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).

  • Implementation aspects in intra block copy in video coding
    Patent number: 11546581
    Abstract: A method of visual media processing includes determining, for a conversion between a current video block of visual media data and a bitstream representation of the current video block, a buffer that stores reference samples for prediction in an intra block copy mode; for a sample spatially located at location of the current video block relative to an upper-left position of a coding tree unit including the current video block and having a block vector, computing a corresponding reference in the buffer at a reference location, wherein the reference location is determined using the block vector and the location; and upon determining that the reference location lies outside the buffer, re-computing the reference location based at least in part on a location of the current video block relative to the coding tree unit including the current video block.
    Type: Grant
    Filed: July 23, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Context coding for matrix-based intra prediction
    Patent number: 11546633
    Abstract: Devices, systems and methods for digital video coding, which includes matrix-based intra prediction methods for video coding, are described. In a representative aspect, a method for video processing includes encoding a current video block of a video using a matrix intra prediction (MIP) mode in which a prediction block of the current video block is determined by performing, on previously coded samples of the video, a boundary downsampling operation, followed by a matrix vector multiplication operation, and selectively followed by an upsampling operation; and adding, to a coded representation of the current video block, a syntax element indicative of applicability of the MIP mode to the current video block using arithmetic coding in which a context for the syntax element is derived based on a rule.
    Type: Grant
    Filed: September 20, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu
  • Direction-based prediction for intra block copy in video coding
    Patent number: 11546599
    Abstract: A method of visual media processing includes determining, for a conversion between a current video block of visual media data and a bitstream representation of the current video block, a buffer that stores reference samples for prediction in an intra block copy mode; for a sample spatially located at location of the current video block relative to an upper-left position of a coding tree unit including the current video block and having a block vector, computing a corresponding reference in the buffer at a reference location, wherein the reference location is determined using the block vector and the location; and upon determining that the reference location lies outside the buffer, re-computing the reference location based at least in part on a location of the current video block relative to the coding tree unit including the current video block.
    Type: Grant
    Filed: June 29, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Utilization of non-sub block spatial-temporal motion vector prediction in inter mode
    Patent number: 11546601
    Abstract: A method of video processing includes determining, for a current block, at least one motion candidate list; and performing a conversion between the current block and a bitstream representation of the current block using the at least one motion candidate list, the at least one motion candidate list including at least one motion candidate derived from a set of neighboring blocks including one or more spatial and temporal neighboring blocks.
    Type: Grant
    Filed: March 19, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • Clipping operation in secondary transform based video processing
    Patent number: 11546636
    Abstract: A video processing method includes determining, for a conversion between a block of a video and a bitstream representation of the video, that an output value from an inverse secondary transform with a reduced dimension (e.g., an inverse low frequency non-separable transform) is constrained within a range of [min, max] inclusively. The inverse secondary transform is applicable to the block between a de-quantization step and an inverse primary transform. The reduced dimension is reduced from a dimension of the block, and min and max are integer values. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: August 19, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Sub-block based use of transform skip mode
    Patent number: 11546595
    Abstract: Devices, systems and methods for lossless coding for visual media coding are described. An exemplary method for video processing includes determining, at a sub-block level of a current video block comprising multiple sub-blocks, whether a coding mode is enabled for representing a corresponding sub-block in a bitstream representation, where, for a given sub-block with the coding mode enabled, the given sub-block is represented in the coded representation without applying a forward transform or the given sub-block is reconstructed from the coded representation without applying an inverse transform, and performing, based on the determining, a conversion between the current video block of a video and the bitstream representation of the video.
    Type: Grant
    Filed: November 18, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Na Zhang, Yue Wang
  • Syntax for subpicture signaling in a video bitstream
    Patent number: 11546593
    Abstract: An example method of video processing includes performing a conversion between a picture of a video that comprises one or more sub-pictures and a bitstream representation of the video. The bitstream representation conforms to a format rule that specifies that information about a sub-picture is included in the bitstream representation based on at least one of: (1) one or more corner positions of the sub-picture, or (2) a dimension of the sub-picture. The format rule further specifies that the information about the sub-picture is positioned after information about a coding tree block in the bitstream representation.
    Type: Grant
    Filed: April 1, 2022
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu
  • Parameter derivation for intra prediction
    Patent number: 11546616
    Abstract: A method for video processing is provided. The method includes determining, for a conversion between a current video block of a video that is a chroma block and a coded representation of the video, parameters of a cross-component linear model (CCLM) based on two or four chroma samples and/or corresponding luma samples; and performing the conversion based on the determining.
