US Patent Issued to Nvidia on May 13 for "Diffusion-based generative modeling for synthetic data generation systems and applications" (Canadian, American Inventors)

ALEXANDRIA, Va., June 12 -- United States Patent no. 12,299,962, issued on May 13, was assigned to Nvidia Corp. (Santa Clara, Calif.).

"Diffusion-based generative modeling for synthetic data generation systems and applications" was invented by Karsten Kreis (Vancouver, Canada), Tim Dockhorn (Waterloo, Canada) and Arash Vahdat (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods described relate to the synthesis of content using generative models. In at least one embodiment, a score-based generative model can use a stochastic differential equation with critically-damped Langevin diffusion to learn to synthesize content. During a forward diffusion process, noise can be intr...