Invention Grant
- Patent Title: Multi-model selection for neural network based tools in video coding
-
Application No.: US17368069Application Date: 2021-07-06
-
Publication No.: US11582453B2Publication Date: 2023-02-14
- Inventor: Zeqiang Li , Wei Wang , Xiaozhong Xu , Wei Jiang , Shan Liu
- Applicant: TENCENT AMERICA LLC
- Applicant Address: US CA Palo Alto
- Assignee: TENCENT AMERICA LLC
- Current Assignee: TENCENT AMERICA LLC
- Current Assignee Address: US CA Palo Alto
- Agency: Sughrue Mion, PLLC
- Main IPC: H04N19/124
- IPC: H04N19/124 ; H04N19/105 ; G06N3/04 ; H04N19/159

Abstract:
A method, computer program, and computer system is provided for video encoding and decoding. Video data including one or more frames is received. One or more quantization parameters associated with the received video data are determined for frame generation or enhancement of a target frame from among the one or more frames. The video data is decoded based on the determined quantization parameters.
Public/Granted literature
- US20220224900A1 MULTI-MODEL SELECTION FOR NEURAL NETWORK BASED TOOLS IN VIDEO CODING Public/Granted day:2022-07-14
Information query