ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,638, issued on June 17, was assigned to NVIDIA Corporaton (Santa Clara, Calif.).

"Generating images of object motion using one or more neural networks" was invented by Ting-Chun Wang (Santa Clara, Calif.), Tim Brooks (Berkeley, Calif.), Ming-Yu Liu (San Jose, Calif.), Tero Karras (Uusimaa, Finland) and Jaakko Lehtinen (Uusimaa, Finland).

According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses, systems, and techniques are presented to reconstruct one or more images. In at least one embodiment, one or more neural networks are used to generate one or more images of one or more objects based, at least in part, on input indicating motion of the one or m...