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).

  • Publication number: 20240259559
    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 template matching (TM) merge candidates for the target block in a TM merge mode; reordering a TM merge candidate in the list of TM merge candidates based on a determination whether a first condition is satisfied to perform TM refinement for the TM merge candidate and a second condition is satisfied to perform decoder-side motion vector refinement (DMVR) or multi-pass DMVR for the TM merge candidate; and performing the conversion based on the reordered TM merge candidate. Compared with the conventional solution, the proposed method can advantageously improve the coding effectiveness and coding efficiency.
    Type: Application
    Filed: April 15, 2024
    Publication date: August 1, 2024
    Inventors: Na ZHANG, Kai ZHANG, Li ZHANG, Yang WANG
  • Publication number: 20240259591
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, during a conversion between a target video block of a video and a bitstream of the video, bilateral matching to refine uni-directional motion information for the target video block, 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: August 1, 2024
    Inventors: Zhipin DENG, Li ZHANG, Kai ZHANG, Na ZHANG
  • Publication number: 20240259552
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, during a conversion between a target video block of a video and a bitstream of the video, a multi-hypothesis prediction process for the target video block based on a plurality of motion candidates from a non-regular merge list; and performing the conversion based on a result of the multi-hypothesis prediction process. Compared with the conventional solution, the proposed method can advantageously improve the coding efficiency and performance.
    Type: Application
    Filed: May 17, 2022
    Publication date: August 1, 2024
    Inventors: Zhipin DENG, Li ZHANG, Kai ZHANG, Na ZHANG
  • Publication number: 20240257732
    Abstract: A pixel driving circuit includes a driving circuit, a first reset circuit, and a second reset circuit. The driving circuit is coupled to a first node and a second node, and is configured to output a driving current according to a voltage difference between the first node and the second node. The first reset circuit is coupled to the first node, a first initial signal terminal and a first reset signal terminal, and is configured to transmit a signal of the first initial signal terminal to the first node in response to a signal of the first reset signal terminal. The second reset circuit is coupled to the second node and a first power terminal, and is configured to transmit a signal of the first power supply terminal to the second node in response to a control signal.
    Type: Application
    Filed: July 30, 2021
    Publication date: August 1, 2024
    Inventors: Huaping SUN, Kai ZHANG, Erlong SONG, Qiang FU, Xingrui CAI
  • Publication number: 20240259555
    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, whether a block vector (BV) candidate of the target video block is valid; in accordance with a determination that the BV candidate is valid, adding the BV candidate in an intra block copy (IBC) candidate list; and performing the conversion based on the IBC candidate list.
    Type: Application
    Filed: March 29, 2024
    Publication date: August 1, 2024
    Inventors: Na ZHANG, Kai ZHANG, Li ZHANG, Jizheng XU
  • Publication number: 20240259558
    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 block of a video and a bitstream of the video, a list of regular merge candidates for the target block in a regular merge mode; reordering the list of regular merge candidates based on a determination whether a condition is satisfied to perform decoder-side motion vector refinement (DMVR) or multi-pass DMVR process for a regular merge candidate in the list of regular merge candidates; and performing the conversion based on the reordered list of regular merge candidates. Compared with the conventional solution, the proposed method can advantageously improve the coding effectiveness and coding efficiency.
    Type: Application
    Filed: April 15, 2024
    Publication date: August 1, 2024
    Inventors: Na ZHANG, Kai ZHANG, Li ZHANG, Yang WANG
  • Publication number: 20240259608
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing comprises: reordering, during a conversion between a current video block of a video and a bitstream of the video, a plurality of candidate signs of a motion vector difference (MVD) for a motion candidate of the current video block; and performing the conversion based on the reordered plurality of candidate signs. Compared with the conventional solution, the proposed method can advantageously improve coding efficiency and coding quality.
    Type: Application
    Filed: April 11, 2024
    Publication date: August 1, 2024
    Inventors: Mehdi SALEHIFAR, Yuwen HE, Kai ZHANG, Na ZHANG, Li ZHANG
  • Publication number: 20240259560
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: processing, during a conversion between a picture of a video and a bitstream of the video, a first video block in the picture based on a combination of decoder-side intra prediction mode derivation (DIMD) and intra prediction with subpartitions (ISP), the DIMD being used for deriving at least one intra prediction mode (IPM); and performing the conversion based on the first video block. Compared with the conventional solution, the proposed method can advantageously improve the coding effectiveness and coding efficiency.
    Type: Application
    Filed: May 19, 2022
    Publication date: August 1, 2024
    Inventors: Yang WANG, Li ZHANG, Kai ZHANG
  • Publication number: 20240259598
    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 video unit of a video and a bitstream of the target block, information related to a combined inter-intra prediction (CIIP) enhancement mode, the video unit being applied with the CIIP enhancement mode; and performing the conversion based on the information related to the CIIP enhancement mode.
    Type: Application
    Filed: March 29, 2024
    Publication date: August 1, 2024
    Inventors: Zhipin DENG, Kai Zhang, Li Zhang
  • Publication number: 20240257733
    Abstract: A pixel driving circuit includes: a driving transistor, a data write circuit, a threshold compensation circuit, a first capacitor, and a second capacitor. A gate of the driving transistor is coupled to a first node, a first electrode is coupled to a second node, and a second electrode is coupled to a third node. The data write circuit is configured to transmit a signal of a data signal terminal to the second node in response to a signal of a first gate driving signal terminal. The threshold compensation circuit is configured to communicate the first node with the third node in response to a signal of a second gate driving signal terminal. The first capacitor is coupled between the first node and the first gate driving signal terminal. The second capacitor is coupled between the first node and the second gate driving signal terminal.
