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).

  • SUBPICTURE INFORMATION SIGNALING IN VIDEO BITSTREAMS
    Publication number: 20220394304
    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 one or more subpictures and a bitstream of the video. The bitstream conforms to a format rule specifying that a first syntax element indicating whether an operation is performed across a boundary of a subpicture in the coded layer video sequence is selectively included responsive to a number of subpictures in the video picture.
    Type: Application
    Filed: August 12, 2022
    Publication date: December 8, 2022
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Ye-kui Wang, Kui Fan
  • Neural Network-Based Video Compression with Spatial-Temporal Adaptation
    Publication number: 20220394240
    Abstract: A mechanism for processing video data is disclosed. A determination is made to apply an end-to-end neural network-based video codec to a current video unit of a video. The end-to-end neural network-based video codec comprises a spatial-temporal adaptive compression (STAC) component including a frame extrapolative compression (FEC) branch and an image compression branch. A conversion is performed between the current video unit and a bitstream of the video via the end-to-end neural network-based video codec.
    Type: Application
    Filed: June 1, 2022
    Publication date: December 8, 2022
    Inventors: Zhaobin Zhang, Li Zhang, Yue Li, Kai Zhang
  • REFERENCE PICTURE RESAMPLING ACTIVATION IN VIDEO CODING
    Publication number: 20220394243
    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 comprising a video picture that includes a video slice and a bitstream of the video. The bitstream conforms to a format rule specifying that, in case a slice type of the video slice is type P and temporal motion vector prediction is enabled, usage of reference picture resampling (RPR) for a reference picture in a collocated reference picture list is disabled. The reference picture is indicated by a reference index of a collocated picture of the video slice used for the temporal motion vector prediction.
    Type: Application
    Filed: August 11, 2022
    Publication date: December 8, 2022
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Ye-kui Wang, Kui Fan
  • Parameter Update of Neural Network-Based Filtering
    Publication number: 20220394288
    Abstract: A method of processing video data including determining, for a conversion between a video and a bitstream of the video, that the bitstream includes an indicator. The indicator indicates that a first parameter set for a neural network (NN) filter model includes different filter parameters than a second parameter set for the NN filter model. The method further includes performing the conversion based on the indicator. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.
    Type: Application
    Filed: May 16, 2022
    Publication date: December 8, 2022
    Inventors: Yue Li, Li Zhang, Kai Zhang
  • On Padding Methods For Neural Network-Based In-Loop Filter
    Publication number: 20220394309
    Abstract: A method implemented by a video coding apparatus. The method includes determining, in real time, padding dimensions for padding samples to be applied to a video unit of a video for in-loop filtering, wherein d1, d2, d3, and d4 represent the padding dimensions corresponding to top, bottom, left, and right boundaries of the video unit, respectively; and performing a conversion between a video unit and a bitstream of the video based on the padding dimensions that were determined. A corresponding video coding apparatus and non-transitory computer-readable recording medium are also disclosed.
    Type: Application
    Filed: May 13, 2022
    Publication date: December 8, 2022
    Inventors: Yue Li, Li Zhang, Kai Zhang
  • PALETTE MODE FOR LOCAL DUAL TREE
    Publication number: 20220394282
    Abstract: Video processing methods, systems and appratrus are described. One example method includes performing a conversion between a video block of a video and a bitstream of the video using a palette mode in which samples of the video block are represented using a palette of representive color values. A size of the palette of the video block is determined based on whether a local dual tree is applied for the conversion.
    Type: Application
    Filed: August 5, 2022
    Publication date: December 8, 2022
    Inventors: Jizheng Xu, Li Zhang, Ye-kui Wang, Kai Zhang, Weijia Zhu, Yue Wang, Yang Wang, Hongbin Liu
  • Double-glass photovoltaic assembly
    Patent number: 11522089
    Abstract: A double-glass photovoltaic assembly includes a laminate member, a junction box, and a first frame and a second frame disposed only at two long sides of the laminate member. The laminate member includes a cover plate glass, a first encapsulation adhesive film, a battery string, a second encapsulation adhesive film, a back plate glass, and a busbar. A through-hole is provided at the back plate glass. An end of the busbar is connected to the battery string. Another end of the busbar passes through the through-hole, and is bent to form a bent edge to be connected to the junction box. The bent edge of the busbar does not contact an edge of the through-hole. The double-glass photovoltaic assembly adopting a double-frame design can meet the requirements of load capacity.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: December 6, 2022
    Assignee: SHANGHAI JA SOLAR TECHNOLOGY CO., LTD.
    Inventors: Daoyuan Chen, Xin Li, Kai Zhang, Lingling Liu
  • Bitstream conformance constraints for intra block copy in video coding
    Patent number: 11523107
    Abstract: A method of processing visual media includes performing a conversion between a current video block of a current picture of a visual media data and a bitstream representation of the visual media data using a buffer comprising reference samples from the current picture for derivation of a prediction block of the current video block. The conversion is based according to rule which specifies that, for the bitstream representation to conform the rule, a reference sample in the buffer is to satisfy a bitstream conformance constraint.
    Type: Grant
    Filed: January 7, 2022
    Date of Patent: December 6, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Luma mapping with chroma scaling
    Patent number: 11523126
    Abstract: Methods, systems, and devices for luma mapping with chroma scaling for video and image coding are disclosed. An example method of video processing includes performing, for a current region comprising a luma block, a first chroma block, and a second chroma block, a conversion between the current region of a video and a bitstream representation of the video according to a rule that specifies an order in which, during decoding, the first chroma block and the second chroma block are processed based on mapped sample values of the luma block.
