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).

  • Patent number: 12007243
    Abstract: A traffic lane line fitting method includes: obtaining map information for a current position of a vehicle, the map information comprising a number of traffic lanes, a road width and line point information of traffic lane lines on both sides of the vehicle; determining, from among the traffic lane lines on both sides of the vehicle, a traffic lane line on one side, consistent with the direction indicated by at least one of the following, to be a traffic lane line offset reference used for traffic lane line fitting; offsetting and generating a plurality of traffic lane lines of the vehicle on the basis of the traffic lane line offset reference; performing curve fitting on a set of line points on the generated plurality of traffic lane lines so as to obtain a corresponding traffic lane line equation.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: June 11, 2024
    Assignee: GREAT WALL MOTOR COMPANY LIMITED
    Inventors: Longbao Zhen, Jianyong Ge, Rutao Han, Long Li, Wei Li, Jian Gao, Kai Zhang, Lin He, Lu Zhang
  • Patent number: 12010321
    Abstract: Disclosed and systems, methods and devices for video processing. An exemplary method for video processing includes: determining for a current video block, an indication which indicates that an affine merge with motion vector difference (MMVD) mode is applied to the current video block; performing a conversion between the current video block and a bitstream representation of a current video block based on the indication, the indication being activated based on the usage of at least one merge list for the current video block.
    Type: Grant
    Filed: July 12, 2021
    Date of Patent: June 11, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Patent number: 12010317
    Abstract: A method of video processing includes performing a conversion between a video including a video region and a bitstream of the video according to a rule. The rule specifies a relationship between enablement of a palette mode and a coding type of the video region. The video region may represent a coding block of the video.
    Type: Grant
    Filed: October 10, 2022
    Date of Patent: June 11, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang
  • Patent number: 12010346
    Abstract: Several techniques for video encoding and video decoding are described. One example method includes performing a conversion between a block of a video and a bitstream of the video according to a rule. The rule specifies that whether a syntax flag indicating whether transform skip residual coding is enabled at a video unit level is present in the bitstream is based on values of a first syntax element indicating usage of sign data hiding in the video unit and a second syntax element indicating usage of dependent quantization in the video unit.
    Type: Grant
    Filed: October 19, 2022
    Date of Patent: June 11, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Ye-Kui Wang, Li Zhang, Kai Zhang, Zhipin Deng
  • Patent number: 12010333
    Abstract: A method for visual media processing, including performing a conversion between a current chroma video block of visual media data and a bitstream representation of the current chroma video block. During the conversion, a chroma residual of the current chroma video block is scaled based on a scaling coefficient. The scaling coefficient is derived at least based on luma samples located in predefined positions.
    Type: Grant
    Filed: December 19, 2022
    Date of Patent: June 11, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Hongbin Liu, Jizheng Xu
  • Patent number: 12010295
    Abstract: Methods, apparatus, systems for video processing, including video encoding or video decoding are described. One example method includes performing a conversion between a video including a video picture that includes a video slice and a bitstream of the video. The bitstream conforms to a format rule specifying that a slice type of the video slice determines a manner by which certain information from a picture header for the video picture is inherited by a slice header of the video slice.
    Type: Grant
    Filed: August 11, 2022
    Date of Patent: June 11, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Ye-kui Wang, Kui Fan
  • Publication number: 20240187576
    Abstract: Embodiments of the present disclosure provide a method for video processing. The method comprises: determining, during a conversion between a current chroma block of a video and a bitstream of the video, a set of target modes of cross component intra prediction (CCIP) for the current chroma block based on reconstructed samples or predicted samples of neighboring samples of the current chroma block; and performing the conversion based on the set of target modes. Compared with the conventional solution, the proposed method can advantageously improve coding efficiency.
