US Patent Issued to Flawless Holdings on Aug. 26 for "Neural network for audio and video dubbing with 3D facial modelling" (British, American Inventors)

ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,400,387, issued on Aug. 26, was assigned to Flawless Holdings Ltd. (London).

"Neural network for audio and video dubbing with 3D facial modelling" was invented by Scott Mann (Sherman Oaks, Calif.), Rob Hall (London) and Hyeongwoo Kim (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method includes obtaining source video data comprising a plurality of image frames, and using a face tracker to detect one or more instances of faces within respective sequences of image frames of the source video data. For a first instance of a given face detected within a first sequence of image frames, the method includes determining a framewis...