Huawei Technologies Co., Limited

Orbbec Inc.

Emc IP Holding Company LLC

Wuhan China Star Optoelectronics Semiconductor Display Technology Co., Ltd.

Central China Normal University

Shenzhen Soocas Technology Co., Ltd.

Zte Corporation

Tencent Technology (Shenzhen) Company Limited

Guangdong University of Technology

Hubei University

Shenzhen Xianyu Power Technology Co., Ltd.

Zte Microelectronics Technology Co., Ltd

Robosen Robotics (Shenzhen) Co., Ltd

Xu Chen

Jianhua Zheng

Xing Xu

Yuanhao Huang

Zhenzhong Xiao

Jicheng An

Haitao Yang

Xiaolu Mei

Xiaozhen Zheng

Pan Xiao

Zhaomin Wang

Peilei Chen

Lianghong Zhong

Min Yan

Lian Zhang

Hao Wang

Fang Du

Huanbang Chen

Yongbing Lin

Hailan Dong

Si Zhang

Di Wu

Sheng Xu

Yin Zhao

Jilin Li

Chengjie Wang

Feiyue Huang

Sheng Jiang

Xudong Wang

Fandi Meng

Changxu Jiang

Zongkai Yang

Zheng Zhong

Zhenzong Jiang

Xiang Ma

Dewei Chen

Wan Lam

Ying Tai

Keke He

Jun Zhang

Yandan Zhao

Junwei Zhu

Xiaosen Chen

Aiqin Liu

Wenyin Liu

Xinwei Han

Liguo Feng

Xianzhuo Liu

Zhiming Huang

Guokun Ma

Xuan Song

Nan Song

Xiongnan Jiang

Hanbin Wang

Tianci Wu

Haozhao Wan

Sihua Hong

Hongbo Xu

Zhengrong Liu

Zhenguo Yang

Huaping Yuan

Yukun Li

Yongxin Ma

This application discloses a face image processing method performed by an electronic device. The method includes: acquiring a face image of a source face and a face template image of a template face; performing three-dimensional face modeling on the face image and the face template image to obtain a three-dimensional face image feature of the face image and a three-dimensional face template image feature of the face template image; fusing the three-dimensional face image feature and the three-dimensional face template image feature to obtain a three-dimensional fusion feature; performing face replacement feature extraction on the face image based on the face template image to obtain an initial face replacement feature; transforming the initial face replacement feature based on the three-dimensional fusion feature to obtain a target face replacement feature; and replacing the template face with the source face based on the target face replacement feature to obtain a target face image.

Face image processing method, face image processing model training method, apparatus, device, storage medium, and program product

This application provides a video picture decoding and encoding method and a video picture decoding and encoding apparatus. When it is determined that a merge or skip mode is used, if it is determined through decoding that a merge mode with motion vector difference (MMVD) indicator is true, a triangle prediction unit (PU) indicator may not be coded. The triangle PU indicator is coded when it is determined through decoding that the MMVD indicator is false. This reduces a quantity of used coding resources, and can reduce bit overheads of a bitstream.

Video picture decoding and encoding method and apparatus

An inter prediction method and apparatus, and a corresponding encoder and decoder are disclosed. The method includes: obtaining an index value of a length of a motion vector difference of the current picture block; determining target length information from a set of candidate length information based on the index value of the length; obtaining the motion vector difference of the current picture block based on the target length information; determining the motion vector target value of the current picture block based on the motion vector difference of the current picture block and the motion vector predictor of the current picture block; and obtaining a prediction block of the current picture block based on the motion vector target value of the current picture block.

Inter prediction method and apparatus, and corresponding encoder and decoder that reduce redundancy in video coding

An intra prediction method includes obtaining respective intra prediction modes or texture distributions of P reconstructed picture blocks in a surrounding region of a current block; obtaining, based on the respective intra prediction modes or texture distributions of the P reconstructed picture blocks, Q priori candidate intra prediction modes of the current block and Q probability values; obtaining, based on M probability values corresponding to M priori candidate intra prediction modes, M weighting factors corresponding to the M priori candidate intra prediction modes; separately performing intra prediction based on the M priori candidate intra prediction modes to obtain M predicted values; and obtaining a predicted value of the current block based on a weighted summation of the M predicted values and the corresponding M weighting factors.

Intra prediction method and apparatus

Techniques for data transmission involve obtaining respective data transmission characteristics of a set of to-be-processed data transmission jobs, the data transmission characteristics of each data transmission job indicating at least one of an expected transmission time and a data size of the data transmission job; determining corresponding weights of the set of data transmission jobs based on the data transmission characteristics of the set of data transmission jobs; and determining a transmission rate of each data transmission job based on the weights and a total transmission rate used for the set of data transmission. Accordingly, different transmission rates may be assigned to different data transmission jobs, thereby increasing a recovery point objective (RPO) completion rate before a failure occurs.

Method, electronic device and computer program product for data transmission

Embodiments of this application disclose a method for obtaining a motion vector, including: determining a reference block of a to-be-processed block, wherein the reference block and the to-be-processed block have a preset spatial correlation, the reference block is obtained based on a prediction block of the reference block determined by a refined initial motion vector, the refined initial motion vector is obtained based on an initial motion vector and one or more preset motion vector offsets, and the initial motion vector is obtained based on a predicted motion vector of the reference block; and using the initial motion vector as a predicted motion vector of the to-be-processed block.

