Patents by Inventor Kai Zhang

Kai Zhang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Nonlinear adaptive loop filtering in video processing
    Patent number: 12047610
    Abstract: A method of processing video data includes determining that a non-linear adaptive loop filtering operation is applied for a current video region of a video; deriving a first filtering index for the current video region and deriving a first filtering parameter based on the first filtering index; deriving a first clipping parameter from a clipping parameter set based on the first filtering index; performing a clipping operation that is part of the non-linear adaptive loop filtering operation based on the first clipping parameter, where the first clipping parameter is used to clip differences between reference sample values of a current sample value of the current video region and the current sample value before applying the first filtering parameter; and performing a conversion between the current video region and a bitstream of the video based on the non-linear adaptive loop filtering operation.
    Type: Grant
    Filed: December 6, 2022
    Date of Patent: July 23, 2024
    Assignees: Beijing Bytedance Network Technology Co., Ltd., Bytedance Inc.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • METHOD, APPARATUS AND MEDIUM FOR POINT CLOUD CODING
    Publication number: 20240242393
    Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: determining, during a conversion between a current point cloud (PC) sample of a point cloud sequence and a bitstream of the point cloud sequence, one or multiple reference PC samples for the current PC sample; and performing the conversion based on the one or multiple reference PC samples.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Yingzhan XU, Kai Zhang, Li Zhang
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244201
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: determining, during a conversion between a current video block of a video and a bitstream of the video, a first filter shape from a plurality of filter shapes; determining, based on the first filter shape, a first filter for coding a first sample of the current video block, a value of a clip parameter of the first filter being dependent on the first filter shape; and performing the conversion based on the first filter. Compared with the conventional solution, the proposed method can advantageously improve the performance of the filtering tool.
    Type: Application
    Filed: March 28, 2024
    Publication date: July 18, 2024
    Inventors: Wenbin YIN, Kai Zhang, Li Zhang
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244200
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: determining, from a plurality of filter shapes during a conversion between a current video block of a video and a bitstream of the video, a first filter shape for coding a first sample of the current video block; and performing the conversion based on the first filter shape. Compared with the conventional solution, the proposed method can advantageously improve the performance of the filtering tool.
    Type: Application
    Filed: March 28, 2024
    Publication date: July 18, 2024
    Inventors: Wenbin YIN, Kai ZHANG, Li ZHANG
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244239
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a target video block of a video and a bitstream of the video, a target coding tool for the target video block by using a machine learning model; and performing the conversion by using the target coding tool. By taking the machine learning model into consideration in selecting the coding tool, a more proper coding tool can be selected. In this way, the coding performance can be enhanced.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Junru LI, Yue LI, Kai ZHANG, Li ZHANG
  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244272
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining a first machine learning (ML) model for processing a video, wherein the first ML model is trained based on one or more second ML models; and performing, according to the first ML model, a conversion between a current video block of the video and a bitstream of the video.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Yue LI, Kai ZHANG, Li ZHANG
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244187
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a target video block of a video and a bitstream of the video, a reference template for the target video block without involving an interpolation process; and performing the conversion based on the reference template. Compared with the conventional solution, the proposed method can advantageously improve the template matching based video coding and thus improve the coding effectiveness and coding efficiency.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Lei ZHAO, Kai ZHANG, Li ZHANG
  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244195
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a target block of a video and a bitstream of the target block, a linear model (LM) mode and an intra prediction mode (IPM); combining a set of predicted signals for at least one chroma component using the LM mode and the IPM; and performing the conversion based on the combined set of predicted signals.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Yang WANG, Kai Zhang, Li Zhang
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244204
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, during a conversion between a target video block of a video and a bitstream of the video, prediction information of a target subblock in the target video block based on types of predicted samples in the target subblock, the target video block being coded by a geometric partitioning tool; and performing the conversion based on the prediction information of the target subblock.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Zhipin DENG, Kai ZHANG, Li ZHANG
  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244222
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: constructing, during a conversion between a target video block of a video and a bitstream of the video, at least one template in the target video block based on at least one neighbor sample of the target video block that satisfies a predetermined criterion; applying template matching to refine motion information for the target video block based on the at least one determined template, to obtain refined motion information; and performing the conversion based on the refined motion information. Compared with the conventional solution, the proposed method can advantageously improve the coding efficiency and performance.
