinement step to increase the accuracy of the obtained motion vector at the sub-pixel level. This process involves the evaluation of different sub-pixel position around the obtained motion vector according to different patterns. The present invention has been devised to improve the known refinement step. It aims at improving the coding efficiency by considering the characteristics of the matching type and/or the signal inside the templates.

Abstract: Interpolation between explicitly signaled CPB (or HRD) parameters at selected bit rates is used to achieve a good compromise between CPB parameter transmission capacity and CPB parametrization effectiveness and may be, particularly, made in an effective manner.

Abstract: A video decoding method performed by a video decoding device according to the present document comprises the steps of: acquiring image information from a bitstream, the image information including a picture header associated with the current picture including a plurality of slices; parsing, from the picture header, a first flag indicating whether information necessary for an inter-prediction operation for a decoding process is present in the picture header; parsing, from the picture header, a second flag indicating whether information necessary for an intra-prediction operation for the decoding process is present in the picture header; and generating prediction samples by performing at least one of intra-prediction or inter-prediction for the slices in the current picture on the basis of the first flag or the second flag.

Abstract: A video decoding method comprises: deriving L0 and L1 motion vectors of a current block; deriving decoder-side motion vector refinement (DMVR) flag information indicating whether to apply a DMVR to the current block; when the DMVR flag information indicates that the DMVR is to be applied to the current block, deriving refined L0 and L1 motion vectors based on the L0 and L1 motion vectors by applying the DMVR to the current block; deriving prediction samples of the current block based on the refined L0 and L1 motion vectors; and generating reconstructed samples of the current block based on the predicted samples, wherein deriving DMVR flag information comprises deriving the DMVR flag information by applying the DMVR to the current block when the height of the current block is 8 or more, and when the values of L0 and L1 luma weighted prediction flag information are both 0.

Abstract: The present invention discloses an image decoding method, the method including generating a candidate list including motion information derived from a spatial neighboring block and a temporal neighboring block adjacent to a current block; deriving motion information of the current block using the candidate list; generating a prediction block of the current block using the derived motion information; and updating the derived motion information in a motion information list, wherein the generating of the candidate list is performed in such a manner as to include at least one information of the motion information included in the updated motion information list in a block decoded before the current block.

Abstract: A method includes receiving a block comprising pixels; encoding the pixels by: arranging the pixels in a sequence; generating a delta encoding of the pixels, the delta encoding comprising (a) a base value and (b) delta values having non-zero delta values and zero delta values, each delta value representing a difference between a corresponding pixel in the sequence and a previous pixel in the sequence; generating a symbol mask indicating whether each of the delta values is zero or non-zero; determining, based on magnitudes of the non-zero delta values, a symbol width for encoding each of the non-zero delta values; generating a sequence of symbols that respectively encode the non-zero delta values using the symbol width; generating a compression of the block by collating the symbol mask, the symbol width, and the sequence of symbols.

Abstract: A device may be configured to general constraint information according to one or more of the techniques described herein.

Abstract: Systems, methods and apparatus for video processing are described. The video processing may include video encoding, video decoding, or video transcoding. One example method of video processing includes performing a conversion between a video comprising one or more pictures comprising one or more slices and a bitstream of the video. The bitstream conforms to a predefined order between a position of a first NAL (network abstraction layer) unit in a picture unit carrying an adaptation parameter set information and a second NAL unit that is a last video coding layer (VCL) NAL unit in the picture unit.

Abstract: An image signal decoding method according to an embodiment of the present disclosure comprises the steps of: partitioning the current picture into a plurality of tiles; decoding partition information indicating a slice type, the partition information indicating whether a rectangular slice is to be applied; determining the number of slices in the current picture; and defining the slices using the tiles.

Abstract: An encoder is configured to encode a representation of a current picture of a video stream of multiple pictures. The encoder is further configured to encode, for each of a plurality of reference pictures included in a buffer description for the current picture, a respective one-bit flag according to one of two available values for the one-bit flag. The two available values for the one-bit flag include a first value explicitly indicating to a decoder to include the reference picture in a reference picture list for decoding the current picture. The two available values for the one-bit flag further include a second value explicitly indicating to the decoder not to include the reference picture in the reference picture list for decoding the current picture. The encoder is further configured to output the representation of the current picture and the one-bit flags.

Abstract: A method of three-dimensional (3D)-Tree coding for neural network model compression, is performed by at least one processor, and includes reshaping a four-dimensional (4D) parameter tensor of a neural network into a 3D parameter tensor of the neural network, the 3D parameter tensor comprising a convolution kernel size, an input feature size, and an output feature size, partitioning the 3D parameter tensor along a plane that is formed by the input feature size and the output feature size into 3D coding tree units (CTU3Ds), partitioning each of the CTU3Ds into a plurality of 3D coding units (CU3Ds) recursively until a predetermined depth, using a quad-tree, and constructing a 3D tree for each of the plurality of CU3Ds, wherein the 3D tree for each of the plurality of CU3Ds is a 3D-Unitree.