Vid Scale, Inc.

Alibaba Group Holding Limited

Qualcomm Incorporated

Interdigital Madison Patent Holdings, Sas

Interdigital Vc Holdings, Inc.

Dolby Laboratories Licensing Corporation

Alibaba (china) Co., Ltd.

Alibaba Innovation Private Limited

Interdigital Patent Holdings, Inc.

Velos Media, LLC

Alibaba Damo (hangzhou) Technology Co., Ltd.

Guangdong Oppo Mobile Telecommunications Corp., Ltd.

Alibaba Singapore Holding Private Limited

Alibaba Group Holding Limtted

Atibaba Group Holding Limited

Yan Ye

Yuwen He

Xiaoyu Xiu

Jiancong Luo

Ru-Ling Liao

Jie Chen

Yong He

Marta Karczewicz

Jie Dong

Mohammed Golam Sarwer

Peisong Chen

Zhao Wang

Ralph Neff

Ahmed Hamza

Xinwei Li

George W McClellan

Alexandros Michael Tourapis

Yiliang L Bao

Eduardo Asbun

Yan Zhang

Peng Yin

Louis Joseph Kerofsky

Giovanni Motta

Qian Chen

Shiqi Wang

Rahul Vanam

Guan-Ming Su

Walter Christian Gish

Sheng Qu

Chia-Yuan Teng

Ming-Chang Tsai

Ariela Zeira

Yuriy Reznik

Samir N Hulyalkar

Sharath Manjunath

Wei-Jung Chien

Eldad M Zeira

Liangping Ma

Anantharaman Balasubramanian

Athanasios Leontaris

Gregory S Sternberg

Hang Liu

Khaled Helmi El-Maleh

Philippe Hanhart

Eun Seok Ryu

Srinivas Gudumasu

Ali C Begen

Chia-Ming Tsai

Markus Kunstner

Can Bal

Saurav Bandyopadhyay

Rahul P Panchal

Chun-Chi Chen

Shurun Wang

Yufei Yuan

Zhifeng Chen

Xuan Huang

Bolin Chen

Eun Ryu

Peshala Vishvajith Pahalawatta

Arash Vosoughi

Gokce Dane

Byung Kwan Yi

Narendranath Malayath

Yen-Chi Lee

Hyukjune Chung

Fanyi Duanmu

Thorsten Laude

Jianhua Chen

Yin Peng

Ruling Liao

Shengyang Xu

Ru-ling Liao

Changyue Ma

Mohammad Golam Sarwer

Enming Luo

Maryam Azimi Hashemi

Yamei Chen

Jiun-Yu Kao

Nien-Chung Feng

Karl Ni

Miaohui Wang

George W Mcclellan

Chen Peisong

He Yong

Fan Ling

Methods and apparatuses are provided for compressing video data based on keypoint features. An exemplary video compression method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream; wherein the encoding includes: representing a first picture by a first set of keypoints and a second set of keypoints, the second set comprising less keypoints than the first set; and compressing the video sequence based on the first set and second set of keypoints.

Keypoints based video compression

Methods and apparatuses are provided for processing video data. An exemplary method includes: decompressing a compressed frame to generate a key frame representing a face; generating, for the key frame, a first set of parameters associated with a 3-dimensional (3D) face representation of the face; reconstructing, for each of one or more inter frames, a second set of parameters associated with a 3D face representation of the face according to compressed inter-predicted residuals of the second set of parameters; and generating a video comprising the face based on the key frame, the first set of parameters, and the second set of parameters.

Method and apparatus for talking face video compression

Systems and methods are described for reducing the complexity of using bi-directional optical flow (BIO) in video coding. In some embodiments, bit-width reduction steps are introduced in the BIO motion refinement process to reduce the maximum bit-width used for BIO calculations. In some embodiments, simplified interpolation filters are used to generate predicted samples in an extended region around a current coding unit. In some embodiments, different interpolation filters are used for vertical versus horizontal interpolation. In some embodiments, BIO is disabled for coding units with small heights and/or for coding units that are predicted using a sub-block level inter prediction technique, such as advanced temporal motion vector prediction (ATMVP) or affine prediction.

Complexity reduction and bit-width control for bi-directional optical flow

A device may determine whether to enable or disable bi-directional optical flow (BIO) for a current coding unit (CU) (e.g., block and/or sub-block). Prediction information for the CU may be identified and may include prediction signals associated with a first reference block and a second reference block (e.g., or a first reference sub-block and a second reference sub-block). A prediction difference may be calculated and may be used to determine the similarity between the two prediction signals. The CU may be reconstructed based on the similarity. For example, whether to reconstruct the CU with BIO enabled or BIO disabled may be based on whether the two prediction signals are similar. It may be determined to enable BIO for the CU when the two prediction signals are determined to be dissimilar. For example, the CU may be reconstructed with BIO disabled when the two prediction signals are determined to be similar.

Motion-compensation prediction based on bi-directional optical flow

The present disclosure provides methods for convolutional-neural-network (CNN) based filter for video coding. An exemplary method includes: applying motion estimation to a target coding block, to determine a reference block of the target coding block; inputting, to a convolutional neural network (CNN) filter, image data associated with the target coding block and the reference block; and executing the CNN filter to determine a residual associated with the target coding block based on the input image data.

