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).

  • MOTION VECTOR DIFFERENCE FOR BLOCK WITH GEOMETRIC PARTITION
    Publication number: 20220337867
    Abstract: Motion vector difference for block with geometric partition is described. One example method of video processing includes determining, for a conversion between a current video block of a video and a bitstream of the current video, that the current video block is coded with a geometric partitioning mode; deriving at least one refined motion vector (MV) for the current video block by adding at least one motion vector difference (MVD) of multiple MVDs signaled or derived for the current video block to a MV derived from a merge candidate associated with the current video block; and performing the conversion based on the refined MV.
    Type: Application
    Filed: June 29, 2022
    Publication date: October 20, 2022
    Inventors: Kai ZHANG, Li ZHANG, Hongbin LIU, Zhipin DENG, Yue WANG
  • Component-dependent sub-block dividing
    Patent number: 11477463
    Abstract: Devices, systems and methods for sub-block based prediction are described. In a representative aspect, a method for video encoding includes partitioning, based on a first rule, a luma component of a block of video data into a first set of sub-blocks. The method also includes partitioning, based on a second rule, a first chroma component of the block of video data into a second set of sub-blocks. The first and the second set of sub-blocks include different numbers of sub-blocks. The method also includes performing a subsequent motion prediction based on the first and the second set of sub-blocks.
    Type: Grant
    Filed: October 15, 2020
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • Implementation aspects in intra block copy in video coding
    Patent number: 11477441
    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: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Multi-parameter adaptive loop filtering in video processing
    Patent number: 11477491
    Abstract: Devices, systems and methods for video processing are described. In an exemplary aspect, a method for video processing includes performing a conversion between a coded representation of a video comprising one or more video regions and the video. The coded representation includes first side information that provides a clipping parameter for filtering a reconstruction of a video unit of a video region using a non-linear adaptive loop filter, and wherein the first side information is signaled together with second side information indicative of filter coefficients used in the non-linear adaptive loop filter.
    Type: Grant
    Filed: June 22, 2021
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Coding of motion information
    Patent number: 11477437
    Abstract: Implementations of the present disclosure provide a solution for encoding and decoding motion information. In this solution, during a conversion between a current video block of a video and a bitstream of the video, a group type of a subgroup of candidates of motion information for the current video block is determined, wherein the group type indicating whether the subgroup of candidates are to be reordered. Further, a list of candidates are constructed based on the group type; and the motion information for the current video block is derived from the list of candidates.
    Type: Grant
    Filed: January 28, 2021
    Date of Patent: October 18, 2022
    Assignee: Lemon Inc.
    Inventors: Na Zhang, Kai Zhang, Li Zhang, Hongbin Liu, Yuwen He, Yue Wang
  • Mapping restriction for intra-block copy virtual buffer
    Patent number: 11477479
    Abstract: A method for video processing includes determining, for a conversion between a current video block of a video picture of a video and a bitstream of the video, a number of reference samples in a virtual buffer comprising reference samples derived from the video picture based on a rule, wherein the rule specifies that a maximum number of available reference samples in the virtual buffer is less than a size of the virtual buffer; and performing the conversion based on the determining, wherein the current video block is coded in a prediction mode in which prediction samples are derived from blocks of the available reference samples in the virtual buffer based on a block vector.
    Type: Grant
    Filed: January 24, 2022
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu
  • Adaptive loop filtering for chroma components
    Patent number: 11477449
    Abstract: Devices, systems and methods related to management of syntax flags with respect chroma formats in video processing are described. In one representative aspect, a video decoding method includes determining, for a conversion between a video and a coded representation of the video, whether a syntax element associated with an adaptive loop filtering (ALF) operation for a chroma component of the video is included in the coded representation based on a condition. The method also includes performing the conversion according to the determining.
    Type: Grant
    Filed: October 6, 2021
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Na Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Restriction on applicability of cross component mode
    Patent number: 11477466
    Abstract: A method for visual media processing, including performing a conversion between a current chroma chroma block of visual media data and a bitstream representation of the current chroma chroma block, wherein, during the conversion, a chroma residual of the current chroma chroma block is scaled based on a scaling coefficient, wherein the scaling coefficient is derived at least based on luma samples located in predefined positions.
