ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,494,013, issued on Dec. 9, was assigned to Snap Inc. (Santa Monica, Calif.).
"Autodecoding latent 3D diffusion models" was invented by Evangelos Ntavelis (Los Angeles), Kyle Olszewski (Los Angeles), Aliaksandr Siarohin (Los Angeles) and Sergey Tulyakov (Santa Monica, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for generating static and articulated 3D assets are provided that include a 3D autodecoder at their core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. ...