Convolutional-neutral-network based filter for video coding

Systems, methods, and instrumentalities are described herein for calculating local illumination compensation (LIC) parameters for bi-predicted coding unit (CU). The LIC parameters may be used to generate adjusted samples for the current CU and to address local illumination changes that may exist among temporal neighboring pictures. LIC parameters may be calculated based on bi-predicted reference template samples and template samples for a current CU. Bi-predicted reference template samples may be generated based on reference template samples neighboring temporal reference CUs. For example, the bi-predicted reference template samples may be generated based on averaging the reference template samples. The reference template samples may correspond to template samples for the current CU. A CU may be or may include a coding block and/or a sub-block that may be derived by dividing the coding block.

Motion compensated bi-prediction based on local illumination compensation

An input video or video stream may be obtained or received. The input video or video stream may include a plurality of video frames, and each frame may be divided into a plurality of blocks. A current block of the plurality of blocks may be predicted using a planar mode. Depending on which planar mode is used, different reference samples may be used for predicting a current sample in the current block.

On planar intra prediction mode

A coding device (e.g., that may be or may include encoder and/or decoder) may receive a frame-packed picture of 360-degree video. The coding device may identify a face in the frame-packed picture that the current block belongs to. The coding device may determine that a current block is located at a boundary of the face that the current block belongs to. The coding device may identify multiple spherical neighboring blocks of the current block. The coding device may identify a cross-face boundary neighboring block. The coding device may identify a block in the frame-packed picture that corresponds to the cross-face boundary neighboring block. The coding device may determine whether to use the identified block to code the current block based on availability of the identified block. The coding device may code the current block based on the determination to use the identified block.

360-degree video coding using face continuities

Methods for encoding a video sequence into a bitstream and decoding a bitstream to output one or more pictures for a video stream. An exemplary method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream associated with the encoded pictures, wherein the encoding comprises: predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs).

Cross component prediction

A video processing method is provided. The method includes inserting a set of spatial merge candidates to a first merge candidate list of a coding block, wherein the first merge candidate list is constructed by: adding a top neighboring block Bto the first merge candidate list when the top neighboring block Bis available; adding a left neighboring block Ato the first merge candidate list when the left neighboring block Ais available; adding a top neighboring block Bto the first merge candidate list when the top neighboring block Bis available; adding a left neighboring block Ato the first merge candidate list when the left neighboring block Ais available; and adding an above-left neighboring block Bto the first merge candidate list when the above-left neighboring block Bis available.

Methods for constructing a merge candidate list

A VVC-standard encoder and a VVC-standard decoder are provided, implementing a residual sign prediction method utilizing a sorting order of residual coefficients and an expanded region of a TB. As sign prediction accuracy is higher for larger transform coefficient levels, a VVC-standard encoder and a VVC-standard decoder sort transform coefficient signs of a TB in a one-dimensional array, based on corresponding QIdx values instead of the residual coefficient level value. The first n signs according to corresponding QIdx values, ordered from largest to smallest, are predicted using a residual sign prediction method, and the rest of the signs are signaled by EP bins. A sign prediction area is also extended, without limitation to an upper-left 4×4 region within the transform block, but to a region up to 32×32 in size; a VVC-standard encoder signals the maximum dimensions of the region to a VVC-standard decoder in syntax structures of the block.

Residual sign prediction of transform coefficients in video coding

A method, an apparatus and non-transitory computer-readable storage medium for video data process are provided. The method includes receiving a bitstream comprising a coding unit coded in a geometric partition mode (GPM); decoding a first parameter associated with the coding unit, the first parameter indicating whether template matching being applied to the coding unit; and determining, according to the first parameter, motion information for the coding unit, wherein when the first parameter indicates the template matching is applied to the coding unit, the motion information is refined using the template matching.

Method, apparatus, and non-transitory computer-readable storage medium for motion vector refinement for geometric partition mode

The present disclosure provides pre-analysis based methods for adaptively compressing image data consumed by machine vision tasks. An exemplary method includes: receiving a video sequence; encoding one or more input pictures associated with the video sequence; and generating a bitstream, wherein the encoding includes: performing instance segmentation of an input picture, to generate one or more segment masks; combining the one or more segment masks to generate a merged mask; extracting, from the input picture, a region comprising the merged mask; and compressing image data representing the extracted region.

Pre-analysis based image compression methods

The present disclosure provides methods and apparatuses for signaling subpicture partitioning information. An exemplary method includes: determining, according to a subpicture information present flag signaled in a bitstream, whether the bitstream comprises subpicture information; and in response to the bitstream comprising the subpicture information, signaling in the bitstream at least one of: a number of subpictures in a picture, a width, a height, a position, and an identifier (ID) mapping of a target subpicture, a subpic_treated_as_pic_flag, and a loop_filter_across_subpic_enabled_flag.

Method and apparatus for signaling subpicture partitioning information

Growing community of inventors

San Diego, CA, United States of America

Yan Ye