US Patent Issued to NVIDIA on March 3 for "Image synthesis using diffusion models created from single or multiple view images" (Finnish, American Inventors)

ALEXANDRIA, Va., March 3 -- United States Patent no. 12,567,197, issued on March 3, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Image synthesis using diffusion models created from single or multiple view images" was invented by Koki Nagano (Playa Vista, Calif.), Eric Ryan Wong Chan (Alameda, Calif.), Tero Tapani Karras (Helsinki), Shalini De Mello (San Francisco), Miika Samuli Aittala (Helsinki) and Matthew Aaron Wong Chan (Los Altos, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and system for performing novel image synthesis using generative networks are provided. The encoder-based model is trained to infer a 3D representation of an input image. A feature image is then generated u...