Invention Grant
- Patent Title: Systems and methods for machine learned image conversion
-
Application No.: US16830032Application Date: 2020-03-25
-
Publication No.: US11379951B2Publication Date: 2022-07-05
- Inventor: Alexandre Delattre , Théo Charvet , Raphaël Poncet
- Applicant: NINTENDO CO., LTD.
- Applicant Address: JP Kyoto
- Assignee: NINTENDO CO., LTD.
- Current Assignee: NINTENDO CO., LTD.
- Current Assignee Address: JP Kyoto
- Agency: Nixon & Vanderhye P.C.
- Main IPC: G06T3/40
- IPC: G06T3/40 ; G06F17/16 ; G06N3/04 ; A63F13/53 ; G06T1/20 ; G06N3/08

Abstract:
A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
Public/Granted literature
- US20210304356A1 SYSTEMS AND METHODS FOR MACHINE LEARNED IMAGE CONVERSION Public/Granted day:2021-09-30
Information query