Patent · US Active

Image composites using a generative adversarial neural network

US10719742B2 · kind B2 · utility

17Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 15, 2018
Grant dateJul 21, 2020
Priority date
Expiry dateOct 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.