Patents by Inventor Shanshe WANG

Shanshe WANG 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).

  • Patent number: 12363311
    Abstract: An encoding method includes binarizing a chrominance prediction mode of an image block of an image that is permitted to use a CCLM and/or regular intra-frame chrominance prediction mode to obtain a bit string including adjacent bits. The CCLM includes first, second, and third modes, a second mode, and a third mode, the regular intra-frame chrominance prediction mode being other intra-frame chrominance prediction modes except CCLM. A first bit of the adjacent bits indicates whether CCLM is used according to whether a value there of is 1. A second bit indicates whether to use the first mode when the first bit indicates to use CCLM. A third bit indicates whether the second or third mode is used when the second bit indicates the first mode is not used. The method further includes using mutually independent probability models to respectively encode the first bit and the second bit.
    Type: Grant
    Filed: December 19, 2023
    Date of Patent: July 15, 2025
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Siwei Ma, Jiaqi Zhang, Xiaozhen Zheng, Shanshe Wang
  • Patent number: 12294737
    Abstract: A video image processing method includes dividing a current image block into a plurality of sub-blocks, in response to a target neighboring block of the current image block satisfying a preset condition, determining related blocks of the sub-blocks in a collocated frame of the current image block according to a motion vector of the target neighboring block, encoding or decoding the current image block according to motion vectors of the related blocks of the sub-blocks, determining a group of control point motion vectors in an affine transformation mode using one or more neighboring blocks of the current image block, and adding the group of control point motion vectors to a motion vector candidate list of the current image block.
    Type: Grant
    Filed: April 1, 2024
    Date of Patent: May 6, 2025
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Tianliang Fu, Shanshe Wang, Siwei Ma, Weiran Li, Suhong Wang
  • Patent number: 12294738
    Abstract: A video encoding method includes determining a base motion vector list that includes a dual-prediction base motion vector group including a first base motion vector and a second base motion vector, determining two motion vector offsets according to a preset offset set, determining motion vectors of a current image block according to the first base motion vector, the second base motion vector, and the two motion vector offsets, and performing prediction on the current image block according to the motion vectors of the current image block.
    Type: Grant
    Filed: May 24, 2024
    Date of Patent: May 6, 2025
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma, Weiran Li
  • Patent number: 12294736
    Abstract: A video processing method includes obtaining motion information of a left neighboring block of a current image block, and, where the left neighboring block satisfies a condition, determining, in a collocated frame of the current image block, a related block of a sub-block of the current image block using a motion vector of the left neighboring block as a motion offset, and determining a motion vector of the sub-block according to a motion vector of the related block. The preset condition includes a reference image of the left neighboring block being same as the collocated frame of the current image block. Determining the motion vector of the sub-block includes, where reference images of the related block and the sub-block are not specific reference images, determining the motion vector of the sub-block according to a scaled motion vector obtained by scaling the motion vector of the related block.
    Type: Grant
    Filed: April 1, 2024
    Date of Patent: May 6, 2025
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma, Weiran Li
  • Publication number: 20250126301
    Abstract: A loop filtering method includes determining clip index parameters of a loop filter and encoding the clip index parameters. The clip index parameters include a first clip index parameter for brightness component and a second clip index parameter for chrominance component. A first clip parameter for the brightness component is selected from a parameter list based on the first clip index parameter. A second clip parameter for the chrominance component is selected from the parameter list based on the second clip index parameter.
    Type: Application
    Filed: December 17, 2024
    Publication date: April 17, 2025
    Inventors: Siwei MA, Xuewei MENG, Xiaozhen ZHENG, Shanshe WANG
  • Publication number: 20250088655
    Abstract: An encoder includes a memory storing program instructions and a processor configured to execute the program instructions to determine a current image block, turn off a temporal motion vector prediction (TMVP) operation in response to a size of the current image block meeting a preset condition so that a temporal candidate motion vector of the current image block is not determined according to the TMVP operation, and encode the current image block. The TMVP operation includes determining a relevant block of the current image block in a temporal neighboring image, and determining the temporal candidate motion vector of the current image block according to a motion vector of the relevant block.
    Type: Application
    Filed: November 25, 2024
    Publication date: March 13, 2025
    Inventors: Xiaozhen ZHENG, Suhong WANG, Shanshe WANG, Siwei MA
  • Patent number: 12231696
    Abstract: The present disclosure provides a loop filtering method which includes determining a clip index parameter of a loop filter, and encoding the clip index parameter by using a non-exponential Golomb encoding method.
