US Patent Issued to Adobe on July 1 for "Generating gesture reenactment video from video motion graphs using machine learning" (California, Washington Inventors)

ALEXANDRIA, Va., July 3 -- United States Patent no. 12,347,135, issued on July 1, was assigned to Adobe Inc. (San Jose, Calif.).

"Generating gesture reenactment video from video motion graphs using machine learning" was invented by Yang Zhou (Sunnyvale, Calif.), Jimei Yang (Mountain View, Calif.), Jun Saito (Seattle), Dingzeyu Li (Seattle) and Deepali Aneja (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments are disclosed for generating a gesture reenactment video sequence corresponding to a target audio sequence using a trained network based on a video motion graph generated from a reference speech video. In particular, in one or more embodiments, the disclosed systems and methods comprise r...