Abstract: A method of video decoding is provided. In the method, a coded video bitstream including a current picture is received. Whether a current block included in the current picture is coded in an intra block copy (IBC) mode is determined. In response to determining that the current block is coded in the IBC mode, a maximum number of IBC predictor candidates associated with the current block is determined as equal to a value of max(M, MaxNumMergeCand). The MaxNumMergeCand is equal to a number of candidates in a merge mode list and the M is a predetermined integer. An IBC predictor candidate list is constructed based on the maximum number of IBC predictor candidates. A block vector associated with the current block is determined based on a block vector predictor included in the IBC predictor candidate list. The current block is reconstructed based on the block vector.

Abstract: A method of video encoding includes receiving a merge sharing region including a plurality of coding blocks, constructing a shared merge candidate list for the merge sharing region, and encoding a current inter coded coding block in the merge sharing region based on the shared merge candidate list. The method also includes determining whether to update a history-based motion vector prediction (HMVP) table with motion information of the current inter coded coding block based on whether the current inter coded coding block is inter coded with a merge/skip mode. The method further includes updating the HMVP table with the motion information of the current inter coded coding block when the HMVP table is determined to be updated with the motion information of the current inter coded coding block.

Abstract: Aspects of the disclosure provide method and apparatus for video coding. In the method, which of a combination of vertical padding and horizontal padding is performed is determined to determine padded values of a reference block in a neighboring left coding tree unit (CTU) included in a fixed search range of blocks in a current CTU. The padded values are determined based on a block vector that points to the reference block and a position of a current block in the CTU. At least a sample of the current block is reconstructed based on one of (i) the padded values of the reference block and (ii) reconstructed samples of the reference block based on availability of the reference block in the fixed search range. The left CTU is padded using a combination of the vertical and the horizontal padding.

Abstract: A method and apparatus of for video enhancement based on neural network based loop filtering using meta learning may include receiving reconstructed video data; receiving one or more quality factors associated with the reconstructed video data; determining a neural network based loop filter comprising neural network based loop filter parameters and a plurality of layers, wherein the neural network based loop filter parameters include shared parameters and adaptive parameters; and generating enhanced video data with artefact reduction, based on the one or more quality factors and the reconstructed video data, using a neural network based loop filter, wherein the neural network based loop filter comprises neural network based loop filter parameters that include shared parameters and adaptive parameters.

Abstract: Systems, devices, and methods for performing video coding for machine (VCM) image enhancement, including obtaining a coded image from a coded bitstream; obtaining enhancement parameters corresponding to the coded image; decoding the coded image using a VCM decoding module to generate a decoded image; generating an enhanced image using an enhancement module based on the decoded image and the enhancement parameters, wherein the enhancement parameters are optimized for one of a human vision VCM task, a machine vision VCM task, and a human-machine hybrid vision VCM task; providing at least one of the decoded image and the enhanced image to at least one of a human vision module and a machine vision module for performing the one of the human vision VCM task, the machine vision VCM task, and the human-machine hybrid vision VCM task.

Abstract: In a method for video coding, prediction information of a current block in a current picture is decoded from a coded video bitstream. The prediction information is indicative of an affine model, and the current block includes two or more control points. A motion vector for each of the two or more control points is determined based on a corresponding motion vector predictor for the respective control point. The corresponding motion vector predictor for the respective control point is a first predictor of a plurality of candidate motion vector predictors in a candidate list and meets a constraint that is associated with a motion vector of the corresponding motion vector predictor. Further, parameters of the affine model are defined based on the determined motion vectors of the two or more control points, and at least a sample of the block is reconstructed according to the affine model.

Abstract: A method of video decoding is provided. In the method, a coded video bitstream including a current picture is received. Whether a current block included in the current picture is coded in an intra block copy (IBC) mode is determined. In response to determining that the current block is coded in the IBC mode, a maximum number of IBC predictor candidates associated with the current block is determined as equal to a value of max(M, MaxNumMergeCand). The MaxNumMergeCand is equal to a number of candidates in a merge mode list and the M is a predetermined integer. An IBC predictor candidate list is constructed based on the maximum number of IBC predictor candidates. A block vector associated with the current block is determined based on a block vector predictor included in the IBC predictor candidate list. The current block is reconstructed based on the block vector.

Abstract: A method, computer program, and computer system is provided for video coding. Video data comprising one or more blocks is received. One or more samples are identified from one or more references images corresponding to the received video data. One or more motion vectors associated with the video data are refined based on interpolating the one or more samples by applying a decoder-side motion vector refinement (DMVR) motion vector offset value to a motion vector associated with a current block from among the one or more blocks.

Abstract: A method and device for coding and decoding are disclosed. The method includes: dividing a picture to be encoded into several slices, each containing macroblocks continuous in a designated scanning sequence in the picture; dividing slices in the picture into one or more slice sets according to attribute information of the slices, each slice set containing one or more slices; and encoding the slices in the slice sets according to slice and slice set division information to get a coded bit stream of the picture. The decoding method includes: obtaining slice and slice set division information from a bit stream to be decoded and decoding the bit stream according to the obtained slice and slice set division information. The invention improves the performance of video transmission effectively and realizes region based coding. The implementation of coding and decoding is simple and the complexity of coding and decoding systems is reduced.

