Invention Grant
- Patent Title: Frame-recurrent video super-resolution
-
Application No.: US15859992Application Date: 2018-01-02
-
Publication No.: US10783611B2Publication Date: 2020-09-22
- Inventor: Raviteja Vemulapalli , Matthew Brown , Seyed Mohammad Mehdi Sajjadi
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Dority & Manning, PA
- Main IPC: G06T3/40
- IPC: G06T3/40 ; G06T3/00 ; G06T5/50 ; G06T7/246 ; G06N20/00

Abstract:
The present disclosure provides systems and methods to increase resolution of imagery. In one example embodiment, a computer-implemented method includes obtaining a current low-resolution image frame. The method includes obtaining a previous estimated high-resolution image frame, the previous estimated high-resolution frame being a high-resolution estimate of a previous low-resolution image frame. The method includes warping the previous estimated high-resolution image frame based on the current low-resolution image frame. The method includes inputting the warped previous estimated high-resolution image frame and the current low-resolution image frame into a machine-learned frame estimation model. The method includes receiving a current estimated high-resolution image frame as an output of the machine-learned frame estimation model, the current estimated high-resolution image frame being a high-resolution estimate of the current low-resolution image frame.
Public/Granted literature
- US20190206026A1 Frame-Recurrent Video Super-Resolution Public/Granted day:2019-07-04
Information query