Tencent America LLC

Peking University

Thomson Licensing

Future Wei Technologies, Inc.

Chinese Academy of Sciences

Huawei Technologies Co., Limited

Tencent Technology (shenzhen) Company Limited

Thomson Licensing S.a.

Ge Medical Systems Global Technology Company, LLC

Mediatek Singapore Pte. Ltd.

Shenzhen Ucloudlink New Technology Co., Ltd.

Wen Gao

Shan Liu

Xiang Zhang

Ronggang Wang

Zhenyu Wang

Ge Li

Wenmin Wang

Hou-Shin Chen

Shengfu Dong

Siwei Ma

Ying Li

Joshua Lawrence Koslov

Haoping Yu

Xiaozhong Xu

Sehoon Yea

Tiejun Huang

Hui Zhao

Paul Gothard Knutson

Yan Lu

Kui Fan

Yik Chung Wu

Jun Tian

Jin Song

Minqiang Jiang

Kumar Ramaswamy

Weiwei Feng

Mingyuan Yang

Xiangyang Ji

Alton Keel

Benyuan Zhang

Yueming Wang

Debin Zhao

Xiubao Jiang

Yang Zhao

Louis Robert Litwin

Xinxin Zhang

Jialing Li

Bing Jian

Manoj Viswambharan

Dirk Schmitt

Mengdi Fan

Ye He

Li Ni Zhang

Stephan Wenger

Hang Liu

Jun Li

Qi Zhang

Rong Wang

Philippe Gilberton

Jing Lv

Jingchang Chen

Yihao Zhang

Yonghong Tian

Yi Ting Shao

Guisen Xu

Peilei Dong

Mingmin Zhen

Chengzhou Tang

Lingyu Duan

Jing Lei

Tie Jun Huang

Qufang Huang

Yu Wang

Qiang Wang

Yi Guo

Richard W Citta

Dong Wang

Lei Chen

Shaw-Min Lei

Xiaoying Xu

Jie Chen

Lu Yu

Xin Zhao

Lei Zhang

Lin Li

Xunan Mao

Guillaume Bichot

Chenchen Gu

Yun He

Zoran Kostic

Gregory William Cook

Charles Chuanming Wang

Sheng Wang

Ivonete Markman

Yuqing Li

Boyun Xie

Wenji Liu

Zhihui Gong

Chao Wang

Shaily Verma

Lianhuan Xiong

Yinghua Huang

Yiting Shao

Xiaofei Ma

Hongbin Cao

Xi Xie

Yan Bai

Zhihao Li

Hao Lv

Zuoyan Zhu

A method, computer program, and computer system is provided for point cloud coding. The method includes receiving, from a bitstream, data corresponding to a point cloud; obtaining from the data a first prediction residual of a first component from among a plurality of components of an attribute associated with the point cloud; reconstructing the first prediction residual; determining a predicted second prediction residual based on the reconstructed first prediction residual and at least one model parameter; obtaining a second prediction residual of a second component from among the plurality of components based on the predicted second prediction residual; reconstructing the second prediction residual; and decoding the data corresponding to the point cloud based on the reconstructed first prediction residual and the reconstructed second prediction residual.

Coding of multiple-component attributes for point cloud coding

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

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.

Enhancement process for video coding for machines

Methods and apparatuses of grid-based patch generation for point cloud coding are provided. The method includes obtaining an input that is a point cloud; grouping one or more voxels in the point cloud into one or more grids, the one or more grids having a cubic dimension; determining whether the cubic dimension associated with the one or more grids exceeds a threshold value; in response to determining the cubic dimension exceeds the threshold value, generating a gridded point cloud; generating one or more patches in the gridded point cloud; converting the one or more patches in the gridded point cloud to one or more patches in the input point cloud; outputting the one or more patches to one or more output devices.

Grid-based patch generation for video-based point cloud coding

A technique for encoding video for machine vision and human/machine hybrid vision, including receiving image data. The technique may also include detecting a plurality of bounding boxes associated with a plurality of objects of interest in a frame of the image data and detecting a frame-level bounding box for the frame based on coordinates of the plurality of bounding boxes. Then, the technique may include encoding the frame-level bounding box using a first bitrate.

Region of interest coding for VCM

Aspects of the disclosure provide methods and apparatuses for point cloud compression and decompression. In some examples, an apparatus for point cloud compression/decompression includes processing circuitry. The processing circuitry determines to use a prediction mode for coding (encoding/decoding) information associated with a current point in a point cloud. In the prediction mode, the information associated with the current point is predicted based on one or more neighbor points of the current point. The processing circuitry calculates, using integer operations, a distance-based weighted average value based on distances of the one or more neighbor points to the current point, and determines the information associated with the current point based on the distance-based weighted average value.