    Type: Grant
    Filed: September 20, 2021
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang, Jizheng Xu
  • Mode dependent motion vector difference precision set
    Patent number: 11477458
    Abstract: A method of processing a video bitstream includes determining a motion precision set based on coding information of a current block. A conversion between a video block and a coded representation of the video block is performed based on the motion precision set. The conversion corresponds to a reconstruction of the current block. In some example aspects, a motion vector difference (MVD) precision of a current block from a motion precision set is determined based on a selected motion precision set and a MVD precision index. A conversion between a video block and a coded representation of the video block using an MVD is performed based on the MVD precision. The MVD represents a difference between a predicted motion vector and an actual motion vector used during motion compensation processing.
    Type: Grant
    Filed: July 28, 2020
    Date of Patent: October 18, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • CROSS-COMPONENT PREDICTION WITH MULTIPLE-PARAMETER MODEL
    Publication number: 20220329816
    Abstract: A method of video processing includes performing a conversion between a current video block of a second color component of a video and a bitstream of the video using a cross-component prediction with multiple-parameter model (CCPMPM) in which samples of the current video block are predictively coded in the bitstream using a linear combination of samples of a first color component multiplied by linear coefficients and/or one or more offsets. The bitstream conforms to a format rule. The linear coefficients of the CCPMPM are determined using a first rule. The samples of the first color component are determined using a second rule.
    Type: Application
    Filed: June 24, 2022
    Publication date: October 13, 2022
    Inventors: Hongbin LIU, Li ZHANG, Kai ZHANG, Jizheng XU, Yuwen HE, Yue WANG
  • USAGE OF TEMPLATES FOR DECODER-SIDE INTRA MODE DERIVATION
    Publication number: 20220329826
    Abstract: Example implementations include a method, apparatus and computer-readable medium of video processing, including constructing, during a conversion between a current video block of a video and a bitstream of the video, at least one template set for the current video block from a plurality of sub-templates. The one or more sub-templates may be selected from a plurality of sub-templates including: a left sub-template, an above sub-template, a right-above sub-template, a left-below sub-template, and a left-above sub-template. The implementations further include deriving at least one intra-prediction mode (IPM) based on cost calculations. The implementations include determining, based on the at least one IPM, a final predictor of the current video block. The implementations include performing the conversion based on the final predictor.
    Type: Application
    Filed: June 10, 2022
    Publication date: October 13, 2022
    Inventors: Yang WANG, Kai ZHANG, Li ZHANG, Yuwen HE, Hongbin LIU
  • Unified Neural Network In-Loop Filter
    Publication number: 20220329836
    Abstract: A method implemented by a video coding apparatus includes applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample, wherein the NN filter is based on an NN filter model generated using a quality-level indicator (QI) input. The method also includes converting between a video media file and a bitstream based on the filtered sample that was generated.
    Type: Application
    Filed: April 5, 2022
    Publication date: October 13, 2022
    Inventors: Yue Li, Li Zhang, Kai Zhang
  • BIDIRECTIONAL OPTICAL FLOW BASED VIDEO CODING AND DECODING
    Publication number: 20220329842
    Abstract: Devices, systems and methods for sample refinement and filtering method for video coding are described. In an exemplary aspect, a method for video processing includes modifying for a conversion between a block of a video and a bitstream representation of the video, a refinement value for a prediction sample in the block by applying a clipping operation to refinement value. The refinement value is derived based on a gradient value of an optical flow coding process. An output of the clipping operation is within a range. The method also includes refining the prediction sample based on the refinement value and performing the conversion based on the refined prediction sample.
