Abstract: A method and apparatus that receives a coded video bitstream from an encoder; retrieves, from the coded video bitstream, a mesh including a plurality of polygons that describe a surface of a volumetric object; triangulates one or more vertices of the mesh, the one or more vertices are located on a boundary of the mesh or interior of the mesh; infers connectivity information between the one or more vertices using the triangulation of the one or more vertices; and reconstructs one or more boundary UV coordinates based on the connectivity information.

Abstract: Aspects of the disclosure provide methods for video encoding/decoding and processing circuitry. In some embodiments, the processing circuitry receives a block in an I slice from a video. In response to a slice type parameter indicating the I slice and at least a width or height of the block being greater than 64, the processing circuitry sets a current mode type parameter to MODE_TYPE_INTRA. The processing circuitry then determines whether a skip mode is possible for the block in the I slice based on at least one of the width or the height of the block being greater than 64 and the current mode type parameter. When neither the width nor the height of the block is greater than 64 and the current mode type parameter is not MODE_TYPE_INTRA, the processing circuitry determines to output the skip mode flag into a coded video bitstream for the block.

Abstract: Some aspects of the disclosure provide a method of mesh decoding processing. The method includes receiving a bitstream including coded information of a polygon mesh, the polygon mesh including vertices that are connected into polygons, the coded information indicates connectivity information of the vertices. The method also includes determining a first connectivity of a first polygon-fan with a first vertex being a pivot vertex of the first polygon-fan according to the coded information; detecting that a second vertex in the first polygon-fan is a a visited vertex that has existing neighborhood information; checking whether the existing neighborhood information of the second vertex and new neighboring information of the second vertex in the first polygon-fan satisfy a condition; and updating the existing neighborhood information of the second vertex based on the new neighboring information when the condition is satisfied.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. An apparatus for video decoding includes processing circuitry that decodes prediction information for a current block in a current coded picture. The prediction information indicates a motion vector predictor index (MVP_idx) for selecting a motion vector predictor in a motion vector predictor list. The processing circuitry determines whether the MVP_idx is smaller than a threshold. When the MVP_idx is determined to be smaller than the threshold, the processing circuitry decodes a motion vector difference (MVD) corresponding to the motion vector predictor and reconstructs the current block based on the motion vector predictor and the MVD. When the MVP_idx is determined to be equal to or larger than the threshold, the processing circuitry reconstructs the current block based on the motion vector predictor without the MVD which is not signaled in the coded video sequence.

Abstract: This disclosure relates generally to encoding and decoding of 3-dimensional (3D) mesh and is particularly directed to predicting a 3D mesh position using a predictor from a reference pool having candidate reference positions on a parallelogram grid. For example, when encoding a current position, a set of prior encoded positions may be used to derive a set of reference positions that are distributed as grid points in in a parallelogram grid space that encompasses a parallelogram prediction position. The set of reference positions may be adaptively determined. The reference set may be derivable by both the encoder and the decoder, thereby requiring no signaling other than an index for an optimal predictor selected from the set of reference positions for encoding the current position.

Abstract: A method and apparatus for adaptive neural image compression with smooth quality control by meta-learning includes receiving an input image and a target quality control parameter; generating quality-adaptive weight parameters of an encoding neural network using shared encoding parameters and adaptive encoding parameters; and encoding the input image, based on the target quality control parameter, using the encoding neural network with the quality-adaptive weight parameters, to generate a compressed representation.

Abstract: A method comprising segmenting an input symmetry mesh into multiple non-connected UV segments; partitioning at least one UV segment via a plane that partitions the at least one UV segment into a first side and a second side; reorganizing the plurality of vertices included in the first side of the at least one UV segment; perform a 2D symmetry detection on the at least one UV segment to find a symmetry transform; determining a predicted vertex for each vertex on the second side of the at least one UV segment based on the symmetry transform of a corresponding vertex on the first side of the at least one UV segment to find a predicted vertex on the first side of the at least one UV segment; and encoding a bitstream that comprises at least the vertices within the first side of the at least one UV segment.

Abstract: This disclosure relates generally to encoding and decoding of 3-dimensional (3D) mesh and specifically to encoding and decoding order and dependency between 3D positions of 3D vertices and 2D positions of 2D texture coordinates of a 3D mesh. In particular, the various embodiments in this disclosure provide a novel method and device to enhance lossless compression of 3D mesh models. The disclosed method and device prioritize encoding texture coordinates before encoding 3D positions. The disclosed method and device further employ angle-preserving position prediction. The disclosed approaches aim to optimize the compression process of 3D meshes by leveraging an inherent correlation between 3D structures and their corresponding 2D texture mappings.

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: 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: A bitstream that includes coded information of a mesh with position vertices and non-position vertices is received. The coded information indicates whether a cut is applied to connections of the position vertices of the mesh. Whether the cut is applied is based on a comparison between a total number of the position vertices of the mesh and a total number of the non-position vertices of the mesh. The position vertices of the mesh are processed when the coded information indicates that the cut is applied to the connections of the position vertices of the mesh. The mesh is reconstructed based on whether the position vertices are processed.