Video coding method and apparatus

This application discloses an apparatus for constructing a merge candidate motion information list, including: one or more processors; a non-transitory memory storage comprising instructions which when executed by the one or more processors, cause the apparatus to obtain first motion information and add the first motion information to a first candidate motion information set, to obtain a second candidate motion information set; obtain second motion information based on an HMVP candidate motion information list; when the second motion information is different from all motion information in the second candidate motion information set, add the second motion information to the second candidate motion information set, to obtain a merge candidate motion information list, wherein a quantity of pieces of motion information in the merge candidate motion information set is equal to a preset threshold. Implementing this application reduces complexity in constructing the merge candidate motion information list, and improve coding efficiency.

Method for constructing merge candidate motion information list, apparatus, and codec

This application discloses a motion vector obtaining method and apparatus, a computer device, and a storage medium. In the method, an initial motion vector of a to-be-processed picture block is determined by using a location relationship between a reference block and the to-be-processed picture block. When the reference block and the to-be-processed picture block are located in a same coding tree block, a decoder uses an initial motion vector of the reference block as the initial motion vector of the to-be-processed picture block. When the reference block and the to-be-processed picture block are located in different coding tree blocks, the decoder uses a final motion vector of the reference block as the initial motion vector of the to-be-processed picture block.

Motion vector obtaining method and apparatus, computer device, and storage medium

A picture decoding method includes determining motion information of a to-be-decoded block; obtaining a first decoding prediction block of the to-be-decoded block based on the motion information; performing motion search with first precision in the prediction reference picture block to obtain at least two second decoding prediction blocks; performing downsampling on the first decoding prediction block and the at least two second decoding prediction blocks to obtain a first sampling pixel array and at least two second sampling pixel arrays, respectively; calculating a difference between the first sampling pixel array and each of the second sampling pixel arrays, and using, as a target prediction motion vector, a motion vector corresponding to a second sampling pixel array with a minimum difference; and obtaining a target decoding prediction block of the to-be-decoded block based on the target prediction motion vector, and decoding the to-be-decoded block based on the target decoding prediction block.

Picture encoding and decoding method and apparatus for video sequence

Methods and apparatuses for inter prediction are disclosed. The method comprises: constructing a merging candidate list of a current picture block; when a number of merging candidates in the merging candidate list is less than a maximum number of candidates minus N, adding at least one history-based motion vector predictor (HMVP) candidate to the merging candidate list to obtain a new merging candidate list, wherein N is a positive integer; obtaining motion information of the current picture block based on the new merging candidate list; and determining a predicted block of the current picture block based on the motion information of the current picture block.

Inter prediction method and apparatus

An inter prediction method includes obtaining predicted motion information of a current image block, where the predicted motion information is used to obtain one or more motion vectors of the current image block, and the motion vectors include a forward MV and a backward MV for a bidirectional inter prediction. The disclosed method further includes determining a motion vector difference for the current image block, and calculating the motion vectors based on the predicted motion information and the motion vector difference, where the motion vector difference is shared by the forward MV and the backward MV.

Bidirectional inter prediction method and terminal based on motion vector difference reduction

A loop filtering method and apparatus are provided. The method includes: obtaining a first pixel matrix, where a value of a pixel at a corresponding location in the first pixel matrix corresponds to a luminance value of a pixel at a corresponding location in a first picture block; obtaining a second pixel matrix, where a pixel at a corresponding location in the second pixel matrix corresponds to a quantization step value corresponding to the luminance value of the pixel at the corresponding location in the first picture block; performing filtering processing on an input pixel matrix by using a filtering network to obtain an output pixel matrix, where the filtering network is a neural network that has a filtering function and is obtained through training, the output pixel matrix includes a third pixel matrix. Thus, filtering effect can be improved for reconstructed pictures of various quality levels.

Loop filtering method and apparatus

A video encoder, a video decoder, and a corresponding method, where the method includes, when a plurality of preset conditions are satisfied, performing bi-directional optical flow (BDOF) processing on a current picture block to obtain a predicted sample value of the current picture block, where the plurality of preset conditions include at least a condition that a height (H) of the current picture block is greater than or equal to 8, a width (W) of the current picture block is greater than or equal to 8, and a product of W and H is greater than 128. Thus encoding/decoding complexity and prediction accuracy can be balanced to some extent.

Video encoder, video decoder, and corresponding method

A picture prediction method includes: determining whether a merge mode is used for a current picture block; when the merge mode is used for the current picture block, determining whether a regular merge mode is available; when the regular merge mode is unavailable, and a high-layer syntax element sps_triangle_enabled_flag corresponding to a triangle partition mode (TPM), indicates that the TPM is forbidden to be used, determining a combined intra and inter prediction (CIIP) mode as a target merge mode used for the current picture block and predicting the current picture block based on the target merge mode.

Picture prediction method and apparatus, and computer-readable storage medium

An integrated power distribution apparatus for a cooking robot, including: a bottom plate (); a motor fixing base () fixedly mounted on one side of a surface of the bottom plate, a power motor () fixedly mounted on one side of the motor fixing base, a control motor () fixedly mounted on a surface of the motor fixing base, two shaft couplers () respectively arranged on one sides of the power motor and the control motor, a fixed support () fixedly mounted on the surface of the bottom plate, two rotation output shafts () respectively arranged on a surface of the fixed support, four power output gears () sequentially arranged from left to right on one side of the rotation output shaft, a placement base () fixedly mounted on the surface of the bottom plate, and bearings () respectively arranged on two sides of an interior of the placement base.

Integrated power distribution apparatus for cooking robot

Growing community of inventors

Shenzhen, China

Xu Chen