US Patent Issued to Adobe on March 24 for "Generative model for multi-modality outputs from a single input" (Washington, California, Illinois Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,344, issued on March 24, was assigned to Adobe Inc. (San Jose, Calif.).

"Generative model for multi-modality outputs from a single input" was invented by Yijun Li (Seattle), Zhixin Shu (San Jose, Calif.), Zhen Zhu (Urbana, Ill.) and Krishna Kumar Singh (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "An image generation system implements a multi-branch GAN to generate images that each express visually similar content in a different modality. A generator portion of the multi-branch GAN includes multiple branches that are each tasked with generating one of the different modalities. A discriminator portion of the multi-branch GAN inclu...