ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,538, issued on Dec. 2, was assigned to Nvidia Corp. (Santa Clara, Calif.).

"Using machine learning for surface reconstruction in synthetic content generation systems and applications" was invented by Jiahui Huang (Beijing), Francis Williams (Brooklyn, N.Y.), Zan Gojcic (Zurich), Matan Atzmon (Toronto), Or Litany (Sunnyvale, Calif.) and Sanja Fidler (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "Approaches presented herein provide for the reconstruction of implicit multi-dimensional shapes. In one embodiment, oriented point cloud data representative of an object can be obtained using a physical scanning process. The point cloud data can be pr...