ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,430,851, issued on Sept. 30, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Synthesizing high resolution 3D shapes from lower resolution representations for synthetic data generation systems and applications" was invented by Tianchang Shen (Markham, Calif.), Jun Gao (Toronto), Kangxue Yin (Toronto), Ming-Yu Liu (San Jose, Calif.) and Sanja Fidler (Toronto).
According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high resolution 3D shapes using simple guides-such as coarse voxels, point clouds, etc.-by marrying implicit and explicit 3D represent...