Tencent America LLC

Qualcomm Incorporated

Other

Cisco Technology, Inc.

International Business Machines Corporation

Marvell International Limited

Nxp Usa, Inc.

Fair Isaac Corporation

Hygon Information Technology Co., Ltd.

Bluevalley Pharmaceutical LLC

Xiang Yang Li

Shan Liu

Xin Zhao

Xiaozhong Xu

Guichun Li

Liang Zhao

Marta Karczewicz

Jianle Chen

Meng Xu

Li Feng Zhang

Wei-Jung Chien

Hsiao-Chiang Chuang

Cheung Auyeung

Krishnakanth Rapaka

Ying Hai Chen

Ling Li

Yi-Wen Chen

Jing Ye

Vadim Seregin

Stephan Wenger

Hongbin Liu

Yixin Du

Kai Zhang

Ye-Kui Wang

Lien-Fei Chen

Byeongdoo Choi

Wei Pu

Yu-Chen Sun

Feng Zou

Joel Sole Rojals

Liwei Guo

Chao Pang

Sungwon Lee

Done Bugdayci Sansli

Adarsh Krishnan Ramasubramonian

Rajan Laxman Joshi

Cheng-Teh Hsieh

Bin Zhu

Yeqing Wu

Anish Tamse

Vijayaraghavan Thirumalai

Nan Hu

David M Lubensky

Ea-Ee Jan

Osamuyimen Stewart

He Huang

Jiannong Gu

Jente Benedict Kuang

Scott Michael Zoldi

Dmytro Rusanovskyy

Madhu Peringassery Krishnan

Amir Said

Chulkyu Lee

James Robert Feddeler

Michael A Stockinger

Keith Alan Bowman

Xiaoyue Wang

Chengjie Tu

Fadi Adel Hamdan

Nadeem Eleyan

Xiaosong Du

Jehangir Athwal

Yanlin Guan

Prasanna Upadhyaya

Arvind Anumula Paramanandam

Gregory C Edgington

Congyi Xu

Soo-Chul Han

Richard W Moseley

Mihir Suchak

Nakul Midha

Varun Radhakrishnan

A method of and an apparatus for controlling intra prediction for decoding of a video sequence are provided. The method includes setting a table including a plurality of intra prediction modes respectively corresponding to a plurality of intra prediction angles, the plurality of intra prediction angles including diagonal intra prediction angles respectively corresponding to diagonal directions of all shapes of coding units, and selecting, for decoding the video sequence, one of the plurality of intra prediction modes, from the set table.

Reference sample padding and filtering for intra prediction in video compression

A method for video decoding in a decoder includes deriving for a block encoded under an intra prediction mode, a candidate list that includes a first candidate intra prediction mode value (Mode) that corresponds to an intra prediction mode of a neighbor block that neighbors the encoded block as a first one of the plurality of intra prediction modes, and a second candidate intra prediction mode value (Mode) and a third candidate intra prediction mode value (Mode) that are determined in accordance with a predetermined offset from the first candidate intra prediction mode value and a modulo M operation. The method further includes determining an intra prediction mode value for the encoded block in accordance with the derived candidate list.

Method and apparatus for most probable mode derivation

A method and apparatus for encoding or decoding a video sequence includes applying a Cross-Component Linear Model (CCLM) to a video sequence, and applying an interpolation filter in the Cross-Component Linear Model (CCLM), wherein the interpolation filter is dependent upon a YUV format of the video sequence.

Method and apparatus for video encoding or decoding

A method of decoding an encoded video. The method includes obtaining the encoded video bitstream and determining whether a chroma array type of a video sequence included in the encoded video bitstream is a first chroma array type indicating that the video sequence includes multiple color planes and that the multiple color planes are jointly. In addition, based on determining that the chroma array type is not the first chroma array type, the method further includes setting a value of at least one syntax element to zero without parsing the at least one syntax element from the encoded video bitstream, and based on the value of the at least one syntax element being zero, decoding the video sequence without applying at least one tool corresponding to the at least one syntax element.

Signaling of video coding tools supporting various chroma format

A method, computer program, and computer system is provided for coding video data. Video data having a coding tree unit size is received. The coding tree unit size associated with the video data is signaled by setting two or more flags. The video data is encoded/decoded based on the flags corresponding to the signaled coding tree unit size.

Coding tree unit size signaling

Aspects of the disclosure provide methods and apparatuses for video coding. In some examples, an apparatus includes processing circuitry that obtains motion information of a group of blocks in a picture from a coded video bitstream, the motion information indicating base motion vectors for the group of blocks, and the base motion vectors pointing to a reference picture in a prediction list. The processing circuitry determines a range of target motion vectors for the group of blocks along a particular coordinate direction according to the base motion vectors and a target difference, where, for any two motion vector within the range, a difference of integer-pixel parts thereof along the particular coordinate direction is equal to or less than the target difference. The processing circuitry further converts the base motion vectors into the target motion vectors according to the range for reconstructing samples of the group of blocks.

