Image composites using a generative adversarial neural network
US10719742B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 15, 2018 |
| Grant date | Jul 21, 2020 |
| Priority date | — |
| Expiry date | Oct 13, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19173
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.