    Type: Application
    Filed: June 13, 2022
    Publication date: October 13, 2022
    Inventors: Hongbin LIU, Li ZHANG, Kai ZHANG, Jizheng XU, Yue WANG
  • Neural Network-Based Post Filter For Video Coding
    Publication number: 20220329837
    Abstract: A method of processing video data. The method includes determining that a supplemental enhancement information (SEI) message of a bitstream includes indicators specifying one or more neural network (NN) filter model candidates or selections for a video unit or samples within the video unit, and converting between a video media file comprising the video unit and the bitstream based on the indicators. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.
    Type: Application
    Filed: April 5, 2022
    Publication date: October 13, 2022
    Inventors: Yue Li, Li Zhang, Kai Zhang
  • VEHICLE POSITIONING METHOD AND SYSTEM FOR FIXED PARKING SCENARIO
    Publication number: 20220326036
    Abstract: The invention relates to a vehicle positioning method and system for a fixed parking scenario. The method includes: a map obtaining step of obtaining, by a vehicle, a parking scenario map from a cloud according to a preset trigger condition; a first positioning step of obtaining first geographical position information of the vehicle based on a first marker in a fixed parking scenario, and matching the first geographic position information with the parking scenario map, so as to obtain a first vehicle pose of the vehicle in the parking scenario map; and a second positioning step of obtaining second geographical position information of the vehicle based on a second marker in the fixed parking scenario, and matching the second geographical position information with the parking scenario map, so as to obtain a second vehicle pose of the vehicle in the parking scenario map.
    Type: Application
    Filed: April 11, 2022
    Publication date: October 13, 2022
    Inventors: Xuejie LV, Shiting WANG, Chengzuo QI, Kai ZHANG, Quansheng DUAN
  • Air admittance valve
    Patent number: 11466442
    Abstract: The present invention relates to an air admittance valve (AAV) that operates automatically at low pressures to selectively open and close an air passageway between an inlet and an outlet. The AAV comprises a valve body having a centrally disposed, internal valve chamber in communication with the ambient environment, and having a valve seat. The AAV includes a sealing member having a flexible diaphragm that is fastened to a support ring, the ring defining one or more lugs on an outer periphery thereof. The AAV further includes a cap member within which the sealing member may be disposed, such that the one or more lugs may interact with an interior surface of the cap. The sealing member may selectively seal or unseal from the valve seat in response to pressure differentials between the inlet and the outlet.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: October 11, 2022
    Assignee: OATEY CO.
    Inventors: Aaron Lorkowski, Kenneth Brown, Kai Zhang
  • Adaptive motion vector difference resolution for affine mode
    Patent number: 11470309
    Abstract: A method of visual media processing includes determining whether to use an affine adaptive motion vector resolution (AMVR) technique on visual media data relying on a control information related to the affine AMVR technique in a bitstream representation of the visual media data, wherein the control information is included or excluded from the bitstream representation based on a rule; and performing a conversion between the visual media data and the bitstream representation of the visual media data.
    Type: Grant
    Filed: November 8, 2021
    Date of Patent: October 11, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • Direction-based prediction for intra block copy in video coding
    Patent number: 11470323
    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: October 11, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Interaction between different DMVD models
    Patent number: 11470341
    Abstract: Apparatus and methods for video processing are described. An exemplary method for video processing includes: determining non-updated motion information associated with a current block; updating the non-updated motion information based on multiple decoder-side motion vector derivation (DMVD) methods to generate updated motion information for the current block; and performing, based on the updated motion information, a conversion between the current block and a bitstream representation of a video including the current block.
    Type: Grant
    Filed: February 3, 2021
    Date of Patent: October 11, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • Simplification of combined inter-intra prediction
    Patent number: 11470331
    Abstract: Techniques for implementing video processing techniques are described. In one example implementation, a method of video processing includes determining, for a conversion between a current block of a video coded using a combined inter and intra prediction (CIIP) coding technique and a bitstream representation of the video, an intra-prediction mode of the current block independently from an intra-prediction mode of a neighboring block. The CIIP coding technique uses an intermedia inter prediction value and an intermedia intra prediction value to derive a final prediction value of the current block. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: January 21, 2021
    Date of Patent: October 11, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang