ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,841, issued on Jan. 13, was assigned to Disney Enterprises INC. (Burbank, Calif.) and ETH Zurich (Eidgenossische Technische Hochschule Zurich) (Zurich, Switzerland).
"Techniques for processing videos using temporally-consistent transformer model" was invented by Yang Zhang (Dubendorf, Switzerland), Mingyang Song (Zurich), Tunc Ozan Aydin (Zurich) and Christopher Richard Schroers (Uster, Switzerland).
According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are disclosed for enhancing videos using a machine learning model that is a temporally-consistent transformer model. The machine learning model processes blocks of frames of a video in which the te...