    Type: Grant
    Filed: January 29, 2021
    Date of Patent: January 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • CONTROLLING METHOD OF VEHICLE EXHAUST GAS RECIRCULATION, APPARATUS, AND ELECTRONIC DEVICE
    Publication number: 20220412293
    Abstract: A controlling method of vehicle exhaust gas recirculation, an apparatus and an electronic device are provided in vehicle field. Before the GPF/DPF starts to work, controlling the EGR to cool the temperature of the recycled gas at a lowest gas temperature required being entranced into the engine; and after the GPF/DPF starts to work, according to a gas temperature change and an intake flow change of an air intake of the EGR, adjusting an opening of a valve arranged in a vent of the EGR and a working power of a pump arranged in a liquid duct of the EGR, for making the EGR to cool the gas recycled by the EGR in a safe temperature range required by the engine. The controlling method is associated controlled with a cooling system of the EGR, for ensuring the recycled exhaust gas temperature and the EGR rate in a suitable range.
    Type: Application
    Filed: June 12, 2021
    Publication date: December 29, 2022
    Inventors: Xinglai Huang, Kai Zhang, Zhixin Zeng, Guanghua Zhong, Ning Zhang, Linggui Zhong
  • USING PICTURE LEVEL SLICE INDEX IN VIDEO CODING
    Publication number: 20220417562
    Abstract: A method includes performing a conversion between a video including at least one video picture and a bitstream of the video according to a rule, wherein the at least one video picture includes one or more slices and one or more subpictures, and wherein the rule specifies that an order of slice indices of the one or more slices in the at least one video picture is indicated responsive to a syntax element associated with the at least one picture indicative of whether a single slice is included per subpicture of the at least one video picture.
    Type: Application
    Filed: August 23, 2022
    Publication date: December 29, 2022
    Inventors: Ye-kui Wang, Li Zhang, Kai Zhang
  • MATRIX DERIVATION IN INTRA CODING MODE
    Publication number: 20220417503
    Abstract: Devices, systems and methods for digital video coding, which includes matrix-based intra prediction methods for video coding, are described. In a representative aspect, a method for video processing includes performing a conversion between a current video block of a video and a bitstream representation of the current video block according to a rule, where the rule specifies a relationship between samples of the current video block and matrices or offset values applied in a matrix weighted intra prediction (MIP) mode during the conversion, and where the MIP mode includes determining a prediction block of the current video block by performing, on previously coded samples of the video, a boundary downsampling operation, followed by a matrix vector multiplication operation, and selectively followed by an upsampling operation.
    Type: Application
    Filed: August 25, 2022
    Publication date: December 29, 2022
    Inventors: Zhipin Deng, Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu
  • SELECTION OF SECONDARY TRANSFORM MATRICES FOR VIDEO PROCESSING
    Publication number: 20220417529
    Abstract: A video processing method is provided to include performing a conversation between a current video block of a video and a coded representation of the video. The conversion comprises selecting, for the current video block of a video, a transform set or a transform matrix to be used in an application of a secondary transform tool to the current video block based on a characteristic of the current video block and applying the selected transform set or transform matrix to the current video block. Using the secondary transform tool, during encoding, a forward secondary transform is applied to an output of a forward primary transform applied to a residual of the current video block prior to quantization, or during decoding, an inverse secondary transform is applied to an output of dequantization of the current video block before applying an inverse primary transform.
    Type: Application
    Filed: August 25, 2021
    Publication date: December 29, 2022
    Inventors: Li ZHANG, Kai ZHANG, Hongbin LIU, Yue WANG
  • Slice and Tile Partitioning in Video Coding
    Publication number: 20220417565
    Abstract: A method includes performing a conversion between a video that includes at least a video tile and a bitstream of the video according to a rule. The rule specifies that a height of a slice in the video tile in units of coding tree units is derived based on a value of a first syntax element in the bitstream indicating a number of explicitly provided slice heights for slices in the video tile that includes the slice.
    Type: Application
    Filed: August 22, 2022
    Publication date: December 29, 2022
    Inventors: Kai Zhang, Li Zhang, Ye-kui Wang, Zhipin Deng, Kui Fan, Jizheng Xu, Hongbin Liu
  • Slice level signaling in video bitstreams that include subpictures
    Patent number: 11539950
    Abstract: An example method of video processing includes performing a conversion between a video comprising one or more pictures and a bitstream representation of the video. The bitstream representation is required to conform to a format rule that specifies that each picture is coded as one or more slices. The format rule prohibits samples in a picture from not being covered by any of the one or more slices.
