US Patent Issued to Adobe on Feb. 11 for "Harmonizing composite images utilizing a semantic-guided transformer neural network" (California Inventors)

ALEXANDRIA, Va., Feb. 12 -- United States Patent no. 12,223,623, issued on Feb. 11, was assigned to Adobe Inc. (San Jose, Calif.).

"Harmonizing composite images utilizing a semantic-guided transformer neural network" was invented by He Zhang (San Jose, Calif.) and Hyun Joon Jung (Monte Sereno, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a multi-branch harmonization neural network architecture to harmonize composite images. For example, in one or more implementations, the semantic-guided transformer-based harmonization system uses a convolutional branch, a transformer branch, and a semantic ...