    Type: Application
    Filed: February 9, 2024
    Publication date: June 6, 2024
    Inventors: Yang WANG, Kai ZHANG, Li ZHANG
  • Publication number: 20240185775
    Abstract: A method for controlling dynamic change of a screen refresh rate and an electronic device are provided. In a scenario of dynamic change of the refresh rate, a refresh rate switching instruction may be sent immediately through an added refresh rate setting interface (displaySetFps) within a current ith frame period before a current Vsync periodicity ends. After receiving the refresh rate switching instruction, a DDIC drives a display screen to switch a screen refresh rate, and then the DDIC returns a new TE signal. After receiving the new TE signal, SurfaceFlinger starts a new Vsync periodicity corresponding to a switched screen refresh rate. In an embodiment of this application, a switching speed at which the screen refresh rate is switched may be increased by adding a new path. For example, it may be ensured that each switching of the screen refresh rate is completed within one frame.
    Type: Application
    Filed: December 22, 2022
    Publication date: June 6, 2024
    Inventors: Kai ZHANG, Jian ZHOU, Shijin LI, Lifeng CAI
  • Publication number: 20240187636
    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 block of a video and a bitstream of the video, a list of motion candidates for motion information for the target block; determining a reordering scheme based at least in part on coding information, the reordering scheme indicating whether and/or how at least one motion candidate in the list of motion candidates is to be reordered; generating a target list of motion candidates from the list of motion candidates according to the reordering scheme; and deriving the motion information for the target block from the target list of motion candidates. Compared with the conventional solution, the proposed method can advantageously improve the coding effectiveness and coding efficiency.
    Type: Application
    Filed: April 8, 2022
    Publication date: June 6, 2024
    Applicants: Beijing Bytedance Network Technology Co., Ltd., Bytedance Inc.
    Inventors: Na ZHANG, Kai ZHANG, Li ZHANG, Hongbin LIU, Zhipin DENG, Yang WANG
  • Publication number: 20240187639
    Abstract: A method of video processing is provided to include maintaining one or more tables, wherein each table includes one or more motion candidates and each motion candidate is associated with corresponding motion information; performing a conversion between a current block and a bitstream representation of a video including the current block by using motion information in a table; and updating, after performing of the conversion, one or more tables based on M sets of additional motion information associated with the current block, M being an integer.
    Type: Application
    Filed: December 5, 2023
    Publication date: June 6, 2024
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Publication number: 20240187569
    Abstract: Embodiments of the present disclosure provide a method for video processing. The method comprises: determining, during a conversion between a current chroma block of a video and a bitstream of the video, a set of candidate intra prediction modes (IPMs) for the current chroma block based on a decoder-side derivation of intra prediction mode (DDIPM); constructing an IPM candidate list for the current chroma block based on the set of candidate IPMs; and performing the conversion based on the IPM candidate list. Thereby, the proposed method can advantageously improve coding efficiency and reduce the coding bits while maintaining the coding quality.
    Type: Application
    Filed: February 9, 2024
    Publication date: June 6, 2024
    Inventors: Yang Wang, Kai Zhang, Li Zhang
  • Publication number: 20240187633
    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 unit in a target picture of a video and a bitstream of the video, second coding data of the target video unit based on first coding data of the target video unit and at least one refinement process, the at least one refinement process being applied based on a predefined criterion; and performing the conversion based on the second coding data. Compared with the conventional solution, the proposed method can advantageously improve the coding performance and efficiency.
    Type: Application
    Filed: April 21, 2022
    Publication date: June 6, 2024
    Inventors: Zhipin DENG, Li ZHANG, Kai ZHANG, Na ZHANG
  • Publication number: 20240187575
    Abstract: A method for video processing is proposed. The method comprises: deriving, during a conversion between a target unit of a video and a bitstream of the target unit, an intra prediction mode (IPM) of the target unit for at least one chroma component (2610), the target unit being applied with a target coding tool; obtaining a prediction of the target unit for the at least one chroma component using the IPM (2620); and performing the conversion based on the prediction of the target unit for the at least one chroma component (2630).
    Type: Application
    Filed: February 9, 2024
    Publication date: June 6, 2024
    Inventors: Yang WANG, Kai ZHANG, Li ZHANG
  • Publication number: 20240187580
    Abstract: A mechanism for processing video data is disclosed. The mechanism determines to apply a bilateral filter and a cross component sample adaptive offset (CCSAO) filter to samples in a current block of a current picture. The bilateral filter includes filter weights that vary based on a distance between surrounding samples and a central sample and differences in intensities of the surrounding samples and the central sample. A conversion is performed between a visual media data and a bitstream based on the bilateral filter and the CCSAO filter.