    Type: Grant
    Filed: December 23, 2021
    Date of Patent: February 18, 2025
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Siwei Ma, Xuewei Meng, Xiaozhen Zheng, Shanshe Wang
  • Publication number: 20240414334
    Abstract: A video encoding method includes encoding an image to generate a bitstream. In the bitstream, a first syntax element is configured to indicate whether a first chrominance component is filtered by adaptive loop filtering (ALF), and a second syntax element is configured to indicate whether a second chrominance component is filtered by the ALF. The ALF is not a cross-component ALF (CC-ALF) filter.
    Type: Application
    Filed: August 19, 2024
    Publication date: December 12, 2024
    Inventors: Siwei MA, Xuewei MENG, Shanshe WANG, Xiaozhen ZHENG
  • Patent number: 12155856
    Abstract: A video image processing method including determining a current image block, constructing a motion information candidate list for the current image block, in response to a size of the current image block meeting a preset condition, turning off a temporal motion vector prediction (TMVP) operation so that a temporal candidate motion vector of the current image block is not determined according to the TMVP operation, and encoding the current image block. The TMVP operation includes determining a relevant block of the current image block in a temporal neighboring image, and determining the temporal candidate motion vector of the current image block according to a motion vector of the relevant block.
    Type: Grant
    Filed: June 26, 2023
    Date of Patent: November 26, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma
  • Publication number: 20240373002
    Abstract: A video processing method including determining a target CC-ALF filter for a chrominance component of a current block of an image from a plurality of CC-ALF filters, determining target CC-ALF filter coefficients for the chrominance component according to the chrominance component after ALF and a luminance component of the current block without ALF, filtering the chrominance component after ALF according to the target CC-ALF filter and the target CC-ALF filter coefficients, determining a filtered chrominance component of the current block according to the chrominance component after being filtered with the target CC-ALF filter coefficients and the chrominance component after the ALF, and encoding the filtered chrominance component, including encoding using a total number of the plurality of CC-ALF filters, an index of the target CC-ALF filter, and the target CC-ALF filter coefficients as syntax elements.
    Type: Application
    Filed: July 15, 2024
    Publication date: November 7, 2024
    Inventors: Siwei MA, Xuewei MENG, Xiaozhen ZHENG, Shanshe WANG
  • Publication number: 20240314356
    Abstract: A video encoding method includes determining a base motion vector list that includes a dual-prediction base motion vector group including a first base motion vector and a second base motion vector, determining two motion vector offsets according to a preset offset set, determining motion vectors of a current image block according to the first base motion vector, the second base motion vector, and the two motion vector offsets, and performing prediction on the current image block according to the motion vectors of the current image block.
    Type: Application
    Filed: May 24, 2024
    Publication date: September 19, 2024
    Inventors: Xiaozhen ZHENG, Suhong WANG, Shanshe WANG, Siwei MA, Weiran LI
  • Patent number: 12069252
    Abstract: A video encoding method includes encoding images of an image sequence to generate a bitstream of the image sequence. Different identifiers are used for two chrominance components of one image in a syntax element of an image level in the bitstream to indicate whether the corresponding chrominance components are filtered by adaptive loop filtering (ALF).
    Type: Grant
    Filed: September 30, 2022
    Date of Patent: August 20, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Siwei Ma, Xuewei Meng, Shanshe Wang, Xiaozhen Zheng
  • Publication number: 20240259592
    Abstract: A video image processing method includes dividing a current image block into a plurality of sub-blocks, in response to a target neighboring block of the current image block satisfying a preset condition, determining related blocks of the sub-blocks in a collocated frame of the current image block according to a motion vector of the target neighboring block, encoding or decoding the current image block according to motion vectors of the related blocks of the sub-blocks, determining a group of control point motion vectors in an affine transformation mode using one or more neighboring blocks of the current image block, and adding the group of control point motion vectors to a motion vector candidate list of the current image block.
    Type: Application
    Filed: April 1, 2024
    Publication date: August 1, 2024
    Inventors: Xiaozhen ZHENG, Tianliang FU, Shanshe WANG, Siwei MA, Weiran LI, Suhong WANG
  • Publication number: 20240251073
    Abstract: A bitstreams generating method includes obtaining a historical motion information candidate list used for encoding each of a plurality of image blocks included in a region of a current frame, encoding the plurality of image blocks according to the historical motion information candidate list, and generating bitstreams including one or more indexes of motion information. The historical motion information candidate list is a history-based motion vector prediction (HMVP) candidate list. During the process of encoding all the plurality of image blocks included in the region, the historical motion information candidate list is not updated. Only the motion information of the last image block in the region is used to update the historical motion information candidate list after the encoding process of the last image block is finished.
