ALEXANDRIA, Va., June 6 -- United States Patent no. 12,282,696, issued on April 22, was assigned to Yeda Research and Development Co. Ltd. (Rehovot, Israel).

"Method and system for semantic appearance transfer using splicing ViT features" was invented by Tali Dekel (Rehovot, Israel), Shai Bagon (Rehovot, Israel), Omer Bar Tal (Rehovot, Israel) and Narek Tumanyan (Rehovot, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "Using a pre-trained and fixed Vision Transformer (ViT) model as an external semantic prior, a generator is trained given only a single structure/appearance image pair as input. Given two input images, a source structure image and a target appearance image, a new image is generated by the...