公开(公告)号：US20230336739A1

公开(公告)日：2023-10-19

申请号：US18030182

申请日：2021-11-03

申请人： DeepMind Technologies Limited

发明人： Chenjie Gu ,  Hongzi Mao ,  Ching-Han Chiang ,  Cheng Chen ,  Jingning Han ,  Ching Yin Derek Pang ,  Rene Andre Claus ,  Marisabel Guevara Hechtman ,  Daniel James Visentin ,  Christopher Sigurd Fougner ,  Charles Booth Schaff ,  Nishant Patil ,  Alejandro Ramirez Bellido

IPC分类号： H04N19/149 ,  H04N19/126 ,  H04N19/172

CPC分类号： H04N19/149 ,  H04N19/126 ,  H04N19/172

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for encoding video comprising a sequence of video frames. In one aspect, a method comprises for one or more of the video frames: obtaining a feature embedding for the video frame; processing the feature embedding using a rate control machine learning model to generate a respective score for each of multiple quantization parameter values; selecting a quantization parameter value using the scores; determining a cumulative amount of data required to represent: (i) an encoded representation of the video frame and (ii) encoded representations of each preceding video frame; determining, based on the cumulative amount of data, that a feedback control criterion for the video frame is satisfied; updating the selected quantization parameter value; and processing the video frame using an encoding model to generate the encoded representation of the video frame.

公开(公告)号：US12088823B2

公开(公告)日：2024-09-10

申请号：US18030182

申请日：2021-11-03

申请人： DeepMind Technologies Limited

发明人： Chenjie Gu ,  Hongzi Mao ,  Ching-Han Chiang ,  Cheng Chen ,  Jingning Han ,  Ching Yin Derek Pang ,  Rene Andre Claus ,  Marisabel Guevara Hechtman ,  Daniel James Visentin ,  Christopher Sigurd Fougner ,  Charles Booth Schaff ,  Nishant Patil ,  Alejandro Ramirez Bellido

IPC分类号： H04N7/12 ,  H04N19/126 ,  H04N19/149 ,  H04N19/172

CPC分类号： H04N19/149 ,  H04N19/126 ,  H04N19/172

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for encoding video comprising a sequence of video frames. In one aspect, a method comprises for one or more of the video frames: obtaining a feature embedding for the video frame; processing the feature embedding using a rate control machine learning model to generate a respective score for each of multiple quantization parameter values; selecting a quantization parameter value using the scores; determining a cumulative amount of data required to represent: (i) an encoded representation of the video frame and (ii) encoded representations of each preceding video frame; determining, based on the cumulative amount of data, that a feedback control criterion for the video frame is satisfied; updating the selected quantization parameter value; and processing the video frame using an encoding model to generate the encoded representation of the video frame.