Training and utilizing an image exposure transformation neural network to generate a long-exposure image from a single short-exposure image
US10783622B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 25, 2018 |
| Grant date | Sep 22, 2020 |
| Priority date | — |
| Expiry date | Nov 6, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20201
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short-exposure images without additional information.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.