Method and apparatus for calculating distance based weighted average for point cloud coding

According to an aspect of the disclosure, a method of point cloud geometry encoding in a point cloud encoder is provided. In the method, geometry coding is performed on a point cloud at a first partition depth. Further, a plurality of largest coding units (LCUs) of the point cloud is determined at a second partition depth. A coding state of a LCU of the plurality of LCUs of the point cloud is set at the second partition depth. The geometry coding is performed on the plurality of LCUs of the point cloud at the second partition depth based on the coding state of the LCU at the second partition depth.

Method and apparatus for point cloud coding

A technique for encoding video for machine vision and human/machine hybrid vision, including receiving at a hybrid codec, input including at least one of video or image data, the hybrid codec including a first and second codec wherein the first codec is a traditional codec designed for human consumption and the second codec is a learning-based codec designed for machine vision; compressing the input using the first codec, wherein the compressing includes down-sampling the input using a down-sampling module and up-sampling the compressed input using an up-sampling module producing a residual signal; quantizing the residual signal to obtain a quantized representation of the input; entropy encoding the quantized representation of the input using one or more convolutional filter modules; and training one or more networks using the entropy encoded quantized representation.

Method and apparatus for video coding for machine vision

A method and apparatus for coding information of a point cloud may be performed by at least one processor and comprises: obtaining the point cloud including a set of points in a three-dimensional space; partitioning the point cloud into a tree structure comprising a plurality of nodes at different depths; encoding geometry information of the nodes; and encoding attribute information of the nodes before the entire point cloud is partitioned.

Node-based geometry and attribute coding for a point cloud

Methods and apparatuses of encoding a video stream encoded using video point cloud coding include obtaining a source point cloud; generating an occupancy map including one or more pixels based on the source point cloud, an occupancy value associated with each pixel being a non-binary value; encoding the occupancy map to generate an encoded occupancy map, wherein a block of the encoded occupancy map corresponds to the one or more pixels of the occupancy map; selecting an occupancy value of the block based on the one or more pixels; and generating an encoded video stream based on the selected occupancy value.

Non-binary occupancy map for video based point cloud coding

A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on reducing a size of an array corresponding to syntax elements for predictive tree-based coding of the point cloud. The data corresponding to the point cloud is decoded based on the reduced number of contexts.

Predictive tree-based geometry coding for a point cloud

In a method for point cloud processing, a bitstream corresponding to a sequence of coded point cloud frames is received. Whether an implicit geometry partition is enabled for the sequence of coded point cloud frames is determined. An octree representing a geometry of points in a bounding box in a coded point cloud frame in the sequence of coded point cloud frames is reconstructed based on whether the implicit geometry partition is determined to be enabled for the sequence of coded point cloud frames.

Implicit geometry partition for point cloud coding

An apparatus for point cloud coding, includes processing circuitry that receives a coded bitstream for a point cloud. The coded bitstream includes encoded data for nodes in an octree structure for the point cloud corresponding to three dimensional (3D) partitions of a space of the point cloud, node sizes of the nodes being associated with sizes of the corresponding 3D partitions of the nodes. The processing circuitry decodes, from the coded bitstream, a first set of occupancy codes for a first set of nodes in the nodes using a first coding order and a second set of occupancy codes for a second set of nodes in the nodes using a second coding order that is different from the first coding order. Further, the processing circuitry reconstructs the octree structure based on at least the first set of occupancy codes and the second set of occupancy codes.

Hybrid coding order for point cloud coding

Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for point cloud compression. An apparatus includes processing circuitry that encodes information associated with a current point of a plurality of points of a point cloud. The plurality of points is partitioned into multiple bounding boxes. The processing circuitry determines whether a first size of a hash table is greater than or equal to a predetermined maximum size of the hash table. The processing circuitry removes information associated with non-boundary points in the multiple bounding boxes from the hash table based on the first size of the hash table being greater than or equal to the predetermined maximum size of the hash table. The processing circuitry stores the encoded information associated with the current point into the hash table.

Method and apparatus for constructing a 3D geometry

Systems, devices, and methods for performing feature compression, including obtaining an input video; obtaining a feature map corresponding to the input video, the feature map including a plurality of feature channels; reordering the plurality of feature channels based on at least one characteristic of the plurality of feature channels; compressing the reordered plurality of feature channels; and generating an encoded bitstream based on the compressed and reordered plurality of feature channels.

Feature compression for video coding for machines

Growing community of inventors

West Windsor, NJ, United States of America

Wen Gao