    Type: Application
    Filed: December 29, 2023
    Publication date: June 6, 2024
    Inventors: Wenbin Yin, Kai Zhang, Li Zhang
  • Publication number: 20240187567
    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 block of a video and a bitstream, reference samples of a sub-template of the current block based on a first set of reference samples of the sub-template in a first reference list and a second set of reference samples of the sub-template in a second reference list; and determining a target motion candidate list based on the reference samples of the sub-template. Compared with the conventional solution, the proposed method can advantageously improve the coding efficiency.
    Type: Application
    Filed: April 9, 2022
    Publication date: June 6, 2024
    Inventors: Na ZHANG, Kai ZHANG, Li ZHANG, Hongbin LIU, Zhipin DENG, Yang WANG
  • Publication number: 20240185794
    Abstract: A pixel circuit and a driving method thereof, a display substrate, and a display device are provided. In the pixel circuit, a data writing circuit is configured to control a connection between a data line and a second terminal of a driving circuit under control of a first scanning signal provided by a first scanning line; a reset circuit is configured to control a connection between a reset voltage line and the second terminal of the driving circuit under control of a third scanning signal provided by a third scanning line; or the reset circuit is coupled to the third scanning line, the reset voltage line and a first terminal of the driving circuit, and is configured to control a connection between the reset voltage line and the first terminal of the driving circuit under control of the third scanning signal.
    Type: Application
    Filed: July 13, 2022
    Publication date: June 6, 2024
    Applicants: CHENGDU BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Gang WANG, Kai ZHANG, Xinyu WEI, Xingrui CAI, Qiang FU
  • Patent number: 12003711
    Abstract: In an exemplary aspect, a method for visual media processing includes identifying a boundary at a vertical edge and/or a horizontal edge of two video blocks; calculating a boundary strength of a filter based on at least one of the two video blocks crossing a vertical edge or a horizontal edge is coded using a combined intra-inter prediction (CIIP) mode; deciding whether to turn on or off the filter; selecting a strength of the filter in case the filter is turned on; and performing, based on the selecting, a deblocking filter (DB) process to the video blocks.
    Type: Grant
    Filed: November 10, 2021
    Date of Patent: June 4, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Weijia Zhu, Kai Zhang, Hongbin Liu, Jizheng Xu
  • Patent number: 12003698
    Abstract: Devices, systems and methods for digital video coding, which include sub-block based inter prediction methods, are described. An exemplary method for video processing includes determining, for a conversion between a current block of video and a bitstream representation of the video, a maximum number of candidates in a sub-block based merge candidate list and/or whether to add sub-block based temporal motion vector prediction (SbTMVP) candidates to the sub-block based merge candidate list based on whether temporal motion vector prediction (TMVP) is enabled for use during the conversion or whether a current picture referencing (CPR) coding mode is used for the conversion, and performing, based on the determining, the conversion.
    Type: Grant
    Filed: May 17, 2021
    Date of Patent: June 4, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Patent number: 12003714
    Abstract: A method of video processing is described. The method includes determining, for subblocks of a current video block of a video, subblock boundaries to which a deblocking filter is to be applied according to a rule; and performing a conversion between the video and a coded representation of the video using the deblocking filter, wherein the rule specifies that a deblocking filter length is determined without checking a relationship between i) a sum of a position of a subblock of the current video block and a predefined value and ii) a width or a height of the current video block.
    Type: Grant
    Filed: August 8, 2022
    Date of Patent: June 4, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Hongbin Liu
  • Patent number: 12003712
    Abstract: A method of video processing includes determining, for a conversion between a picture of a video that includes one or more blocks and a bitstream representation of the video, whether a virtual boundary is enabled for a block within the picture for a filtering process based on a rule related to a relationship between a bottom boundary of the block and the picture. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: December 10, 2021
    Date of Patent: June 4, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang