Tencent America LLC

Hfi Innovation Inc.

Mediatek Corporation

Tencent Technology (shenzhen) Company Limited

Other

Mediatek Singapore Pte. Ltd.

Xiaozhong Xu

Shan Liu

Xiang Yang Li

Guichun Li

Xiang Li

Jun Tian

Xin Zhao

Xiang Zhang

Chao Huang

Tzu-Der Chuang

Jing Ye

Wei Jiang

Meng Xu

Yu-Chen Sun

Wang-Lin Lai

Wei Wang

Ching-Yeh Chen

Yu-Wen Huang

Byeongdoo Choi

Wei W Wang

Ding Ding

Wen Gao

Stephan Wenger

Sheng Lin

Yiming Li

Jungsun Kim

Zeqiang Li

Liang Zhao

Ding-Yun Chen

Thuong Nguyen Canh

Han Huang

Zhenzhong Chen

Lien-Fei Chen

Weiwei Feng

Yeqing Wu

Yu Wang

Shaw-Min Lei

Jicheng An

Yixin Du

Han Gao

Xianguo Zhang

Yingbin Wang

Chenghao Liu

Liqiang Wang

Chih-Wei Hsu

Anish Tamse

Madhu Peringassery Krishnan

Shih-Ta Hsiang

Ying Hu

Bin Zhu

Fang-yi Chao

Biao Wang

Jacob Yu

Ling Li

Ethan Schur

Karen Yun Chang

Aspects of the disclosure provide a method, an apparatus, and non-transitory computer-readable storage medium for video decoding. The apparatus includes processing circuitry configured to reconstruct an area in a block in a current picture from a coded video bitstream. The block includes one or more coding blocks (CBs) in the current picture. After the reconstructing, the processing circuitry determines whether to update a previous local reference range for an intra block copy (IBC) mode based on a content of the reconstructed area and/or prediction information of the reconstructed area. In response to a determination not to update the previous local reference range for the IBC mode, the previous local reference range for the IBC mode is not updated. The processing circuitry decodes a coding block in the current picture using the IBC mode that is based on the previous local reference range, which does not include the reconstructed area.

Adaptive local reference range

Aspects of the disclosure provide methods and apparatuses for mesh coding. In some examples, an apparatus for mesh coding includes processing circuitry. The processing circuitry receives a bitstream carrying a 3D mesh frame. The 3D mesh frame represents a surface of an object with polygons, the polygons are defined by vertices and edges connecting the vertices, the 3D mesh frame is parameterized into a plurality of 2D charts in a 2D UV atlas. The processing circuitry determines respective chart based coding modes for the plurality of 2D charts according to one or more indices decoded from the bitstream, and decodes, from the bitstream, at least respective geometry information associated with the plurality of 2D charts according to the respective chart based coding modes. The processing circuitry reconstructs the 3D mesh frame according to the respective geometry information associated with the plurality of 2D charts.

Method and apparatus for chart based mesh compression

This disclosure relates generally to video coding and particularly to intra block copy coding mode. An example method may include determining a first search area in a video frame, wherein the first search area is a first candidate area for locating IntraBC prediction block; determining a second search area, wherein the second search area is a second candidate area for locating the IntraBC prediction block, and the IntraBC prediction block overlapping with the second search area in a second overlap area of the IntraBC prediction block; selecting a target overlap area from the first overlap area and the second overlap area; replacing samples in the target overlap area to obtain an updated IntraBC prediction block; and encoding the at least the portion of the current block based on the updated IntraBC prediction block; encoding a block vector used for identifying the IntraBC prediction block.

Method and apparatus for intra block copy (IntraBC) mode coding with search range restrictions

Method, apparatus, and system for atlas sampling-based dynamic mesh compression are provided. The process may include receiving a mesh frame with polygons representing a surface of an object; determining that the mesh frame is associated with an irregular UV chart in response to one or more singularity components in the mesh frame; performing boundary detection to the UV chart to identify one or more boundary loops in the UV chart; and compressing information of the identified one or more boundary loops into a bitstream.

Atlas sampling based mesh compression with charts of general topology

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.

DNN-based cross component prediction

There is includes a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining volumetric data of at least one three-dimensional (3D) visual content, obtaining a plurality of 3D meshes from the volumetric data, projecting vertices of the plurality of 3D meshes onto a plurality of two-dimensional (2D) meshes, signaling connectivity information of the plurality of 3D meshes based on the plurality of 2D meshes, wherein the signaling the connectivity information comprises signaling whether ones of pixels of a 2D occupancy map is to be inferred or explicitly signaled.

Vertex prediction based on mesh triangulation derivation

Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that receives metadata associated with a coded video bitstream. The metadata includes labeling information of one or more objects detected in a first picture that is coded in the coded video bitstream. The processing circuitry decodes the labeling information of the one or more objects in the first picture that is coded in the coded video bitstream. The processing circuitry applies the labeling information to the one or more objects in the first picture.

