US Patent Issued to ADOBE on Oct. 7 for "Generation using depth-conditioned autoencoder" (California, Washington, Massachusetts Inventors)

ALEXANDRIA, Va., Oct. 8 -- United States Patent no. 12,437,427, issued on Oct. 7, was assigned to ADOBE INC. (San Jose, Calif.).

"Generation using depth-conditioned autoencoder" was invented by Taesung Park (San Francisco), Sylvain Paris (Jamaica Plain, Mass.), Richard Zhang (San Francisco) and Elya Shechtman (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "An image processing system uses a depth-conditioned autoencoder to generate a modified image from an input image such that the modified image maintains an overall structure from the input image while modifying textural features. An encoder of the depth-conditioned autoencoder extracts a structure latent code from an input image and depth informatio...