US Patent Issued to Google on Aug. 18 for "Systems and methods for training models to predict dense correspondences in images using geodesic distances" (American, Chinese, Swiss Inventors)

ALEXANDRIA, Va., Aug. 18 -- United States Patent no. 12,711,742, issued on Aug. 18, was assigned to Google LLC (Mountain View, Calif.).

"Systems and methods for training models to predict dense correspondences in images using geodesic distances" was invented by Yinda Zhang (Daly City, Calif.), Feitong Tan (Beijing), Danhang Tang (West Hollywood, Calif.), Mingsong Dou (Cupertino, Calif.), Kaiwen Guo (Zurich), Sean Ryan Francesco Fanello (San Francisco), Sofien Bouaziz (Los Gatos, Calif.), Cem Keskin (San Francisco), Ruofei Du (San Francisco), Rohit Kumar Pandey (Mountain View, Calif.) and Deqing Sun (Cambridge, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for training models to pre...