Deepmind Technologies Limited

Daniel James Visentin

Nishant P Patil

Chenjie Gu

Ching Yin Derek Pang

Christopher Sigurd Fougner

Cheng Chen

Charles Booth Schaff

Alejandro Ramirez Bellido

Jingning Han

Ching-Han Chiang

Rene Andre Claus

Hongzi Mao

Marisabel Guevara Hechtman

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.

Rate control machine learning models with feedback control for video encoding

Growing community of inventors

London, United Kingdom

Daniel James Visentin