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).

  • Selective use of adaptive in-loop color-space transform and other video coding tools
    Patent number: 11778233
    Abstract: A method of video processing is provided. The method includes: determining, for a conversion between a current video unit of a video and a coded representation of the video, that applicability of a first coding tool and a second coding tool is mutually exclusive; and performing the conversion based on the determining, wherein the first coding tool corresponds to an adaptive color space transformation (ACT) tool; wherein 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: October 3, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Jizheng Xu, Kai Zhang, Hongbin Liu, Weijia Zhu, Yue Wang
  • SYNTAX ELEMENT FOR CHROMA RESIDUAL SCALING
    Publication number: 20230308691
    Abstract: A method for visual media processing includes processing a bitstream representation for a conversion between a current video block in a video region of a visual media data and the bitstream representation. The bitstream representation is based on a rule that specifies that one or more syntax elements used in a luma-dependent chroma residual scaling step are selectively included in the bitstream representation. The luma-dependent chroma residual scaling step includes scaling chroma samples based on neighboring reconstructed luma samples during the conversion. The one or more syntax elements are usable to derive a chroma residual scaling factor used for the scaling.
    Type: Application
    Filed: April 4, 2023
    Publication date: September 28, 2023
    Inventors: Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang, Jizheng Xu
  • PRECISION TRANSFORM COEFFICIENT SCALING AND QUANTIZATION FOR IMAGE AND VIDEO CODING
    Publication number: 20230308659
    Abstract: Methods, systems, and devices for high-precision transform and quantization for image and video coding are described. A example method of video processing includes determining, for a conversion between a video comprising a current block and a bitstream representation of the video, that the conversion comprises an application of a transform to the current block, and performing, based on the determining, the conversion. A bit-shifting operation of a scaling process for transform coefficients associated with the transform is based on whether the current block is coded with a block-based differential pulse code modulation (BDPCM) mode.
    Type: Application
    Filed: June 2, 2023
    Publication date: September 28, 2023
    Inventors: Jizheng Xu, Kai Zhang, Li Zhang, Hongbin Liu, Zhipin Deng, Yue Wang
  • INTERPLAY BETWEEN REFERENCE PICTURE RESAMPLING AND VIDEO CODING TOOLS
    Publication number: 20230308641
    Abstract: An example method of video processing includes determining, for a conversion between a current block of a current picture of a video and a bitstream of the video, whether to disable a coding tool for the current block; and performing the conversion based on the determining, wherein the coding tool is disabled when a dimension of a reference picture of one or more reference pictures of the current block is different from a dimension of the current picture, or a dimension of a scaling window in a reference picture of one or more reference pictures of the current block is different from a dimension of a scaling window in the current picture.
    Type: Application
    Filed: May 5, 2023
    Publication date: September 28, 2023
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu
  • Multiple hypothesis for sub-block prediction blocks
    Patent number: 11770540
    Abstract: A method of encoding or decoding video includes: dividing a current video block into multiple sub-blocks video blocks; generating a merge candidate list for at least one sub-blocks video blocks of the multiple sub-blocks video blocks; and performing a conversion between the video block and a bitstream of the video block based one the merge candidate list; wherein the merge candidate list comprises at least one merge candidate with multi-hypothesis mode.
    Type: Grant
    Filed: May 10, 2021
    Date of Patent: September 26, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Change detection criteria for updating sensor-based reference maps
    Patent number: 11767028
    Abstract: This document describes change detection criteria for updating sensor-based maps. Based on an indication that a registered object is detected near a vehicle, a processor determines differences between features of the registered object and features of a sensor-based reference map. A machine-learned model is trained using self-supervised learning to identify change detections from inputs. This model is executed to determine whether the differences satisfy change detection criteria for updating the sensor-based reference map. If the change detection criteria is satisfied, the processor causes the sensor-based reference map to be updated to reduce the differences, which enables the vehicle to safely operate in an autonomous mode using the updated reference map for navigating the vehicle in proximity to the coordinate location of the registered object.
    Type: Grant
    Filed: February 22, 2021
    Date of Patent: September 26, 2023
    Assignee: Aptiv Technologies Limited
    Inventors: Kai Zhang, Walter K. Kosiak
  • Reference picture resampling
    Patent number: 11770563
    Abstract: Several techniques for video encoding and video decoding are described. One example method includes performing a conversion between a subpicture in a video picture of a video and a bitstream of the video according to a rule. The rule specifies that multiple syntax elements are used to specify usage of a reference picture resampling tool.