    Type: Grant
    Filed: March 16, 2022
    Date of Patent: December 6, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kui Fan, Li Zhang, Kai Zhang, Yue Wang
  • Nonlinear adaptive loop filtering in video processing
    Patent number: 11523140
    Abstract: Devices, systems and methods for video processing are described. In an exemplary aspect, a method for video processing includes encoding a video unit of a video as an encoded video unit; generating reconstruction samples from the encoded video unit; performing a clipping operation on the reconstruction samples, wherein a clipping parameter used in the clipping operation is a function of a clipping index and a bit-depth of the reconstruction samples or a bit-depth of samples of the video unit; applying a non-linear adaptive loop filter to an output of the clipping operation; and generating a coded representation of the video using the encoded video unit.
    Type: Grant
    Filed: June 22, 2021
    Date of Patent: December 6, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Position restriction for inter coding mode
    Patent number: 11523108
    Abstract: A method of video processing includes determining, for a conversion between a current block of a first picture of a video and a bitstream representation of the video, a motion candidate based on motion information from a second picture according to a rule. The rule specifies that a position from which the motion information is accessed is constrained to be within a specific subpicture of the second picture. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: February 4, 2022
    Date of Patent: December 6, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu
  • Interaction between IBC and ATMVP
    Patent number: 11523123
    Abstract: Devices, systems and methods for applying intra-block copy (IBC) in video coding are described. In general, methods for integrating IBC with existing motion compensation algorithms for video encoding and decoding are described. In a representative aspect, a method for video encoding using IBC includes determining whether a current block of the current picture is to be encoded using a motion compensation algorithm, and encoding, based on the determining, the current block by selectively applying an intra-block copy to the current block. In a representative aspect, another method for video encoding using IBC includes determining whether a current block of the current picture is to be encoded using an intra-block copy, and encoding, based on the determining, the current block by selectively applying a motion compensation algorithm to the current block.
    Type: Grant
    Filed: September 3, 2020
    Date of Patent: December 6, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • CROSS COMPONENT ADAPTIVE LOOP FILTERING FOR VIDEO CODING
    Publication number: 20220385898
    Abstract: A method of video processing comprises performing a conversion between a video unit of a video and a bitstream of the video according to a rule, wherein the rule specifies that whether a cross-component adaptive loop filter (CC-ALF) mode and an adaptive loop filter (ALF) mode are enabled for coding the video unit are indicated in the bitstream in a mutually independent manner.
    Type: Application
    Filed: July 1, 2022
    Publication date: December 1, 2022
    Inventors: Weijia Zhu, Li Zhang, Jizheng Xu, Kai Zhang, Ye-kui Wang
  • Conditions for Applicability of Cross-Component Coding
    Publication number: 20220385926
    Abstract: A method for visual media processing, including: using a rule that specifies representing, based on a fixed value, a chroma residual scaling factor for at least one chroma block associated with a current video unit of visual media data, wherein the fixed value is based at least on one or more conditions; and performing a conversion between the current video unit and a bitstream representation of the current video unit.
    Type: Application
    Filed: July 26, 2022
    Publication date: December 1, 2022
    Inventors: Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang, Jizheng Xu
  • Bidirectional optical flow based video coding and decoding
    Patent number: 11516497
    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: Grant
    Filed: August 18, 2021
    Date of Patent: November 29, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Jizheng Xu, Yue Wang
  • Implementation aspects in intra block copy in video coding
    Patent number: 11516467
    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: November 29, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Simplification of combined inter-intra prediction
    Patent number: 11516480
    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: November 29, 2022
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Constraints on Value Ranges in Video Bitstreams
    Publication number: 20220377383
    Abstract: A method of video processing includes performing a conversion between a video and a bitstream of the video according to a rule, wherein the rule specifies that a first syntax element, which indicates a number of parameters for an output layer set (OLS) hypothetical reference decoder (HRD) in a video parameter set (VPS) associated with the video, is less than a first predetermined threshold.
    Type: Application
    Filed: July 8, 2022
    Publication date: November 24, 2022
    Inventors: Ye-kui Wang, Li Zhang, Kai Zhang
  • CONSTRAINTS FOR VIDEO CODING AND DECODING
    Publication number: 20220377353
    Abstract: A method of video processing is provided that includes performing a conversion between a block of a video and a bitstream of the video. The bitstream conforms to a formatting rule specifying that a size of a merge estimation region (MER) is indicated in the bitstream and the size of the MER is based on a dimension of a video unit. The MER comprises a region used for deriving a motion candidate for the conversion.
    Type: Application
    Filed: July 11, 2022
    Publication date: November 24, 2022
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu, Ye-kui Wang
  • INDEPENDENT CODING OF PALETTE MODE USAGE INDICATION
    Publication number: 20220377341
    Abstract: Devices, systems and methods for palette mode coding are described. An exemplary method for video processing includes performing a conversion between a block of a video region of a video and a bitstream representation of the video. The bitstream representation is processed according to a first format rule that specifies whether a first indication of usage of a palette mode is signaled for the block and a second format rule that specifies a position of the first indication relative to a second indication of usage of a prediction mode for the block.
    Type: Application
    Filed: May 26, 2021
    Publication date: November 24, 2022
    Inventors: Weijia ZHU, Li ZHANG, Jizheng XU, Kai ZHANG, Hongbin LIU, Yue WANG