ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,688, issued on June 17, was assigned to Nvidia Corp. (Santa Clara, Calif.).
"Denoising diffusion generative adversarial networks" was invented by Zhisheng Xiao (Chicago), Karsten Kreis (Vancouver, Canada) and Arash Vahdat (Mountain View, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "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 ...