中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1338 records (took 0.039 seconds)

    METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING
    11.
    发明申请
    METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING 有权

    公开(公告)号：US20250047891A1

    公开(公告)日：2025-02-06

    申请号：US18905949

    申请日：2024-10-03

    Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

    Inventor： Zhipin DENG ,  Kai Zhang ,  Li Zhang

    IPC: H04N19/513 ,  H04N19/105 ,  H04N19/176

    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a current video block of a video and a bitstream of the video, a first motion vector (MV) for a target video block, the target video block being determined by applying a sample adjusting process to a plurality of samples of the current video block; adjusting the first MV based on a second MV generated for the target video block; and performing the conversion based on the adjusted first MV.

    Techniques for modifying quantization parameter in transform skip mode
    13.
    发明授权
    Techniques for modifying quantization parameter in transform skip mode 有权

    公开(公告)号：US12206850B2

    公开(公告)日：2025-01-21

    申请号：US17944876

    申请日：2022-09-14

    Applicant: Bytedance Inc.

    Inventor： Weijia Zhu ,  Li Zhang ,  Jizheng Xu

    IPC: H04N19/124 ,  H04N19/159 ,  H04N19/176 ,  H04N19/70

    Abstract: A method of video processing is described. The method includes performing a conversion between a current video block of a video and a coded representation of the current video block according to a rule, wherein the rule specifies that, due to use of an identity transform coding tool for representing the current video block into the coded representation, a syntax field indicative of a quantization parameter used for decoding the current video block is included such that a value of the quantization parameter is modified according to a rule, wherein the identity transform coding tool allows coefficient values at a transform domain of the current block to be same as values of a residual block of the current video block.

    Matrix derivation in intra coding mode
    17.
    发明授权
    Matrix derivation in intra coding mode 有权

    公开(公告)号：US12166968B2

    公开(公告)日：2024-12-10

    申请号：US17895511

    申请日：2022-08-25

    Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

    Inventor： Zhipin Deng ,  Kai Zhang ,  Li Zhang ,  Hongbin Liu ,  Jizheng Xu

    IPC: H04N19/132 ,  H04N19/105 ,  H04N19/159 ,  H04N19/176 ,  H04N19/70

    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.

    Image/video super resolution
    20.
    发明授权
    Image/video super resolution 有权

    公开(公告)号：US12136188B2

    公开(公告)日：2024-11-05

    申请号：US17453968

    申请日：2021-11-08

    Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  ByteDance Inc.

    Inventor： Meng Wang ,  Jizheng Xu ,  Li Zhang ,  Shiqi Wang

    IPC: G06T3/4076 ,  G06T3/4046

    Abstract: Embodiments of the present disclosure provide a solution for image/video super resolution. A method for image processing is proposed. The method comprises: receiving a first image with a first resolution and at least one reference image associated with the first image, the first image and the at least one reference image being associated with a same video; determining a difference between the first image and the at least one reference image; and generating a second image with a second resolution based on the difference, the first image and the at least one reference image, the second resolution being higher than the first resolution.

Patent Agency Ranking