Abstract: Aspects of the disclosure provide a method and an apparatus for video coding. In some examples, the apparatus includes processing circuitry for video encoding. The processing circuitry selects a resolution from a set of resolutions that includes a 1-integer-pel resolution and a 4-integer-pel resolution. A current block is encoded with an intra block copy mode based on the selected resolution. The processing circuitry determines a block vector of the current block. The processing circuitry determines a block vector difference of the current block based on the block vector and a block vector predictor of the current block. The block vector difference is in the selected resolution. The processing circuitry encodes prediction information indicating the selected resolution and the block vector difference.

Abstract: A method includes receiving a current picture, a first reference picture, and a second reference picture. The method includes obtaining a plurality of predefined weighting patterns, each weighting pattern being signaled as an index value and selecting a weighting pattern based on a predetermined condition. The method includes deriving a first weight to be applied to a first sub-block in the first reference picture and a second weight to be applied to a second sub-block in the second reference picture based on the index value corresponding to the selected weighting pattern. The method includes assigning the first weight to the first sub-block and the second weight to the second sub-block based on the selected weighting pattern. The method includes decoding the current block by a weighted bi-prediction based at least on the first sub-block weighted by the first weight and the second sub-block weighted by the second weight.

Abstract: Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a step size of the input image indicating a learning rate of a training model, determining a substitute image based on the training model, encoding the substitute image in lieu of the input image to generate a bitstream, and mapping the substitute image to the bitstream to generate a compressed representation. Further, step size may be determined by a scheduler and change throughout the training of the training model. The image may also be split into patches for which a scheduler is assigned for each patch and each patch is encoded instead of the entire input image.

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 and an apparatus for video decoding are disclosed. The apparatus includes processing circuitry that decodes prediction information of a current block that is indicative of an intra block copy mode. The current block is in a current region of a plurality of regions of a current coding tree unit (CTU) in a current picture. The processing circuitry determines a block vector for the current block, a reference block indicated by the block vector being in a search range that excludes at least a region in a previously reconstructed CTU that is collocated with the current region of the current CTU, a position of the collocated region in the previously reconstructed CTU having a same relative position as the current region in the current CTU, the search range being in the current picture. The processing circuitry reconstructs at least one sample of the current block according the block vector.

Abstract: A method and apparatus for video coding of chroma coded in derived-mode Intra prediction are disclosed. If derived-mode (DM) Intra prediction is selected for a current chroma block, a corresponding luma block area is determined by locating a first upper-left pixel address of the corresponding luma block area corresponding to that of the current chroma block. Further, one or more candidate luma coding modes are determined from a sub-block set consisting of one or more sub-blocks of the corresponding luma block area, where if the sub-block set consists of only one sub-block, the sub-block set excludes a corner sub-block located at a top-left corner of the corresponding luma block area. Additionally, a current chroma Intra mode for the current chroma block is derived based on information comprising the candidate luma coding modes, and Intra-prediction encoding or decoding is applied to the current chroma block using the current chroma Intra mode derived.

Abstract: Aspects of the disclosure provide methods and apparatuses for video coding. In some examples, an apparatus includes processing circuitry. The processing circuitry obtains prediction information of a first block in a picture from a coded video bitstream, and generates reconstructed samples of the first block according to the prediction information and one of bi-directional prediction and uni-directional prediction. The processing circuitry adds motion information and a bi-prediction weight index of a History-based Motion Vector Prediction (HMVP) candidate to an HMVP list based on the prediction information of the first block and whether the first block is coded according to the bi-directional prediction or the uni-directional prediction. Further, the processing circuitry generates reconstructed samples of a second block in the picture based on a plurality of candidates that includes the HMVP candidate.

Abstract: Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a substitute image based on a training model of the E2E NIC framework, encoding the substitute image to generate a bitstream, mapping the substitute image to the bitstream to generate a compressed representation of the input image. Further, the input may be partitioned into blocks for which a substitute representation is determined for each block and each block is encoded instead of the entire substitute image.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain an input mesh comprising volumetric data of at least one three-dimensional (3D) visual content, derive a plurality of submeshes of the input mesh from a frame of the volumetric data, set bitdepths to a first submesh and a second submesh from the submeshes, a first bitdepth being different than a second bitdepth, quantize the first submesh and the second submesh based on respective ones of the first bitdepth and the second bitdepth, and signal a result of quantizing the first submesh and the second submesh.

Abstract: Aspects of the disclosure provide methods and apparatuses for video coding. In some examples, an apparatus includes processing circuitry configured to encode a first block in a picture according to one of bi-directional prediction and uni-directional prediction. The processing circuitry is configured to add motion information and a bi-prediction weight index of a History-based Motion Vector Prediction (HMVP) candidate to an HMVP list based on whether the first block is encoded according to the bi-directional prediction or the uni-directional prediction, the bi-prediction weight index indicating bi-prediction weights of the bi-directional prediction for the first block when the first block is encoded according to the bi-directional prediction, and the bi-prediction weight index indicating a default value when the first block is encoded according to the uni-directional prediction.

