Diverse image inpainting using contrastive learning
US12272031B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 21, 2022 |
| Grant date | Apr 8, 2025 |
| Priority date | — |
| Expiry date | May 16, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An image inpainting system is described that receives an input image that includes a masked region. From the input image, the image inpainting system generates a synthesized image that depicts an object in the masked region by selecting a first code that represents a known factor characterizing a visual appearance of the object and a second code that represents an unknown factor characterizing the visual appearance of the object apart from the known factor in latent space. The input image, the first code, and the second code are provided as input to a generative adversarial network that is trained to generate the synthesized image using contrastive losses. Different synthesized images are generated from the same input image using different combinations of first and second codes, and the synthesized images are output for display.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.