    Type: Application
    Filed: May 17, 2022
    Publication date: July 18, 2024
    Inventors: Zhipin DENG, Li ZHANG, Kai ZHANG, Na ZHANG
  • METHOD, APPARATUS, AND MEDIUM FOR POINT CLOUD CODING
    Publication number: 20240244249
    Abstract: Embodiments of the present disclosure provide a method for point cloud coding. The method comprises: obtaining, during a conversion between a current frame of a point cloud sequence and a bit-stream of the point cloud sequence, motion information of the current frame; determining a binarized representation of the motion information, the binarized representation at least reflecting an absolute value of the motion information; and performing the conversion based on the binarized representation of the motion information. Compared with the conventional solution, the proposed method can advantageously improve the accuracy of motion information coding and coding quality.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Wenyi WANG, Kai ZHANG, Li ZHANG
  • METHOD, DEVICE, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244269
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: filtering, according to a machine learning model during a conversion between a current video block of a video and a bitstream of the video, the current video block based on first information associated with one or multiple previously coded frames of the video; and performing the conversion based on the filtered current video block.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Yue LI, Kai ZHANG, Li ZHANG
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244226
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a target video block of a video and a bitstream of the video, a distortion metric for the target video block based at least in part on at least one distortion of: a set of filtered distortions of the target video block according to a set of machine learning models, or a second distortion of the target video block determined without using the set of machine learning models; determining, based on the distortion metric, information regarding using the set of machine learning models in a rate-distortion optimization (RDO) process on the target video block; and performing the conversion based on the information. In this way, the RDO process can be improved, and thus the coding performance can be enhanced.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Junru LI, Yue Li, Kai Zhang, Li Zhang
  • METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    Publication number: 20240244223
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a current video block of a video and a bitstream of the video, a motion candidate for the current video block based on merge mode with motion vector differences (MMVD) with an initial set of search points, a first direction of a first search point in the initial set of search points being non-vertical and non-horizontal; and performing the conversion based on the motion candidate. Compared with the conventional solution, the proposed method can advantageously improve coding efficiency and coding quality.
    Type: Application
    Filed: March 29, 2024
    Publication date: July 18, 2024
    Inventors: Mehdi Salehifar, Yuwen He, Kai Zhang, Na Zhang, Li Zhang
  • Intra-Prediction on Non-dyadic Blocks
    Publication number: 20240244191
    Abstract: A mechanism for processing video data implemented by a video coding apparatus is disclosed. The mechanism determines to apply template-based intra mode derivation (TIMD) to a block based on whether the block is dyadic or non-dyadic, where TMID is associated with intra prediction. A conversion between a visual media data and a bitstream is performed by applying intra prediction to the block based on TIMD.
    Type: Application
    Filed: February 8, 2024
    Publication date: July 18, 2024
    Inventors: Kai Zhang, Li Zhang, Zhipin Deng, Na Zhang, Yang Wang
  • History-based motion vector prediction with default parameters
    Patent number: 12041268
    Abstract: Video coding and decoding techniques, including history-based motion vector prediction with default parameters, are described. One example video processing method includes resetting for a conversion between a video unit of a video and a bitstream of the video, a history-based motion vector prediction (HMVP) table of size N by adding K HMVP motion candidates to the HMVP table, where the K HMVP motion candidates have default values, where N and K are positive integers, and where K?N; and performing the conversion between the video unit and the bitstream using the HMVP table resulting from the resetting.
    Type: Grant
    Filed: November 30, 2021
    Date of Patent: July 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Multi-iteration motion vector refinement
    Patent number: 12041267
    Abstract: A method for video processing includes: refining motion information of a video block by using a multi-step refinement processing, multiple refined motion vectors (MVs) of the video block being derived iteratively in respective steps of the multi-step refinement processing, and performing a video processing on the video block based on the multiple refined MVs of the video block.
    Type: Grant
    Filed: November 18, 2022
    Date of Patent: July 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • Coding of pictures containing slices and tiles
    Patent number: 12041237
    Abstract: Techniques for video processing, including video coding, video decoding and video transcoding are described. One example method includes performing a conversion between a video picture that includes one or more tiles and one or more rectangular slices and a bitstream of the video according to a rule. The rule specifies that, for iteratively determining information about the one or more rectangular slices, a variable indicating a tile index is updated only for slices having indices that are smaller than a value equal to a number of slices in the video picture minus 1.
    Type: Grant
    Filed: August 19, 2022
    Date of Patent: July 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Ye-kui Wang, Zhipin Deng, Kui Fan, Jizheng Xu, Hongbin Liu
  • Restrictions of usage of tools according to reference picture types
    Patent number: 12041225
    Abstract: A video processing method includes determining, for a conversion between a current video block of a video including multiple video blocks and a coded representation of the video, and from types of reference pictures used for the conversion, applicability of a coding tool to the current video block and performing the conversion based on the determining. The method may be performed by a video decoder or a video encoder or a video transcoder.
    Type: Grant
    Filed: February 21, 2023
    Date of Patent: July 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Na Zhang, Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • PIXEL CIRCUIT, DRIVING METHOD THEREOF, DISPLAY SUBSTRATE AND DISPLAY DEVICE
    Publication number: 20240233601
    Abstract: In the pixel circuit, the data writing-in circuit is configured to control to connect the data line and the second terminal of the driving circuit under the control of a first scanning signal provided by the first scanning line; the compensation control circuit is configured to control to connect the first terminal of the driving circuit and the connection node under the control of a second scanning signal provided by the second scanning line; the first control circuit is configured to control to connect the control terminal of the driving circuit and the connection node under the control of the first scanning signal.
    Type: Application
    Filed: July 13, 2022
    Publication date: July 11, 2024
    Applicants: CHENGDU BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Gang WANG, Kai ZHANG, Xinyu WEI, Qiang FU, Xingrui CAI