ALEXANDRIA, Va., June 12 -- United States Patent no. 12,299,896, issued on May 13, was assigned to Amazon Technologies Inc. (Seattle).

"Synthetic image generation by manifold modification of a machine learning model" was invented by Qianli Feng (Seattle), Raghu Deep Gadde (Bothell, Wash.), Pietro Perona (Altadena, Calif.) and Aleix Margarit Martinez (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Described herein is a computer-implemented method for generating a synthetic image. An input image can be received by a computing device. A representation of the input image on an image approximation manifold can be identified by inputting the input image into a machine learning model. The image approximatio...