ALEXANDRIA, Va., April 9 -- United States Patent no. 12,271,975, issued on April 8, was assigned to Sony Interactive Entertainment Inc. (Tokyo).

"Training a machine learning model for reconstructing occluded regions of a face" was invented by Rathish Krishnan (San Mateo, Calif.), Deepali Arya (San Mateo, Calif.), Manoj Srivastava (San Mateo, Calif.) and Seema Kataria (San Mateo, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A machine learning (ML) model is trained using pairs of images. Each pair includes an image of a human face and a duplicate of the image with a computer game headset overlaid on the face using computer graphics. The ML model subsequently can be used to receive an image of a gamer ...