Abstract: A method and apparatus comprising computer code for mesh coding configured to cause a processor or processors to receive a dynamic input mesh representing a volumetric data of at least one three-dimensional (3D) visual content; determine, for a mesh at a first level of sub-division, a plurality of first vertices, wherein the plurality of first vertices are determined using a mid-point sub-division scheme and a plurality of previous vertices of a mesh at a previous level of sub-division, wherein the mesh at the first level and the mesh at the previous level are generated from the dynamic input mesh; determine a valence of a first vertex among the plurality of first vertices to be a first value based on whether a selected two vertices of the mesh at the first level; and generate a compressed bitstream for the dynamic input mesh based on the valence of the first vertex.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video encoding includes receiving circuitry and processing circuitry. The processing circuitry determines whether a block is under a local dual tree structure, and disallows a palette based coding mode for encoding the block in response to the block being under the local dual tree structure.

Abstract: A video processing method is provided. In the method, a video bit stream is obtained. Configuration information of the video bit stream is determined. The configuration information includes reference image information. The reference image information indicates (i) whether a video track corresponding to the video bit stream includes a reference image and (ii) whether the video track requires reference to the reference image. The video bit stream and the configuration information are encapsulated to obtain the video track.

Abstract: A method includes receiving a polygon mesh that includes a plurality of vertices; generating a set of candidate predictors, each candidate predictor in the set of candidate predictors corresponding to a respective displacement vector between a vertex from the plurality of vertices to a vertex to be coded; selecting a candidate predictor from the set of candidate predictors; and generating a bitstream that includes at least a candidate predictor index corresponding to the selected candidate predictor.

Abstract: The various implementations described herein include methods and systems for coding video. In one aspect, a method includes receiving a video bitstream including a current coding block of a current image frame and determining that the current coding block is to be predicted in a weighted bi-prediction (WBP) mode. The method further includes in response to the current coding block being predicted in the WBP mode, determining that the current coding block is associated with two bi-prediction blocks and identifying a plurality of distinct weighting factor lists including at least a first list of positive weighting factors and a second list of mixed weighting factors. The method further includes selecting one of the weighing factor lists, identifying a first weighting factor from the weighing factor lists, and reconstructing the current image frame, including determining the current coding block by combining the two bi-prediction blocks based on the first weighting factor.

Abstract: A method and apparatus for encoding or decoding a video sequence includes encoding or decoding the video sequence using a 4:4:4 chroma format, or encoding or decoding the video sequence using a 4:2:2 chroma format, wherein when encoding or decoding the video sequence using the 4:4:4 chroma format, copying an affine motion vector of one 4×4 luma block using an operation other than an averaging operation and associating the affine motion vector to a co-located 4×4 chroma block, and when encoding or decoding the video sequence using the 4:2:2 chroma format, associating each 4×4 chroma block with two 4×4 co-located luma blocks such that an affine motion vector of one 4×4 chroma block is an average of the motion vectors of the two co-located luma blocks.

Abstract: A video decoding method includes performing entropy decoding processing on a code block of a video image frame of a video image frame sequence, to obtain a quantization coefficient block of residual data corresponding to the code block; collecting statistics of quantization coefficients in a target region in the quantization coefficient block, to obtain a quantization coefficient statistical value; selecting a transform matrix combination corresponding to the quantization coefficient statistical value; and performing inverse transform processing on an inverse quantization result of the quantization coefficient block based on the selected transform matrix combination, to obtain reconstructed residual data, the reconstructed residual data being used for video image reconstruction.

Abstract: A method and apparatus that derives a curve of a mesh sequence from a frame of a video bitstream, the curve comprising a plurality of vertices; subdivides the curve by adding a plurality of subdivided vertices; calculates one or more displacement vectors between each of the plurality of vertices on the curve and each of the plurality of subdivided vertices on the subdivided curve; transforms the one or more displacement vectors to output one or more original coefficients; tracks the current frame with a previous frame to obtain a one-to-one correspondence between the plurality of vertices of the current frame and a plurality of vertices of the previous frame; predicts one or more coefficients of each of the plurality of vertices in current frame based on the one-to-one correspondence; performs entropy coding on one or more prediction residues; and encodes the one or more prediction residues.

Abstract: A method for video encoding includes determining that a current block in a first coding tree unit (CTU) of a current picture is to be coded using an affine model in a merge mode, and obtaining, from a line buffer, one or more motion vectors of blocks located at bottom locations in a second CTU above the current block. The line buffer only stores motion vectors of minimum-size blocks located at the bottom locations of the second CTU above the current block and the line buffer does not store (i) a block width or block height of the minimum-size blocks, (ii) affine control point information, and (iii) an affine flag. The method further includes deriving motion vectors of control points of the current block using the affine merge model, and encoding the current block based on the affine merge model and the motion vectors of the control points.

Abstract: A method of video encoding includes determining whether a reference block for a current block is located in a different coding tree unit (CTU) than a CTU of the current block. The method also includes, in response to the reference block being located in the different CTU, (i) determining whether a memory location of a reference sample memory for the reference block is available. The second area is collocated in the different CTU with a position of the first area in the CTU of the current block. In response to the determination that the reference block is located in the different CTU, the method also includes, (ii) in response to a determination that the memory location for the reference block is available, retrieving, from the memory location corresponding to the reference block, one or more samples to encode the current block.