Abstract: This disclosure relates generally to coding and decoding of 3-dimensional (3D) mesh and specifically to merging of boundary vertexes in a symmetric mesh.

Abstract: A first point cloud is determined based on a plurality of first vertices of a reference mesh and a second point cloud is determined based on a plurality of second vertices of a distorted mesh. The distorted mesh is associated with the reference mesh. At least one of a symmetric geometric error or a symmetric attribute error is determined based on a plurality of distances between points of the first point cloud and points of the second point cloud. Each of the plurality of distances is determined between a respective point of the first point cloud and a point of the second point cloud that corresponds to the respective point of the first point cloud. A peak signal to noise ratio (PSNR) is determined based on one of the symmetric geometric error and the symmetric attribute error.

Abstract: The present disclosure provides a video decoding method. The method includes obtaining a bitstream that needs to be decoded, the bitstream that needs to be decoded comprising a current decoding block, the current decoding block using an intra string copy mode, and the current decoding block comprising a current string; determining a string length encoding resolution of the current string; decoding the bitstream that needs to be decoded to obtain an encoded string length corresponding to the current string; and obtaining a string length of the current string according to the string length encoding resolution of the current string and the corresponding encoded string length. The string length encoding resolution of the current string is at least one of the following: at least one preset value, each preset value being an integer pixel greater than or equal to 1, or a width or a height of the current decoding block.

Abstract: A plurality of vertices corresponding to a mesh of a current frame that is positionally tracked is divided into a plurality of vertex groups based on a predetermined constant integer. The plurality of vertex groups includes a first vertex group. A first position of a current vertex in the first vertex group is estimated based on a second position of a reference vertex in a reference frame that is different from the current frame. An estimation error indicating a difference between the reference vertex in the reference frame and the current vertex in the first vertex group is determined. A prediction mode of vertices in the first vertex group is encoded based at least on the estimation error between the reference vertex and the current vertex. Prediction information of the vertices in the first vertex group is generated based on the encoded prediction mode of the vertices of the first vertex group.

Abstract: This disclosure relates generally to video coding and particularly to intra block copy (IBC) padding mode. One method is disclosed for performing an IBC padding. The method includes receiving a coded video bitstream; extracting, from the coded video bitstream, a first syntax element, the first syntax element indicating that an IBC padding is available for a current video block; extracting, from the coded video bitstream, a second syntax element, the second syntax element indicating that the current video block is predicted using the IBC padding; extracting, from the coded video bitstream, at least one syntax element; partitioning the current video block into at least two sub-partitions based on the at least one syntax element, wherein the at least two sub-partitions comprise a padding sub-partition and an IBC sub-partition; predicting the padding sub-partition based on a predefined padding rule; and predicting the IBC sub-partition based on a predefined IBC rule.

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: Aspects of the disclosure provide a method and an apparatus for video decoding. The apparatus includes processing circuitry that receives a coded bitstream comprising a first block in a current picture. The processing circuitry obtains prediction information indicating whether the first block is coded in an intra template matching prediction (IntraTMP) mode. If the IntraTMP mode is applied to the first block, the first block is reconstructed based on a prediction block within a reconstructed search area in the current picture. A reference template of the prediction block is matched to a current template of the first block in the IntraTMP mode. An IntraTMP-based block vector BVIntraTMP of the first block is stored. The IntraTMP-based block vector indicates a position displacement between the current template of the first block and the reference template of the prediction block. A second block is reconstructed based on the stored IntraTMP-based block vector.

Abstract: An aspect of the disclosure provides a method of mesh decoding. For example, a bitstream that includes coded information of a mesh frame is received. A syntax element is parsed from the bitstream, the syntax element indicates whether an adaptive linear wavelet transform is used, the adaptive linear wavelet transform applies different weight values to different neighboring vertices of a vertex in a wavelet transform of attribute values associated with vertices of the mesh frame. When the syntax element indicates a use of the adaptive linear wavelet transform, at least a first vertex in the vertices of the mesh frame is reconstructed according to the adaptive linear wavelet transform.

Abstract: A plurality of candidate predictions of a current vertex is determined. The current vertex is one of a plurality of vertices of a mesh. Each of the plurality of candidate predictions is determined based on a respective one of a plurality of triangles in the mesh and including two-dimensional (2D) coordinates in a 2D domain. An average prediction of the plurality of candidate predictions is computed. A 2D prediction of the current vertex is selected from a prediction list that includes the plurality of candidate predictions and the average prediction. A three-dimensional (3D) prediction of the current vertex is determined based on one or more neighboring vertices of the current vertex in the mesh. A prediction residue comprising a prediction error of the current vertex is encoded. The prediction residue is obtained based on the selected 2D prediction and the determined 3D prediction of the current vertex.