Patent · US Active

Image matting using deep learning

US10255681B2 · kind B2 · utility

12Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 2, 2017
Grant dateApr 9, 2019
Priority date
Expiry dateMay 3, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and systems are provided for generating mattes for input images. A neural network system can be trained where the training includes training a first neural network that generates mattes for input images where the input images are synthetic composite images. Such a neural network system can further be trained where the training includes training a second neural network that generates refined mattes from the mattes produced by the first neural network. Such a trained neural network system can be used to input an image and trimap pair for which the trained system will output a matte. Such a matte can be used to extract an object from the input image. Upon extracting the object, a user can manipulate the object, for example, to composite the object onto a new background.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.