    Type: Grant
    Filed: September 21, 2022
    Date of Patent: September 26, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Ye-kui Wang, Li Zhang, Kai Zhang, Zhipin Deng
  • POSITION DEPENDENT COEFFICIENT REORDERING IN CODED VIDEO
    Publication number: 20230300334
    Abstract: Methods, system and apparatus for video processing are described. One example method of processing video data includes performing a conversion between a current block of a video and a bitstream of the video. Samples of the current block are represented in the bitstream using coefficients that are arranged according to a rule responsive to locations of the samples of the current block.
    Type: Application
    Filed: May 23, 2023
    Publication date: September 21, 2023
    Inventors: Li Zhang, Kai Zhang, Yuhuai Zhang, Hongbin Liu, Yue Wang, Siwei Ma
  • SIMPLIFIED HISTORY BASED MOTION VECTOR PREDICTION
    Publication number: 20230300322
    Abstract: A video coding or decoding method includes using history-based motion vector prediction (HMVP) for conversion between multiple video blocks including a current block of video and a bitstream representation of the multiple video blocks such that for a uni-predicted block that for which a single reference picture is used for motion compensation, refraining from updating a look-up table for HMVP candidates for the uni-predicted block. The video coding or decoding method further includes performing the conversion using look-up tables for the multiple video blocks.
    Type: Application
    Filed: March 27, 2023
    Publication date: September 21, 2023
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • HIGH LEVEL SYNTAX FOR INTER PREDICTION WITH GEOMETRIC PARTITIONING
    Publication number: 20230300337
    Abstract: A method of processing video data is described. The method includes performing a conversion between a current video block of a video and a bitstream of the video. A geometric partitioning mode index for the current video block is coded in the bitstream and a binarization of the geometric partitioning mode index is performed according to a rule. The geometric partitioning mode index specifies a geometric splitting shape of a geometric partitioning mode applied to the current video block. The rule specifies that the geometric partitioning mode index is coded with a fixed-length binarization.
    Type: Application
    Filed: May 23, 2023
    Publication date: September 21, 2023
    Inventors: Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang, Jizheng Xu, Yang Wang, Yue Wang
  • CROSS-COMPONENT ADAPTIVE LOOP FILTERING IN VIDEO CODING
    Publication number: 20230300380
    Abstract: An example method of video processing includes making a determination, for a conversion between a current video block of a video and a bitstream representation of the video, whether a cross-component adaptive loop filtering tool is enabled for the current video block based on a color property of the video. The method also includes performing the conversion according to the determination.
    Type: Application
    Filed: May 23, 2023
    Publication date: September 21, 2023
    Inventors: Weijia Zhu, Li Zhang, Jizheng Xu, Kai Zhang
  • Cross-component adaptive loop filter
    Patent number: 11765368
    Abstract: Methods, systems and apparatus for video processing including coding or decoding are described. One example method of video processing includes determining, for a conversion between a video region of a chroma component of a video and a bitstream of the video, a manner of applying a cross-component adaptive loop filtering (CC-ALF) operation to a first sample of the chroma component based on a position of a second sample associated with the first sample. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: August 3, 2022
    Date of Patent: September 19, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Yue Wang
  • Denoising autoencoder image captioning
    Patent number: 11763544
    Abstract: In an approach to augmenting a caption dataset by leveraging a denoising autoencoder to sample and generate additional captions from the ground truth captions, one or more computer processors generate a plurality of new captions utilizing an autoencoder fed with one or more noisy captions, wherein the autoencoder is trained with a dataset comprising a plurality of ground truth captions. The one or more computer processors calculate an importance weight for each new caption in the plurality of generated new captions as compared to a plurality of associated ground truth captions based on a consensus metric. The one or more computer processors train a caption model with the generated plurality of new captions and associated calculated weights.
    Type: Grant
    Filed: July 7, 2020
    Date of Patent: September 19, 2023
    Assignee: International Business Machines Corporation
    Inventors: Shiwan Zhao, Hao Kai Zhang, Yi Ke Wu, Zhong Su
  • Entropy coding for partition syntax
    Patent number: 11765358
    Abstract: Systems, methods and apparatus for video processing are described. The video processing may include video encoding, video decoding or video transcoding. One example method of video processing includes performing a conversion between a current block of a video and a bitstream of the video according to a rule. The rule specifies that selection of a context for coding a syntax element specifying whether the block is split horizontally or vertically is based on a number of allowed vertical splits and a number of allowed horizontal splits. The number of allowed vertical splits includes a number of allowed binary vertical splits and a number of allowed ternary vertical splits, and the number of allowed horizontal splits includes a number of allowed binary horizontal splits and a number of allowed ternary horizontal splits.
