Patent · US Active

Multi-scale output techniques for generative adversarial networks

US12333427B2 · kind B2 · utility

1Cited by
27References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 23, 2021
Grant dateJun 17, 2025
Priority date
Expiry dateApr 14, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2210/22
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An improved system architecture uses a Generative Adversarial Network (GAN) including a specialized generator neural network to generate multiple resolution output images. The system produces a latent space representation of an input image. The system generates a first output image at a first resolution by providing the latent space representation of the input image as input to a generator neural network comprising an input layer, an output layer, and a plurality of intermediate layers and taking the first output image from an intermediate layer, of the plurality of intermediate layers of the generator neural network. The system generates a second output image at a second resolution different from the first resolution by providing the latent space representation of the input image as input to the generator neural network and taking the second output image from the output layer of the generator neural network.

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