Patent · US Active

Denoising diffusion generative adversarial networks

US12333688B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 30, 2022
Grant dateJun 17, 2025
Priority date
Expiry dateNov 6, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20182
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Apparatuses, systems, and techniques are presented to train and utilize one or more neural networks. A denoising diffusion generative adversarial network (denoising diffusion GAN) reduces a number of denoising steps during a reverse process. The denoising diffusion GAN does not assume a Gaussian distribution for large steps of the denoising process and applies a multi-model model to permit denoising with fewer steps. Systems and methods further minimize a divergence between a diffused real data distribution and a diffused generator distribution over several timesteps. Accordingly, various embodiments may enable faster sample generation, in which the samples are generated from noise using the denoising diffusion GAN.

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