Labeling detected objects in frames of a video

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 one or more surfaces of a volumetric object; predicts a current value of an index of the UV-to-XYZ index array from at least one previously coded value included in another index in the UV-to-XYZ index array, wherein the UV-to-XYZ index array includes a plurality of indices which correspond each two-dimensional (2D) UV vertex associated with the mesh to a three-dimensional (3D) XYZ vertex associated with the mesh; derives a prediction residual associated with the current value of the index of the UV-to-XYZ index array; and reconstructs a boundary UV coordinate based on the predicted current value of the index of the UV-to-XYZ index array and the derived prediction residual.

Predictive coding of boundary UV2XYZ index for mesh compression

Coding information of a mesh is received. The coding information includes a plurality of first coordinates and a plurality of second coordinates corresponding to a plurality of vertices and a texture map that are associated with the mesh. A respective first coordinate and a respective second coordinate associated with each of the plurality of vertices are normalized by adjusting the respective first coordinate based on a first factor and the respective second coordinate based on a second factor. The first factor and the second factor are associated with at least one of (i) a bit depth value indicating a coded range of the first coordinates and the second coordinates and (ii) a size of the texture map. The normalized respective first coordinate and the normalized respective second coordinate are expanded based on the first factor and the second factor respectively.

UV coordinate ranges and texture map size

A method and apparatus comprising computer code configured to cause a processor or processors to obtain volumetric data of at least one three-dimensional (3D) visual content, derive a first layer of a mesh including a plurality of first vertices from at least one frame of the volumetric data, determine displacement vectors from ones of the plurality of vertices of the first layer to respective ones of a plurality of second vertices of a second layer of the mesh, a total quantity of the plurality of second vertices is greater than a total quantity of the plurality of first vertices, and signal the volumetric data based on the displacement vectors.

Vertex prediction based on decoded neighbors

Method, apparatus, and system for generating temporally correlated UV atlases are provided. The process may include generating plurality of consistent UV charts based on partition information associated with one or more previous frames; removing one or more non-manifold vertices from the plurality of consistent UV charts based on assigning one or more incident faces associated with the one or more non-manifold vertices to corresponding UV charts; merging more than one of the plurality of consistent UV charts based on a similarity between the plurality of consistent UV charts and one or more reference charts associated with the one or more previous frames; and generating temporally correlated UV atlases for the current frame based on aligning the plurality of consistent UV charts with the one or more reference charts associated with the one or more previous frames.

Mesh parameterization with temporally correlated UV atlases

Neural network based image compression using an optimized end-to-end (E2E) neural image compression (NIC) framework being performed by at least one processor and includes receiving an input image to an E2E NIC framework, processing the input image in its entirety using an encoder in the E2E NIC framework to obtain a first bitstream representation of the input image in its entirety, reconstructing an output image from the first bitstream representation of the input image in its entirety using a decoder in the E2E NIC framework, optimizing the encoder in the E2E NIC framework by reducing a distortion loss between the input image and the output image, and processing the input image using the optimized encoder in the E2E NIC framework to obtain a second bitstream representation of the input image. Further, the input may be partitioned into blocks for which encoder optimization is performed for each block and each block is encoded instead of the entire image.

Method and apparatus for optimizing end-to-end neural image compression framework

Aspects of the disclosure provide methods and apparatuses for mesh coding (e.g., compression and decompression). In some examples, an apparatus for mesh coding includes processing circuitry. The processing circuitry decodes, using a decoder supporting a first bitdepth, a plurality of segmental attribute values having the first bitdepth from a bitstream carrying a mesh that represents a surface of an object. The plurality of segmental attribute values is associated with attribute values of the mesh, the attribute values of the mesh have a second bitdepth that is higher than the first bitdepth. The processing circuitry determines the attribute values of the mesh having the second bitdepth according to the plurality of segmental attribute values having the first bitdepth.

Segment based compression methods for mesh compression

This disclosure relates generally to video coding and particularly to intra block copy coding mode using wedgelet partitioning. For example, a method is disclosed for processing video data which may include receiving a video bitstream comprising a current block of a video frame; extracting an IntraBC flag from the video bitstream indicating that the current block is predicted under an IntraBC mode; determining from the video bitstream that the current block is partitioned under a wedgelet partitioning mode, wherein the current block is partitioned into a plurality of partitions comprising a first partition and a second partition; identifying at least the first partition and the second partition of the current block; determining a first block vector for predicting the first partition and a second block vector for predicting the second partition, respectively; and decoding the current block based on at least the first block vector and second block vector.

IntraBC using wedgelet partitioning

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.

Method and apparatus for signaling skip mode flag

Growing community of inventors

State College, PA, United States of America

Xiaozhong Xu