ALEXANDRIA, Va., July 9 -- United States Patent no. 12,354,337, issued on July 8, was assigned to Amazon Technologies Inc. (Seattle).

"Image generation based on a multi-image set and pose data" was invented by Amin Kheradmand (Mountain View, Calif.), Jiayun Wang (Berkeley, Calif.) and Himanshu Arora (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for image generation based on a multi-image set and pose data is described herein. In an example, a computer system generates, by at least using a first machine learning (ML) model, a pose feature based on pose data that indicates a target pose. The computer system generates, by at least using a second ML model, a first appearance featur...