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

Guangdong Oppo Mobile Telecommunications Corp., Ltd.

Alibaba Singapore Holding Private Limited

Alibaba Damo (hangzhou) Technology Co., Ltd.

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

Mohammed Golam Sarwer

Jie Dong

Peisong Chen

Ralph Neff

Ahmed Hamza

Philippe Hanhart

Zhao Wang

Xinwei Li

George W McClellan

Alexandros Michael Tourapis

Yiliang L Bao

Eduardo Asbun

Eun Seok Ryu

Srinivas Gudumasu

Ali C Begen

Chia-Ming Tsai

Yan Zhang

Peng Yin

Louis Joseph Kerofsky

Giovanni Motta

Qian Chen

Rahul Vanam

Markus Kunstner

Can Bal

Guan-Ming Su

Walter Christian Gish

Sheng Qu

Chia-Yuan Teng

Ming-Chang Tsai

Rahul P Panchal

Chun-Chi Chen

Ariela Zeira

Yuriy Reznik

Samir N Hulyalkar

Sharath Manjunath

Yufei Yuan

Zhifeng Chen

Xuan Huang

Saurav Bandyopadhyay

Shurun Wang

Eun Ryu

Wei-Jung Chien

Eldad M Zeira

Liangping Ma

Anantharaman Balasubramanian

Athanasios Leontaris

Gregory S Sternberg

Hang Liu

Peshala Vishvajith Pahalawatta

Arash Vosoughi

Gokce Dane

Byung Kwan Yi

Narendranath Malayath

Yen-Chi Lee

Hyukjune Chung

Shiqi Wang

Fanyi Duanmu

Jianhua Chen

Thorsten Laude

Yin Peng

Shengyang Xu

Changyue Ma

Naresh Soni

Yamei Chen

Karl Ni

Nien-Chung Feng

Enming Luo

Maryam Azimi Hashemi

Jiun-Yu Kao

Miaohui Wang

Ruling Liao

George W Mcclellan

Chen Peisong

A time-domain filtering method is provided, including: determining a to-be-filtered image frame in a group of pictures; extracting a relative motion feature of the to-be-filtered image frame, where the relative motion feature represents relative motion complexity between image contents of the to-be-filtered image frame and image contents of the remaining image frames in the group of pictures; and determining a target filtering magnitude corresponding to the relative motion feature, and performing time-domain filtering on the to-be-filtered image frame by using the target filtering magnitude.

Time-domain filtering method and apparatus, electronic device, and computer-readable storage medium

A method for performing motion compensation includes: receiving a first wrap-around motion compensation flag associated with one or more pictures, and a second wrap-around motion compensation flag associated with a sequence of pictures; and determining whether the first wrap-around motion compensation flag is equal to a first value or a second value based on the second wrap-around motion compensation flag or a luma coding tree block size: when the second wrap-around motion compensation flag is equal to the second value, determining the first wrap-around motion compensation flag equal to the second value, or when the luma coding tree block size in unit of minimum coding block plus 1 is greater than a picture width in unit of minimum coding block minus 1, determining the first wrap-around motion compensation flag is equal to the second value.

Methods for performing wrap-around motion compensation

Video encoding and decoding techniques for bi-prediction with weighted averaging are disclosed. According to certain embodiments, a computer-implemented video signaling method includes signaling, by a processor to a video decoder, a bitstream including weight information used for prediction of a coding unit (CU). The weight information indicates: if weighted prediction is enabled for a bi-prediction mode of the CU, disabling weighted averaging for the bi-prediction mode.

On block level bi-prediction with weighted averaging

Embodiments of video coding systems and methods are described for reducing coding latency introduced by decoder-side motion vector refinement (DMVR). In one example, two non-refined motion vectors are identified for coding of a first block of samples (e.g. a first coding unit) using bi-prediction. One or both of the non-refined motion vectors are used to predict motion information for a second block of samples (e.g. a second coding unit). The two non-refined motion vectors are refined using DMVR, and the refined motion vectors are used to generate a prediction signal of the first block of samples. Such embodiments allow the second block of samples to be coded substantially in parallel with the first block without waiting for completion of DMVR on the first block. In additional embodiments, optical-flow-based techniques are described for motion vector refinement.

Methods and apparatus for reducing the coding latency of decoder-side motion refinement

The present disclosure provides methods and systems for motion compensation. The method can include: determining a plurality of intermediate interpolation coefficients of an interpolation filter, the determining of the plurality of intermediate interpolation coefficients being: based on positions of a plurality of integer samples respectively, and based on fractional reference positions of a plurality of fractional samples respectively; determining a plurality of integer interpolation coefficients of the interpolation filter by rounding the plurality of intermediate interpolation coefficients to a plurality of integers respectively; and applying the plurality of integer interpolation coefficients on a picture to perform motion compensation prediction.

Motion compensation methods for video coding

The present disclosure provides systems and methods for signaling a maximum transform size and a residual coding method. According to certain disclosed embodiments, the methods include: receiving a bitstream comprising a set of pictures, determining, according to the received bitstream, a value of a coded tree block size; and determining, based on the value of the coded tree block size, whether to signal a flag indicating a maximum transform size for luma samples.

