利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

4 条记录 (耗时 0.007 秒)

    IMPROVED ENTROPY CODING IN IMAGE AND VIDEO DECOMPRESSION USING MACHINE LEARNING
    3.
    发明公开
    IMPROVED ENTROPY CODING IN IMAGE AND VIDEO DECOMPRESSION USING MACHINE LEARNING 审中-实审

    公开(公告)号：EP4436176A2

    公开(公告)日：2024-09-25

    申请号：EP24182040.6

    申请日：2019-10-31

    申请人： GOOGLE LLC

    发明人： BOKOV, Alexander ,  SU, Hui

    IPC分类号： H04N19/593

    CPC分类号： H04N19/13 ,  H04N19/14 ,  H04N19/157 ,  H04N19/176 ,  H04N19/194 ,  H04N19/11 ,  H04N19/593

    摘要： Machine learning is used to refine a probability distribution for entropy coding video or image data. A probability distribution is determined for symbols associated with a video block (e.g., quantized transform coefficients, such as during encoding, or syntax elements from a bitstream, such as during decoding), and a set of features is extracted from video data associated with the video block and/or neighbor blocks. The probability distribution and the set of features are then processed using machine learning to produce a refined probability distribution. The video data associated with a video block are entropy coded according to the refined probability distribution. Using machine learning to refine the probability distribution for entropy coding minimizes the cross-entropy loss between the symbols to entropy code and the refined probability distribution.

    IMPROVED ENTROPY CODING IN IMAGE AND VIDEO DECOMPRESSION USING MACHINE LEARNING
    4.
    发明公开
    IMPROVED ENTROPY CODING IN IMAGE AND VIDEO DECOMPRESSION USING MACHINE LEARNING 审中-公开

    公开(公告)号：EP4436176A3

    公开(公告)日：2024-10-23

    申请号：EP24182040.6

    申请日：2019-10-31

    申请人： GOOGLE LLC

    发明人： BOKOV, Alexander ,  SU, Hui

    IPC分类号： H04N19/11 ,  H04N19/13 ,  H04N19/14 ,  H04N19/157 ,  H04N19/176 ,  H04N19/194 ,  H04N19/593

    摘要： Machine learning is used to refine a probability distribution for entropy coding video or image data. A probability distribution is determined for symbols associated with a video block (e.g., quantized transform coefficients, such as during encoding, or syntax elements from a bitstream, such as during decoding), and a set of features is extracted from video data associated with the video block and/or neighbor blocks. The probability distribution and the set of features are then processed using machine learning to produce a refined probability distribution. The video data associated with a video block are entropy coded according to the refined probability distribution. Using machine learning to refine the probability distribution for entropy coding minimizes the cross-entropy loss between the symbols to entropy code and the refined probability distribution.