    Type: Application
    Filed: July 30, 2021
    Publication date: August 1, 2024
    Inventors: Yao HUANG, Benlian WANG, Ming HU, Lang LIU, Kai ZHANG, Weiyun HUANG
  • Publication number: 20240259586
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: deriving, during a conversion between a target block of a video and a bitstream of the target block, a motion vector predictor for the target block from a parameter table that stores a set of affine parameters from at least one previously coded block, the target block being a non-affine coded block; and performing the conversion based on the motion vector predictor.
    Type: Application
    Filed: March 28, 2024
    Publication date: August 1, 2024
    Inventors: Kai ZHANG, Li ZHANG, Zhipin DENG
  • Publication number: 20240259588
    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, at least one group of motion vector predictions (MVP) candidates of the target video block; determining an MVP candidate list by sorting the at least one group of MVP candidates based on respective template matching costs of MVP candidates in the at least one group; and performing the conversion based on the MVP candidate list. In this way, a proper MVP candidate list can be determined, and thus the coding effectiveness and coding efficiency can be improved.
    Type: Application
    Filed: April 11, 2024
    Publication date: August 1, 2024
    Inventors: Lei Zhao, Kai Zhang, Li Zhang
  • Patent number: 12052428
    Abstract: Techniques are described for using an inter-intra-prediction block. A video coder may generate a first prediction block according to an intra-prediction mode and generate a second prediction block according to an inter-prediction mode. The video coder may weighted combine, such as based on the intra-prediction mode, the two prediction blocks to generate an inter-intra-prediction block (e.g., final prediction block). In some examples, an inter-intra candidate is identified in a list of candidate motion vector predictors, and an inter-intra-prediction block is used based on identification of the inter-intra candidate in the list of candidate motion vector predictors.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: July 30, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Kai Zhang, Jianle Chen, Li Zhang, Xiang Li, Marta Karczewicz
  • Patent number: 12052420
    Abstract: A method of video processing includes performing a prediction for a current video block or for a subblock split from the current video block; generating residual samples corresponding to the current video block or the subblock; obtaining quantized residual samples; and coding the quantized residual samples to perform a conversion on the current video block, a first one-dimensional (1-d) transform being applied to the residual samples before residual samples are quantized and/or a second 1-d transform being applied to the quantized residual samples.
    Type: Grant
    Filed: October 25, 2021
    Date of Patent: July 30, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Hongbin Liu, Jizheng Xu, Li Zhang, Kai Zhang, Yue Wang
  • Publication number: 20240251075
    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 set of motion vector prediction (MVP) candidates of the target video block based on decoded information of the target video block; sorting the set of MVP candidates based on respective template matching costs of the set of MVP candidates; and performing the conversion based on the sorting.
    Type: Application
    Filed: April 5, 2024
    Publication date: July 25, 2024
    Inventors: Lei ZHAO, Kai ZHANG, Li ZHANG
  • Publication number: 20240251108
    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 granularity of selection of a machine learning model for processing a video and a second granularity of applying the machine learning model; and performing, based on the first and second granularities, 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 25, 2024
    Inventors: Yue LI, Kai Zhang, Li Zhang
  • Publication number: 20240249441
    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 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, wherein at least one reference frame comprising the one or multiple reference PC samples and a current frame comprising the current PC sample are in a GOF; and performing the conversion based on the one or multiple reference PC samples.
    Type: Application
    Filed: April 4, 2024
    Publication date: July 25, 2024
    Inventors: Yingzhan XU, Kai Zhang, Li Zhang
  • Publication number: 20240249680
    Abstract: Provided are a pixel circuit, a driving method and a display apparatus, including: a light emitting device; a driving transistor, configured to produce a current for driving the light emitting device to emit light according to a data voltage; a voltage control circuit, coupled to the driving transistor, wherein the voltage control circuit is configured to reset the driving transistor (MO) and input the data voltage in response to a loaded signal; and a light emitting control circuit, coupled to the driving transistor and the light emitting device, wherein the light emitting control circuit is configured to provide the current produced by the driving transistor to the light emitting device; wherein a frequency of resetting the driving transistor is not less than a frequency of inputting the data voltage.
    Type: Application
    Filed: January 29, 2022
    Publication date: July 25, 2024
    Inventors: Yi ZHANG, Ming HU, Huijuan YANG, Tingliang LIU, Kai ZHANG, Haijun QIU, Youngyik KO, Tinghua SHANG, Biao LIU
  • Patent number: 12047558
    Abstract: A method of video processing includes performing a conversion between a video unit of a video and a coded representation of the video using at least a video picture. Only one of a sub-picture coding mode or a resolution-changing coding mode is enabled for the video unit. The sub-picture coding mode is a mode in which the video picture is divided into multiple sub-pictures, and the resolution-changing coding mode is a mode in which a resolution of the video picture is adjusted during the conversion.
    Type: Grant
    Filed: February 4, 2022
    Date of Patent: July 23, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu
  • Patent number: 12047585
    Abstract: A method of decoding video data, including receiving a first block of video data encoded using an inter-prediction mode associating a first intra-prediction mode with the first block of video data, wherein the first intra-prediction mode is associated with a second block of video data, and determining a second intra-prediction mode for a neighbor block of video data based at least in part on the first intra-prediction mode.
    Type: Grant
    Filed: August 31, 2022
    Date of Patent: July 23, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Kai Zhang, Jianle Chen, Xiang Li, Marta Karczewicz