US Patent Issued to ADOBE on Sept. 22 for "Discovering and mitigating biases in large pre-trained multimodal based image editing" (California Inventors)

ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,818, issued on Sept. 22, was assigned to ADOBE INC. (San Jose, Calif.).

"Discovering and mitigating biases in large pre-trained multimodal based image editing" was invented by Md Mehrab Tanjim (Santa Clara, Calif.), Krishna Kumar Singh (San Jose, Calif.), Kushal Kafle (Sunnyvale, Calif.) and Ritwik Sinha (Cupertino, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method, apparatus, non-transitory computer readable medium, apparatus, and system for image processing include obtaining a text prompt and an input image depicting a person, generating a latent code based on the text prompt and the input image, wherein the latent code is optimized ...