Invention Grant
- Patent Title: Hybrid motion-compensated neural network with side-information based video coding
-
Application No.: US16516784Application Date: 2019-07-19
-
Publication No.: US11689726B2Publication Date: 2023-06-27
- Inventor: Debargha Mukherjee , Urvang Joshi , Yue Chen , Sarah Parker
- Applicant: GOOGLE LLC
- Applicant Address: US CA Mountain View
- Assignee: GOOGLE LLC
- Current Assignee: GOOGLE LLC
- Current Assignee Address: US CA Mountain View
- Agency: Young Basile Hanlon & MacFarlane, P.C.
- Main IPC: H04N19/147
- IPC: H04N19/147 ; H04N19/184 ; H04N19/59 ; G06N3/04

Abstract:
A hybrid apparatus for coding a video stream includes a first encoder. The first encoder includes a neural network having at least one hidden layer, and the neural network receives source data from the video stream at a first hidden layer of the at least one hidden layer, receives side information correlated with the source data at the first hidden layer, and generates guided information using the source data and the side information. The first encoder outputs the guided information and the side information for a decoder to reconstruct the source data.
Public/Granted literature
- US20200186809A1 Hybrid Motion-Compensated Neural Network with Side-Information Based Video Coding Public/Granted day:2020-06-11
Information query