公开(公告)号：US11405626B2

公开(公告)日：2022-08-02

申请号：US17091570

申请日：2020-11-06

Applicant: QUALCOMM Incorporated

Inventor： Adam Waldemar Golinski ,  Yang Yang ,  Reza Pourreza ,  Guillaume Konrad Sautiere ,  Ties Jehan Van Rozendaal ,  Taco Sebastiaan Cohen

IPC: H04N19/42 ,  H04N19/137 ,  G06N3/08 ,  H04N19/85 ,  H04N19/172

Abstract: Techniques are described herein for coding video content using recurrent-based machine learning tools. A device can include a neural network system including encoder and decoder portions. The encoder portion can generate output data for the current time step of operation of the neural network system based on an input video frame for a current time step of operation of the neural network system, reconstructed motion estimation data from a previous time step of operation, reconstructed residual data from the previous time step of operation, and recurrent state data from at least one recurrent layer of a decoder portion of the neural network system from the previous time step of operation. A decoder portion of the neural network system can generate, based on the output data and recurrent state data from the previous time step of operation, a reconstructed video frame for the current time step of operation.