ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,749,287, issued on Sept. 29, was assigned to Amazon Technologies Inc. (Seattle).
"Machine learning systems for generating representations based on multiple images of an object" was invented by George Leotescu (Bucharest, Romania), Alin-Ionut Popa (Bucharest, Romania), Daniel Voinea (Vladiceasca, Romania), Mingwei Shen (Shoreline, Wash.) and Pietro Perona (Altadena, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A single latent representation is generated based on multiple images of an item using an iterative process that sequentially updates the latent representation as each image is processed. A first image is encoded and used to initialize a f...