    Type: Application
    Filed: March 18, 2024
    Publication date: July 25, 2024
    Inventors: Suhong WANG, Xiaozhen ZHENG, Shanshe WANG, Siwei MA
  • Publication number: 20240251099
    Abstract: A video processing method includes obtaining motion information of a left neighboring block of a current image block, and, where the left neighboring block satisfies a condition, determining, in a collocated frame of the current image block, a related block of a sub-block of the current image block using a motion vector of the left neighboring block as a motion offset, and determining a motion vector of the sub-block according to a motion vector of the related block. The preset condition includes a reference image of the left neighboring block being same as the collocated frame of the current image block. Determining the motion vector of the sub-block includes, where reference images of the related block and the sub-block are not specific reference images, determining the motion vector of the sub-block according to a scaled motion vector obtained by scaling the motion vector of the related block.
    Type: Application
    Filed: April 1, 2024
    Publication date: July 25, 2024
    Inventors: Xiaozhen ZHENG, Suhong WANG, Shanshe WANG, Siwei MA, Weiran LI
  • Patent number: 12041231
    Abstract: An in-loop filtering method includes determining a target filter for a chrominance component of a current block of an image from a plurality of cross-component ALF filters, determining target filter coefficients for the chrominance component according to the chrominance component after ALF and a luminance component of the current block without ALF, filtering the chrominance component after ALF according to the target filter and the target filter coefficients, determining a filtered chrominance component of the current block according to the chrominance component after being filtered with the target filter coefficients and the chrominance component after the ALF, encoding according to the filtered chrominance component of the current block, and encoding a total number of the plurality of cross-component ALF filters as a syntax element. A stream of the image includes only one syntax element for indicating the total number of the plurality of cross-component ALF filters.
    Type: Grant
    Filed: June 29, 2022
    Date of Patent: July 16, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Siwei Ma, Xuewei Meng, Xiaozhen Zheng, Shanshe Wang
  • Publication number: 20240195981
    Abstract: An encoding method includes binarizing a chrominance prediction mode of an image block of an image that is permitted to use a CCLM and/or regular intra-frame chrominance prediction mode to obtain a bit string including adjacent bits. The CCLM includes first, second, and third modes, a second mode, and a third mode, the regular intra-frame chrominance prediction mode being other intra-frame chrominance prediction modes except CCLM. A first bit of the adjacent bits indicates whether CCLM is used according to whether a value there of is 1. A second bit indicates whether to use the first mode when the first bit indicates to use CCLM. A third bit indicates whether the second or third mode is used when the second bit indicates the first mode is not used. The method further includes using mutually independent probability models to respectively encode the first bit and the second bit.
    Type: Application
    Filed: December 19, 2023
    Publication date: June 13, 2024
    Inventors: Siwei MA, Jiaqi ZHANG, Xiaozhen ZHENG, Shanshe WANG
  • Patent number: 11997312
    Abstract: A video encoding method including obtaining a motion vector candidate list of a current image block; determining a base motion vector according to motion vectors in the motion vector candidate list; in response to the base motion vector pointing to a short-term reference image, scaling a motion vector offset of the base motion vector using a scaling factor to obtain a scaled motion vector offset, and performing prediction for the current image block according to a motion vector determined by the scaled motion vector offset and the base motion vector; and in response to the base motion vector pointing to a long-term reference image, skipping scaling of the motion vector offset, and performing prediction for the current image block according to a motion vector determined by the motion vector offset that is not scaled and the base motion vector.
    Type: Grant
    Filed: November 29, 2021
    Date of Patent: May 28, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma, Weiran Li
  • Patent number: 11997254
    Abstract: A video processing method includes obtaining a historical motion information candidate list, and encoding or decoding a plurality of first image blocks in a first region of a current frame according to the historical motion information candidate list. The historical motion information candidate list is obtained based on motion information of one or more second image blocks each being an encoded or decoded image block in a second region of the current frame outside the first region.
    Type: Grant
    Filed: June 29, 2021
    Date of Patent: May 28, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Shanshe Wang, Tianliang Fu, Siwei Ma
  • Patent number: 11949911
    Abstract: A video processing method includes obtaining motion information of a neighboring block of a current image block, dividing the current image block into a plurality of sub-blocks in response to the neighboring block satisfying a preset condition, determining, in a time-domain reference image of the current image block, related blocks of the plurality of sub-blocks according to a motion vector of the neighboring block, and performing prediction on the current image block according to motion vectors of the related blocks.
    Type: Grant
    Filed: May 23, 2022
    Date of Patent: April 2, 2024
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Xiaozhen Zheng, Suhong Wang, Shanshe Wang, Siwei Ma, Weiran Li