US Patent Issued to NVIDIA on Feb. 10 for "Techniques for training a machine learning model to reconstruct different three-dimensional scenes" (California, Massachusetts Inventors)

ALEXANDRIA, Va., Feb. 11 -- United States Patent no. 12,548,258, issued on Feb. 10, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Techniques for training a machine learning model to reconstruct different three-dimensional scenes" was invented by Yang Fu (San Diego), Sifei Liu (San Diego), Jan Kautz (Lexington, Mass.), Xueting Li (Santa Clara, Calif.), Shalini De Mello (San Francisco), Amey Kulkarni (San Jose, Calif.) and Milind Naphade (Cupertino, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various embodiments, a training application trains a machine learning model to generate three-dimensional (3D) representations of two-dimensional images. The training application maps a depth image and...