    Type: Grant
    Filed: October 31, 2022
    Date of Patent: September 19, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLGY CO., LTD., BYTEDANCE INC.
    Inventors: Yang Wang, Li Zhang, Zhipin Deng, Kai Zhang, Hongbin Liu
  • Decoding order of different SEI messages
    Patent number: 11765394
    Abstract: Methods, devices and systems for video coding and encoding, which include constraints, restrictions and signaling for subpictures, slices, and tiles, are described. One example method of video processing includes performing a conversion between a video and a bitstream of the video, wherein the bitstream comprises one or more access units according to a format rule, and wherein the format rule specifies an order in which a first message and a second message that apply to an operation point (OP) are present within an access unit (AU) such that the first message precedes the second message in a decoding order.
    Type: Grant
    Filed: July 7, 2022
    Date of Patent: September 19, 2023
    Assignee: BYTEDANCE INC.
    Inventors: Ye-kui Wang, Li Zhang, Kai Zhang
  • Multiple prediction blocks for one intra-coded block
    Patent number: 11765345
    Abstract: Devices, systems and methods for digital video processing, which includes multiple prediction blocks for one intra-coded block, are described. In a representative aspect, a method for video processing includes generating a final prediction block for a conversion between a current block of visual media data and a bitstream representation of the current block and performing the conversion based on the final prediction block. At least a portion of the final prediction block is generated based on a combination of a first prediction block and a second prediction block that are based on reconstructed samples from an image segment that comprises the current block.
    Type: Grant
    Filed: March 18, 2021
    Date of Patent: September 19, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Border partition
    Patent number: 11765398
    Abstract: Devices, systems and methods for picture border coding are described. In a representative aspect, a method for processing picture includes segmenting a picture into one or multiple picture segments, determining that a first block of a picture segment covers at least one region that is outside a border of the picture segment, wherein a size of the first block is M×N pixels, selecting a second block of size K×L pixels, where (K?M and L<N) or (K<M and L?N), wherein the second block falls entirely within the picture segment and wherein the second block is used as a largest coding unit, a leaf coding block or a coding tree block; and processing, using a partition tree, the border of the picture segment, wherein the partition tree is based on the size of the second block.
    Type: Grant
    Filed: December 21, 2020
    Date of Patent: September 19, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Hsiao Chiang Chuang, Yue Wang
  • Using quantization groups in video coding
    Patent number: 11765352
    Abstract: An example method of video processing includes applying, in a conversion between a video comprising multiple components and a bitstream representation of the video, a deblocking filter to video blocks of the multiple components. A deblocking filter strength for the deblocking filter of each of the multiple components is determined according to a rule that specifies to use a different manner for determining the deblocking filter strength for the video blocks of each of the multiple components.
    Type: Grant
    Filed: June 8, 2022
    Date of Patent: September 19, 2023
    Assignee: BYTEDANCE INC.
    Inventors: Weijia Zhu, Li Zhang, Jizheng Xu, Kai Zhang, Ye-kui Wang
  • USING QUANTIZATION GROUPS IN VIDEO CODING
    Publication number: 20230291898
    Abstract: An example method of video processing includes applying, in a conversion between a video comprising multiple components and a bitstream representation of the video, a deblocking filter to video blocks of the multiple components. A deblocking filter strength for the deblocking filter of each of the multiple components is determined according to a rule that specifies to use a different manner for determining the deblocking filter strength for the video blocks of each of the multiple components.
    Type: Application
    Filed: May 23, 2023
    Publication date: September 14, 2023
    Inventors: Weijia Zhu, Li Zhang, Jizheng Xu, Kai Zhang, Ye-kui Wang
  • UNIQUE PDC MICROSTRUCTURE AND THE METHOD OF MAKING IT
    Publication number: 20230287251
    Abstract: A superabrasive compact and a method of making the superabrasive compact are disclosed. A superabrasive compact may comprise a diamond table and a substrate. The diamond table may be attached to the substrate. The diamond table may include bonded diamond grains defining interstitial channels. The interstitial channels may be filled with non-catalytic binder materials in some regions. The interstitial channels in some other regions may be filled with a catalytic materials from the substrate.
    Type: Application
    Filed: March 14, 2022
    Publication date: September 14, 2023
    Inventor: Kai ZHANG