Beijing Dajia Internet Information Technology Co., Ltd.

Qualcomm Incorporated

Nokia Corporation

Nokia Technologies Oy

Xianglin Wang

Yi-Wen Chen

Xiaoyu Xiu

Marta Karczewicz

Bing Yu

Tsung-Chuan Ma

Hong-Jheng Jhu

Wei Chen

Wei-Jung Chien

In Suk Chong

Liwei Guo

Vadim Seregin

Geert Van Der Auwera

Yunfei Zheng

Peisong Chen

Muhammed Zeyd Coban

Cheng-Teh Hsieh

Jianle Chen

Joel Sole Rojals

Rajan Laxman Joshi

Xin Zhao

Ying Hai Chen

Ye-Kui Wang

Woo-Shik Kim

Li Feng Zhang

Hongbin Liu

Miska Matias Hannuksela

Han Gao

Che-Wei Kuo

Shuiming Ye

Ning Yan

Chengjie Tu

Justin Ridge

Yang Yu

Jaehong Chon

Guoxin Jin

Yiliang L Bao

Sungwon Lee

Yucong Chen

Yue Huang

Shufei Fan

Xing Wen

Hsiao-Chiang Chuang

Kai Wang

Sanjeev Kumar

Prasanjit Panda

Shu Xiao

Hariharan Ganesh Lalgudi

Siping Tao

Mayank Tiwari

Hong-Jheng Zhu

Yun-fei Zheng

Shashidhar Jangili

Ying Chen

A method of video decoding, a method of video encoding, apparatuses and non-transitory computer-readable storage media thereof are provided. The method of video decoding includes obtaining one or more constructed motion vector (MV) candidates from a plurality of non-adjacent neighbor blocks to a current block by jointly or independently scanning a plurality of scanning areas at one or more scanning distances, where one scanning distance indicates a number of blocks away from one side of the current block. Furthermore, the method may include obtaining one or more control point motion vectors (CPMVs) for the current block based on the one or more constructed MV candidates.

Methods and devices for candidate derivation for affine merge mode in video coding

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. In one method, a decoder obtains a signaled flag that indicates whether a template-based intra mode derivation (TIMD) mode is applied on a current video block; and in response to determining that the TIMD mode is applied on the current video block based on the signaled flag, the decoder derives an intra prediction mode from the TIMD mode based on different templates in a reconstruction area for the current video block, wherein the reconstruction area comprises reconstructed neighboring blocks for the current video block.

Methods and devices for decoder-side intra mode derivation

A method and an apparatus for hybrid training of neural networks for video coding are provided. The method includes: obtaining, in an offline training stage, an offline trained network by training a neural network offline; and refining, in an online training stage, a plurality of neural network layers with constraint on a plurality of parameters of the plurality of neural network layers, where the plurality of neural network layers may include at least one neural network layer in the offline trained network or in a simple neural network connected to the offline trained network.

Network based image filtering for video coding

Implementations of the disclosure provide a video processing apparatus and method for intra prediction in video coding with an adaptive coding order. The method may include receiving, by one or more processors, one or more reference blocks from a video frame of a video for performing intra prediction on a video block of the video frame. The method may include dividing, by the one or more processors, the video block into a plurality of video sub-blocks. The method may include determining, by the one or more processors, the adaptive coding order for the plurality of video sub-blocks. The method may include generating, by the one or more processors, a plurality of reconstructed sub-blocks for the plurality of video sub-blocks based on the adaptive coding order and the one or more reference blocks. The plurality of reconstructed sub-blocks form a reconstructed block for the video block.

Adaptive coding order for intra prediction in video coding

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. The method includes: in response to determining that transform skip is disabled, disabling, by a decoder, a presence of a rice parameter for transform skip residual coding. The method may further include adopting a flag of transform skip, sps_transform_skip_enabled_flag, to condition a presence of sps_ts_residual_coding_rice_present_in_sh_flag.

Residual and coefficients coding for video coding

Provided is a method for video decoding including: receiving a control variable enabling adaptive switch between motion vector refinement (MVR) offset sets; receiving an indication variable enabling adaptive switch between codeword tables that binarize offset magnitudes in the MVR offset sets under the coding level; partitioning the video block into a first and a second geometric partition; selecting an MVR offset set based on the control variable; receiving syntax elements to determine a first and second MVR offsets applied to the first and second geometric partitions from the selected MVR offset set; obtaining a first and second MVs from a candidate list for the first and the second geometric partition; calculating a first and second refined MVs based on the first and second MVs and the first and second MVR offsets; and obtaining prediction samples based on the first and second refined MVs.

Methods and devices for geometric partition mode with motion vector refinement

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for PROF. A decoder obtains first reference picture and second reference picture associated with a video block that is coded by affine mode within a video signal. The decoder obtains first and second horizontal and vertical gradient values based on first prediction samples I(i,j) and second prediction samples I(i,j) associated with the first reference picture and second reference picture. The decoder obtains first and second horizontal and vertical motion refinements based on CPMVs associated with the first reference picture and second reference picture. The decoder obtains first prediction refinement ΔI(i,j) and second prediction refinement ΔI(i,j) based on the horizontal and vertical gradient values and the first and second horizontal and vertical motion refinements. The decoder obtains final prediction samples of the video block.

Methods and apparatus for prediction refinement with optical flow

Method and devices are provided for video coding. In the method, a decoder obtains a cross-component sample adaptive offset (CCSAO) quantization associated with an offset quantization control syntax and a quantization step size that are predefined or indicated by an encoder at at least one level. Furthermore, the decoder obtains a CCSAO based on the CCSAO quantization and adds the CCSAO to a reconstructed sample for prediction.

Cross-component sample adaptive offset

A method and an apparatus for image filtering in video coding using a neural network are provided. The method includes: loading, a plurality of quantization parameter (QP) map (QpMap) values at a plurality of QpMap channels into the neural network; obtaining a QP scaling factor by adjusting a plurality of input QP values related to an input frame; and adjusting, according to a QP scaling factor, the plurality of QpMap values for the neural network to learn and filter the input frame to the neural network.

An electronic apparatus performs a method of decoding video signal, including: receiving, from the video signal, a picture frame that includes a first component, and a second component; selecting an edge direction across a collocated sample of the first component or a current sample of the second component relative to the respective sample of the second component; calculating a first edge strength determining a difference between values of two samples from the group consisting of the collocated or current sample, a first neighbouring sample, and a second neighbouring sample; quantizing the first edge strength into M segments according to M−1 threshold values; determining the classifier for the respective sample of the second component based on the M segments; determining a sample offset for the respective sample of the second component according to the classifier; and modifying the respective sample of the second component based on the determined sample offset.

Coding enhancement in cross-component sample adaptive offset

An electronic apparatus performs a method of decoding video data, comprising: receiving, from the video signal, a picture frame that includes a first component and a second component in a first color space; determining a classifier for the second component in the first color space from a set of one or more samples of the first component associated with a respective sample of the second component in the first color space, wherein the set of one or more samples are in a second color space; determining a sample offset for the respective sample of the second component in the first color space according to the classifier; and modifying the value of the respective sample of the second component in the first color space based on the determined sample offset.

Methods and devices are provided for rectifying a forward mapping coding bit length issue introduced by LMCS. In one method, a plurality of prediction samples, in a mapped domain, of luma component of a CU that is coded by a CIIP mode under LMCS framework is obtained, a plurality of residual samples, in the mapped domain, of the luma component of the CU is obtained, the plurality of prediction samples in the mapped domain is added to the plurality of residual samples in the mapped domain, resulting in a plurality of reconstructed samples, in the mapped domain, of the luma component, and the plurality of reconstructed samples of the luma component is converted from the mapped domain into an original domain based on a pre-defined plurality of inverse mapping scaling factors.

Methods and devices for prediction dependent residual scaling for video coding

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for decoding a video signal. A method may include obtain a first reference picture and a second reference picture associated with a video block, wherein the first reference picture is before a current picture and the second reference picture is after the current picture in display order; obtain first prediction samples of the video block from the first reference picture; obtain second prediction samples of the video block from the second reference picture; obtain padded prediction samples, and obtain horizontal and vertical gradient values of the first prediction samples and the second prediction samples based on the padded prediction samples; obtain motion refinements for samples in the video block based on the horizontal and vertical gradient values; and obtain bi-prediction samples of the video block based on the motion refinements.

Methods and apparatuses for prediction refinement with optical flow

Methods and apparatuses are provided for video coding with lossless coding modes. The method includes: partitioning a video picture into a plurality of CUs comprising a lossless CU; determining a residual coding block size of the lossless CU; and in response to determining that the residual coding block size of the lossless CU is greater than a predefined maximum value, splitting the residual coding block into two or more residual blocks for residual coding.

Lossless coding modes for video coding

A method for video coding is provided. The method includes: determining a signaling of merge modes for deriving motion information of a current block, where the merge modes include: regular merge mode and extended merge modes; and deriving motion information of the current block using the regular merge mode, upon determining that the signaling of merge modes includes a positive signal of regular merge mode.

Methods and apparatuses for signaling of merge modes in video coding

Growing community of inventors

San Diego, CA, United States of America

Xianglin Wang