Invention Grant
- Patent Title: Block-wise content-adaptive online training in neural image compression
-
Application No.: US17729978Application Date: 2022-04-26
-
Publication No.: US11889112B2Publication Date: 2024-01-30
- Inventor: Ding Ding , Wei Jiang , Wei Wang , 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: ARENTFOX SCHIFF LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; H04N19/593 ; H04N19/176

Abstract:
Aspects of the disclosure provide a method, an apparatus, and a non-transitory computer-readable storage medium for video decoding. The apparatus can include processing circuitry. The processing circuitry is configured to decode first neural network update information in a coded bitstream for a first neural network in the video decoder. The first neural network is configured with first pretrained parameters. The first neural network update information corresponds to a first block in an image to be reconstructed and indicates a first replacement parameter corresponding to a first pretrained parameter in the first pretrained parameters. The processing circuitry is configured to update the first neural network in the video decoder based on the first replacement parameter. The processing circuitry can decode the first block based on the updated first neural network for the first block.
Public/Granted literature
- US20220353528A1 BLOCK-WISE CONTENT-ADAPTIVE ONLINE TRAINING IN NEURAL IMAGE COMPRESSION Public/Granted day:2022-11-03
Information query