Constraining motion vectors of groups of blocks

In a method, coded information of a current block in a current picture of a video is received from a coded video bitstream. The coded information indicates that the current block is partitioned into at least a first partition and a second partition based on a geometric partition mode (GPM). The first partition is associated with an intra block copy (IBC) prediction mode, and the second partition is associated with an intra prediction mode. Prediction mode information for a first subblock of a plurality of subblocks of the current block is stored. The prediction mode information includes one of a DC mode, a Planar mode, and an intra prediction mode based on whether the first subblock is associated with one of the IBC prediction mode, the intra prediction mode, and both the IBC prediction mode and the intra prediction mode.

Intra prediction mode information propagation for geometric partition mode with IBC and intra prediction

A method, apparatus and storage medium for performing a video quality assessment (VQA) are provided. The method includes obtaining a plurality of images of a video, the plurality of images being divided into one or more groups; determining first images among the plurality of images to which a parametric-based VQA is to be applied, the first images being all of the plurality of images; determining a first score based on applying the parametric-based VQA to each of the first images; determining second images among the plurality of images to which a sample-based VQA is to be applied; determining a second score based on applying the sample-based VQA to each of the second images; and outputting a final score for at least one image based on the first score and the second score.

Methods of video quality assessment using parametric and pixel level models

Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. The processing circuitry determines that a non-interleaved separate tree structure is used for coding different color components of coding tree units (CTUs) in a bitstream. The processing circuitry decodes a first color component of a plurality of CTUs from a first portion of the bitstream, and decodes a second color component of the plurality of CTUs from a second portion of the bitstream, the second portion is located after the first portion in the bitstream.

Non-interleaved separate tree

A method of utilizing an N-point primary transform core matrix to encode may include determining whether to use a first transform core matrix that is an N-point 8-bit primary transform core matrix. When a result of the determination is to use the first transform core matrix, the method may include: (i) constructing the first transform core based on a set of unique numbers, and (ii) encoding using the derived primary transform core. The method may further include, when a result of the determination is to not use the first primary transform: (i) deriving a second transform core based on the same set of unique numbers, and (ii) encoding using the derived second transform core.

Method, apparatus and medium for decoding

A method, computer program, and computer system is provided for video coding. Video data comprising a reference frame and residual blocks is received. Transform coefficients associated with the residual blocks are identified. The video data corresponding to the one or more residual blocks is encoded based on an extended dynamic range associated with the transform coefficients.

Method to extend the range of rice parameter for residual coding in transform skip mode

Aspects of the disclosure provide methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. In a method, whether an adaptive color transform (ACT) is enabled for a current block is determined. A maximum transform size is determined based on whether the ACT is enabled for the current block. Whether a subblock transform (SBT) is applied to the current block is determined based at least on the maximum transform size. Further, the SBT is performed on the current block based on the SBT being determined to be applied to the current block.

Defining transform size and subblock transform based on adaptive color transform

Aspects of the disclosure provide methods and apparatuses for cloud gaming. In some examples, an apparatus for cloud gaming includes processing circuitry. For example, the processing circuitry receives a video sequence and metadata associated with the video sequence. The video sequence includes a sequence of picture frames generated in response to gaming control information, and the metadata is determined based on the gaming control information. The processing circuitry can determine, based on the metadata, an encoding configuration for encoding the video sequence. Then the processing circuitry encodes, based on the encoding configuration, the video sequence into a coded video bitstream.

Method and apparatus for cloud gaming

Aspects of the disclosure provide methods and apparatuses for video processing. In some examples, an apparatus for video processing includes processing circuitry. The processing circuitry converts a picture in a subsampled format in a color space into a non subsampled format in the color space. Then, the processing circuitry clips values of a color component of the picture in the non subsampled format before providing the picture in the non subsampled format as an input to a neural network based filter.

Method and apparatus for video coding

In a method of video encoding for an encoder, a determination is made to determine whether (i) an implicit transform scheme is enabled, and (ii) at least one of a low-frequency non-separable transform (LFNST) and a matrix-based intra predication mode (MIP) is invalid for a coding unit (CU). In response to the determination that the implicit transform scheme is enabled, and at least one of the LFNST and MIP is invalid, a primary transform type is determined based on a size of the CU. A primary transform is performed for a transform block that is partitioned from the CU in accordance with the determined primary transform type. A coded bitstream that indicates the primary transform type of the CU is subsequently output.

Method and apparatus for improved implicit transform selection

Growing community of inventors

Houston, TX, United States of America

Xiang Yang Li