US Patent Issued to NVIDIA on Feb. 17 for "3D model generation using multimodal generative AI" (Canadian, British Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,555,343, issued on Feb. 17, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"3D model generation using multimodal generative AI" was invented by Cheng Xie (Toronto), Jonathan Lorraine (Toronto), Xiaohui Zeng (Toronto), James Lucas (Royston, Great Britain), Jun Gao (Toronto) and Sanja Fidler (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples, systems and methods are disclosed relating to generating an output 3D latent representation by encoding, using a text encoder, a text prompt and encoding, using a 2D/3D encoder, a 2D image of an object or a 3D representation of the object. A 3D output is generated by applying the output ...