Patent · US Active

Image compression and decoding, video compression and decoding: training methods and training systems

US11881003B2 · kind B2 · utility

1Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 20, 2023
Grant dateJan 23, 2024
Priority date
Expiry dateJan 20, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer-implemented method of training an image generative network fθ for a set of training images, in which an output image {circumflex over (x)} is generated from an input image x of the set of training images non-losslessly, and in which a proxy network is trained for a gradient intractable perceptual metric that evaluates a quality of an output image {circumflex over (x)} given an input image x, the method of training using a plurality of scales for input images from the set of training images. In an embodiment, a blindspot network bα is trained which generates an output image {tilde over (x)} from an input image x. Related computer systems, computer program products and computer-implemented methods of training are disclosed.

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