知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.016 seconds)

    GROUP OF PICTURES SIZE DETERMINATION METHOD AND ELECTRONIC DEVICE
    1.
    发明公开
    GROUP OF PICTURES SIZE DETERMINATION METHOD AND ELECTRONIC DEVICE 审中-公开

    公开(公告)号：US20240298001A1

    公开(公告)日：2024-09-05

    申请号：US18590220

    申请日：2024-02-28

    Applicant: Alibaba (China) Co., Ltd.

    Inventor： Shengyang XU ,  Jianhua CHEN ,  Yan YE

    IPC: H04N19/137 ,  H04N19/122 ,  H04N19/177

    CPC classification number: H04N19/137 ,  H04N19/122 ,  H04N19/177

    Abstract: Embodiments of the present disclosure provide a method, an electronic device and a computer storage medium for determining the size of group of pictures. The method includes: determining a plurality of candidate sizes; computing motion complexity of picture sets corresponding to the plurality of candidate sizes; and performing preset operation based on the motion complexity of each of the picture sets, and selecting a target size from the plurality of candidate sizes as the GOP size according to the operation result, the GOP including continuous to-be-encoded picture frames in the picture set corresponding to the target size.

    MOTION COMPENSATION METHOD, APPARATUS, AND STORAGE MEDIUM
    3.
    发明公开
    MOTION COMPENSATION METHOD, APPARATUS, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：US20240333939A1

    公开(公告)日：2024-10-03

    申请号：US18616964

    申请日：2024-03-26

    Applicant: Alibaba (China) Co., Ltd.

    Inventor： Shuqing Fang ,  Jianhua Chen ,  Yan YE

    IPC: H04N19/139 ,  H04N19/156 ,  H04N19/176 ,  H04N19/182 ,  H04N19/48

    CPC classification number: H04N19/139 ,  H04N19/156 ,  H04N19/176 ,  H04N19/182 ,  H04N19/48

    Abstract: A motion compensation method, includes: acquiring a plurality of matching costs between a to-be-processed block and a plurality of first pixel blocks, the plurality of first pixel blocks corresponding to a plurality of integer pixels within a search range in a reference frame; based on the plurality of matching costs, estimating matching costs between the to-be-processed block and a plurality of second pixel blocks to obtain a plurality of approximate matching costs, the plurality of second pixel blocks corresponding to a plurality of sub-pixels within the search range in the reference frame; and performing motion compensation on the to-be-processed block according to the plurality of matching costs and the plurality of approximate matching costs.

    CROSS COMPONENT PREDICTION
    5.
    发明申请
    CROSS COMPONENT PREDICTION 有权

    公开(公告)号：US20250008108A1

    公开(公告)日：2025-01-02

    申请号：US18750267

    申请日：2024-06-21

    Applicant: Alibaba (China) Co., Ltd.

    Inventor： Xinwei LI ,  Jie CHEN ,  Yan YE ,  Ru-ling LIAO

    IPC: H04N19/132 ,  H04N19/176 ,  H04N19/186

    Abstract: Methods for encoding a video sequence into a bitstream and decoding a bitstream to output one or more pictures for a video stream. An exemplary method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream associated with the encoded pictures, wherein the encoding comprises: predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs).

    SYSTEMS AND METHODS FOR INTER PREDICTION COMPENSATION
    7.
    发明申请
    SYSTEMS AND METHODS FOR INTER PREDICTION COMPENSATION 有权

    公开(公告)号：US20220272323A1

    公开(公告)日：2022-08-25

    申请号：US17651639

    申请日：2022-02-18

    Applicant: Alibaba (China) Co., Ltd.

    Inventor： Xinwei LI ,  Jie CHEN ,  Ru-Ling LIAO ,  Yan YE

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

    Abstract: A video processing method includes: determining whether an inter predictor correction is enabled for a coding block; and when the inter predictor correction is enabled for the coding block, performing the inter predictor correction by: obtaining a plurality of predicted samples from a top boundary and a left boundary of a predicted block corresponding to the coding block; obtaining a plurality of reconstructed samples from top neighboring reconstructed samples and left neighboring reconstructed samples of the coding block; and deriving a corrected predicted block based on the plurality of the predicted samples, the plurality of the reconstructed samples and the predicted block.

    LIGHTWEIGHT SPATIAL UPSAMPLING METHODS FOR MACHINE VISION
    9.
    发明申请
    LIGHTWEIGHT SPATIAL UPSAMPLING METHODS FOR MACHINE VISION 有权

    公开(公告)号：US20250008131A1

    公开(公告)日：2025-01-02

    申请号：US18748659

    申请日：2024-06-20

    Applicant: Alibaba (China) Co., Ltd.

    Inventor： Shurun WANG ,  Yan YE

    IPC: H04N19/33 ,  H04N19/124 ,  H04N19/172

    Abstract: The present disclosure provides spatial upsampling models used for processing video data suitable for machine vision tasks. An exemplary decoding method includes: receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures, wherein the decoding includes: generating one or more decompressed pictures by decompressing one or more compressed pictures included in the bitstream; and performing spatial upsampling on the one or more decompressed pictures by a spatial upsampling model to obtain one or more reconstructed pictures, respectively, wherein a total length of coding bits of parameters of the spatial upsampling model is less than a threshold that is pre-determined based on a desired quality of the reconstructed pictures.

Patent Agency Ranking