公开(公告)号：US20240195985A1

公开(公告)日：2024-06-13

申请号：US18286574

申请日：2021-05-07

申请人： Google LLC

发明人： David Charles Minnen ,  Sung Jin Hwang ,  Elliott Michael Karpilovsky ,  Debargha Mukherjee

IPC分类号： H04N19/176 ,  H04N19/119 ,  H04N19/159

CPC分类号： H04N19/176 ,  H04N19/119 ,  H04N19/159

摘要： Methods, systems, and apparatus, including computer programs, for compression and decompression of video data using an ensemble of machine learning models. Methods can include defining for each frame in a video, a plurality of blocks in the frame. Methods can further include processing the frames of video in sequential sets, wherein each sequential set is at least a current frame (220) of video and a prior frame (240) of video in the ordered sequence. Each respective prediction of a block in the frame of the video includes providing, as input to a prediction model a first and the second border (235,230) of a current block (225) of the current frame, a first and a second border (250, 255) for a respective current block (245) of the prior frame and the respective current block (245) of the prior frame.