Invention Grant
- Patent Title: Joint forward and backward neural network optimization in image processing
-
Application No.: US17800886Application Date: 2021-02-17
-
Publication No.: US12003746B2Publication Date: 2024-06-04
- Inventor: Guan-Ming Su
- Applicant: DOLBY LABORATORIES LICENSING CORPORATION
- Applicant Address: US CA San Francisco
- Assignee: DOLBY LABORATORIES LICENSING CORPORATION
- Current Assignee: DOLBY LABORATORIES LICENSING CORPORATION
- Current Assignee Address: US CA San Francisco
- Priority: EP 158278 2020.02.19
- International Application: PCT/US2021/018407 2021.02.17
- International Announcement: WO2021/168001A 2021.08.26
- Date entered country: 2022-08-18
- Main IPC: H04N19/436
- IPC: H04N19/436 ; H04N19/119 ; H04N19/136 ; H04N19/186

Abstract:
A source color grade and a destination color grade may be received by an end-to-end image mapping pipeline comprising forward and backward paths. Forward neural networks in the forward path may be applied to generate, from the source color grade, a forward reshaped color grade corresponding to the destination color grade. Backward neural networks in the backward path may be applied to generate, from the forward reshaped color grade, a backward reshaped color grade corresponding to the source color grade. An overall neural network cost function may be specified for the forward path and the backward path to generate a cost that may be used as a basis for determining operational parameters for the forward and backward neural networks.
Public/Granted literature
- US20230084705A1 JOINT FORWARD AND BACKWARD NEURAL NETWORK OPTIMIZATION IN IMAGE PROCESSING Public/Granted day:2023-03-16
Information query