Patent · US Active

Video inpainting with deep internal learning

US11055828B2 · kind B2 · utility

4Cited by
0References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 9, 2019
Grant dateJul 6, 2021
Priority date
Expiry dateOct 14, 2039

Classification

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

Abstract

Techniques of inpainting video content include training a neural network to perform an inpainting operation on a video using only content from that video. For example, upon receiving video content including a sequence of initial frames, a computer generates a sequence of inputs corresponding to at least some of the sequence of initial frames and each input including, for example, a uniform noise map. The computer then generates a convolutional neural network (CNN) using the sequence of input as the initial layer. The parameters of the CNN are adjusted according to a cost function, which has components including a flow generation loss component and a consistency loss component. The CNN then outputs, on a final layer, estimated image values in a sequence of final frames.

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