Abstract: A method of video decoding includes determining whether a maximum number of merge candidates is signaled in a coded video bitstream for a current block of a current picture. The method further includes, in response to a determination that the maximum number of merge candidates is signaled for the current block, setting a maximum number of intra block copy (IBC) candidates for the current block to a value of the signaled maximum number of merge candidates, and, in response to a determination that the maximum number of merge candidates is not signaled for the current block, setting the maximum number of IBC candidates to a predetermined value. The method further includes constructing a candidate list of vector predictors based on at least one of the maximum number of merge candidates or the maximum number of IBC candidates for the current block.

Abstract: A method for controlling block intra prediction is provided for a decoder. The method includes: obtaining a coded video bitstream; decoding, prediction information of a current coding unit (CU) in a segment of a current picture from the coded video bitstream; determining, according to the prediction information, a prediction type of a chroma coding block (CB) of the current CU, the prediction type being intra prediction or inter prediction; and reconstructing the chroma CB according to the prediction information, where a width of any reconstructed chroma CB intra-predicted from the coded video bitstream is greater than 2.

Abstract: A pruning method of neural network based video coding of a current block of a picture of a video sequence is performed by at least one processor and includes categorizing parameters of a neural network into groups, setting a first index to indicate that a first group of the groups is to be pruned, and a second index to indicate that a second group of the groups is not to be pruned, and transmitting, to a decoder, the set first index and the set second index. Based on the transmitted first index and the transmitted second index, the current block is processed using the parameters of which the first group of the groups is pruned.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data including one or more reference locations is received. The one or more reference locations are updated in a history list associated with the received video data based on intra block copy for a single value string mode. The video data is decoded based on the updated reference locations.

Abstract: Systems and methods for content-adaptive segmented prediction mode are provided. A method includes receiving a picture, and encoding the picture, the encoding including predicting a current block of the picture.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry that determines previous probability information associated with each entropy coded region of multiple regions in a previous picture. The processing circuitry selects, based on (i) a location or a quantization parameter of an independently decodable coding segment in a current picture or (ii) syntax information of the independently decodable coding segment, a region among the multiple regions. Initial probability information for one or more current syntax elements of a block in the independently decodable coding segment is determined based on the previous probability information associated with the selected region. The one or more current syntax elements are first to be entropy decoded in the independently decodable coding segment. The processing circuitry entropy decodes coded bits associated with the one or more current syntax elements into a bin string based on the initial probability information.

Abstract: A method of video encoding includes, prior to encoding a first tile of s plurality of tiles of a current picture, initializing a shared row buffer that is shared among multiple processor threads associated with the first tile. The method also includes encoding a first unit of a plurality of units in a first row of the first tile by a first processor thread and using a corresponding first HMVP buffer. The method also includes, when all of the plurality of blocks in the first unit have been encoded, copying contents of the first HMVP buffer into the shared row buffer, copying contents of the shared row buffer into a second HMVP buffer, starting encoding of a unit in a second row of the plurality of rows by the second processor thread using the second HMVP buffer, and resetting the first HMVP buffer.

Abstract: A method of video encoding includes determining a predetermined condition associated with signaling data for a current block included in a current picture, the predetermined condition specifying whether a maximum number of merge mode candidates is different from a maximum number of IBC candidates. The method includes setting, based on the predetermined condition, a size of an index included in the signaling data for a candidate list of vector predictors to one of (i) the maximum number of merge mode candidates and (ii) the maximum number of IBC candidates. The method includes constructing the candidate list of vector predictors and retrieving a vector predictor from the candidate list of vector predictors in accordance with the index. The method includes encoding the current block in accordance with the retrieved vector predictor, and generating a coded video bitstream including the current picture and the signaling data.

Abstract: Methods, apparatuses, and non-transitory computer-readable mediums are provided. A block vector of a current block that is to be coded in intra block copy (IBC) mode is determined. The block vector points to a first reference block of the current block in a current picture. An operation is performed on at least one component of the block vector based on the first reference block being outside a search range of the current block. The block vector is modified by the operation to point to a second reference block that is within the search range for the current block. The current block is encoded based on the modified block vector. The performing the operation includes performing a modulo operation on a y component of the block vector based on a size of a current coding tree unit (CTU) that includes the current block.

Abstract: A method, computer program, and computer system is provided for video coding. Video data having one or more coding coefficients is received. A flipping or rotation operation is performed on the received video data based on selecting a scan region based coefficient coding definition to concentrate the coding coefficients in a scan region. The video data is decoded based on the selected scan region based coefficient coding definition.

Abstract: An apparatus for video encoding includes processing circuitry that determines that a current block is not coded in an intra block copy (IBC) mode. Responsive to the determination that the current block is not coded in the IBC mode, the processing circuitry determines whether a size of the current block is greater than a threshold. The processing circuitry encodes a mode prediction flag into a coded bitstream based on the size of the current block being greater than the threshold. The mode prediction flag indicates whether the current block is coded in an intra prediction mode.