    Type: Grant
    Filed: April 1, 2022
    Date of Patent: December 27, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu
  • Adaptive in-loop color-space transform for video coding
    Patent number: 11539981
    Abstract: A method of video processing is provided. The method includes determining, due to a dual tree partitioning structure being used for a conversion between a video unit and a coded representation of the video unit, that use of an adaptive color space transformation (ACT) tool is disabled for the video unit; and performing, based on the determining, the conversion by disabling the ACT tool for the video unit, wherein the use of the ACT tool comprises: converting, during encoding a representation of a visual signal from a first color domain to a second color domain, or converting during decoding, a representation of a visual signal from the second color domain to the first color domain.
    Type: Grant
    Filed: December 20, 2021
    Date of Patent: December 27, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Jizheng Xu, Kai Zhang, Hongbin Liu, Weijia Zhu, Yue Wang
  • Devices and methods for controlling smart lock
    Patent number: 11538298
    Abstract: The present disclosure discloses a method for controlling a smart lock. The method includes obtaining a control request for a smart lock, wherein the control request carries ciphertext information; decrypting the ciphertext information in response to the control request; and controlling the smart lock to perform a target operation based on a decrypted control request.
    Type: Grant
    Filed: November 12, 2021
    Date of Patent: December 27, 2022
    Assignee: YUNDING NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Tao Li, Binghui Peng, Qi Yi, Kai Zhang, Wenfeng Li
  • Determination of picture partition mode based on block size
    Patent number: 11539949
    Abstract: Methods, systems, and devices for coding or decoding video wherein the picture partition mode is based on block size are described. An example method for video processing includes using a dimension of a virtual pipeline data unit (VPDU) used for a conversion between a video comprising one or more video regions comprising one or more video blocks and a bitstream representation of the video to perform a determination of whether a ternary-tree (TT) or a binary tree (BT) partitioning of a video block of the one or more video blocks is enabled, and performing, based on the determination, the conversion, wherein the dimension is equal to VSize in luma samples, wherein dimensions of the video block are CtbSizeY in luma samples, wherein VSize=min(M, CtbSizeY), and wherein M is a positive integer.
    Type: Grant
    Filed: January 24, 2022
    Date of Patent: December 27, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Hongbin Liu
  • Position-based coefficients scaling
    Patent number: 11539970
    Abstract: A video processing method includes determining, according to a rule, whether to apply a scaling matrix based on whether a secondary transform matrix is applied to a portion of a video block of a video, wherein the scaling matrix is used to scale at least some coefficients of the video block, and wherein the secondary transform matrix is used to transform at least some residual coefficients of the portion of the video block during the conversion; and performing a conversion between the video block of the video and a bitstream representation of the video using the selected scaling matrix.
    Type: Grant
    Filed: February 18, 2022
    Date of Patent: December 27, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Sample padding for cross-component adaptive loop filtering
    Patent number: 11539946
    Abstract: A method for video processing is described. The method includes determining, for a conversion between a video unit of a video and a bitstream representation of the video, whether to enable a mirrored padding process for padding an unavailable luma sample during an application of a loop filtering tool to the video unit; and performing the conversion based on the determining.
    Type: Grant
    Filed: June 10, 2022
    Date of Patent: December 27, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Yang Wang, Li Zhang, Hongbin Liu, Kai Zhang, Zhipin Deng, Yue Wang
  • COMPOSITE COATING FOR ELIMINATING POLLUTION BY HEAVY METAL CHROMIUM AND VOCS FROM SOURCE AND PREPARATION METHOD
    Publication number: 20220403525
    Abstract: Disclosed is a composite coating for eliminating pollution by chromium and VOCs from a source, the coating comprising a conversion film layer and a coating surface layer. The conversion film layer is made of a surface pretreatment liquid, and the surface pretreatment liquid comprises the following components: an organic compound A having an aromatic ring and at least two phenolic hydroxyl groups in the molecule thereof, or a hydrate thereof; an ionic compound B containing zirconium and/or titanium and fluorine; a mixed solution C containing manganese fluoride; and an inorganic salt D containing potassium ions or sodium ions. The coating surface layer is an FEVE-type fluorocarbon powder coating layer. Also disclosed is a preparation method for the described composite coating.
    Type: Application
    Filed: February 24, 2020
    Publication date: December 22, 2022
    Applicant: GUANGDONG PROVINCIAL ACADEMY OF BUILDING RESEARCH GROUP CO., LTD
    Inventors: Kai ZHANG, Shichao YANG, Yang MA