ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,541,862, issued on Feb. 3, was assigned to Adobe Inc. (San Jose, Calif.).
"Rendering augmented reality video using filtered point-to-point image matches to compute perspective-n-point camera poses" was invented by Chang Xiao (Sunnyvale, Calif.), Ryan Rossi (Santa Clara, Calif.) and Enyu Cai (West Lafayette, Ind.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects and features of this disclosure relate to providing a hybrid approach for camera pose estimation using a deep learning-based image matcher and a match refinement procedure. The image matcher takes an image pair as an input and estimates coarse point-to-point feature matches between th...