Signaling of maximum transform size and residual coding method

Techniques are described for encoding and decoding digital video data using macroblocks that are larger than the macroblocks prescribed by conventional video encoding and decoding standards. For example, the techniques include encoding and decoding a video stream using macroblocks comprising greater than 16×16 pixels. In one example, an apparatus includes a video encoder configured to encode a coded unit comprising a plurality of video blocks, wherein at least one of the plurality of video blocks comprises a size of more than 16×16 pixels and to generate syntax information for the coded unit that includes a maximum size value, wherein the maximum size value indicates a size of a largest one of the plurality of video blocks in the coded unit. The syntax information may also include a minimum size value. In this manner, the encoder may indicate to a decoder the proper syntax decoder to apply to the coded unit.

Video coding with large macroblocks

Methods and apparatuses for video encoding, comprising: receiving a video sequence; encoding the video sequence by using control flags for luma mapping with chroma scaling (LMCS) at a sequence level, a picture level, or a slice level, wherein the sequence level, the picture level, and the slice level are levels ranking from high to low; signaling a first control flag indicating whether the LMCS is enabled at a first level; and in response to the first control flag indicating the LMCS is enabled at the first level, signaling a second control flag indicating whether LMCS is enabled at a second level, wherein: the LMCS is enabled at the second level when a value of the second control flag equals to 1; the LMCS is disabled at the second level when the value of the second control flag equals to 0; and the second level is a lower level than the first level.

High level syntax control of loop filter

An image data encoding method is provided. The image data encoding method includes receiving an input image and a quantization parameter (QP); performing pre-analysis of the input image based on the QP to obtain input image data for machine version; determining at least one of a temporal redundancy or a spatial redundancy of the input image data; determining, based on the at least one of temporal redundancy or spatial redundancy, whether to perform at least one of temporal down-sampling or spatial down-sampling; performing down-sampling of the input image data according to the determination, wherein the down-sampling includes at least one of temporal down-sampling or spatial down-sampling; and encoding the down-sampled image data based on the QP.

Methods and non-transitory computer readable storage medium for pre-analysis based resampling compression for machine vision

A method for performing combined inter and intra prediction (CIIP) includes determining the CIIP being enabled for a target block; determining a first intra prediction mode of the target block using a template-based intra mode derivation (TIMD) method; generating an intra predictor of the target block with the first intra prediction mode; and obtaining a final predictor of the target block by weighted averaging the intra predictor of the target block and an inter predictor of the target block.

Methods and systems for performing combined inter and intra prediction

The present disclosure provides systems and methods for processing video content. The method can include: partitioning, along a partitioning edge, a plurality of blocks associated with a picture into a first partition and a second partition; performing inter prediction on the plurality of blocks, to generate a first prediction signal for the first partition and a second prediction signal for the second partition; and blending the first and second prediction signals for edge blocks associated with the partitioning edge.

Block partitioning methods for video coding

The present disclosure provides methods for performing training and executing of a multi-density neural network in video processing. An exemplary method comprises: receiving a video stream comprising a plurality of pictures; processing the plurality of pictures using a first branch of a first block in the neural network, wherein the neural network is configured to reduce blocking artifacts in video compression of the video stream and the first branch comprises one or more residual blocks; and processing the plurality of pictures using a second branch of the first block in the neural network, wherein the second branch comprises a down-sampling processing, an up-sampling processing, and one or more residual blocks.

Neural network based in-loop filtering for video coding

In a method of encoding a video sequence into a bitstream, an encoder determines, based on a value of a first encoded flag, whether to encode a second flag into the bitstream. The first flag indicates whether sign data hiding is turned off at a slice level for a video frame. The second flag indicates whether transform skip residual coding is turned off at the slice level for the video frame.

Sign data hiding of video recording

A VVC-standard encoder and a VVC-standard decoder are provided, implementing a decoder-side chroma intra prediction mode gradient-based derivation method, which improves coding efficiency of chroma intra prediction, thereby saving on signaling cost. A VVC-standard decoder configures one or more processors of a computing system to derive one of multiple possible chroma intra prediction modes by computing gradients of adjacent luma samples and chroma samples of a current chroma block. With minimal increase in signaling cost, the VVC-standard coding and decoding processes are enhanced to base intra prediction modes for chroma blocks on collocated luma block-adjacent reconstructed luma samples adjacent reconstructed chroma samples, enabling prior computational work done on coding and decoding adjacent blocks to be referenced. In this fashion, coding gains can be achieved in matching texture characteristics of the current chroma block based on a texture gradient including adjacent blocks.

Decoder-side chroma intra prediction mode gradient-based derivation

The present disclosure provides systems and methods for processing video content using motion compensation interpolation. The methods include: encoding or decoding a picture block by applying one or more filters to a reference picture, wherein the applying of the one or more filters generates a sample at a fractional sample position, and wherein the one or more filters comprise an 8-tap filter that has a plurality of coefficients [p0, p1, . . . , p7] for each 1/16 fractional sample position p.

Filters for motion compensation interpolation with reference down-sampling

Growing community of inventors

San Diego, CA, United States of America

Yan Ye