US Patent Issued to Adobe on Jan. 27 for "Mask-robust image inpainting utilizing machine-learning models" (Washington, Pennsylvania, California, Illinois Inventors)

ALEXANDRIA, Va., Jan. 28 -- United States Patent no. 12,536,626, issued on Jan. 27, was assigned to Adobe Inc. (San Jose, Calif.).

"Mask-robust image inpainting utilizing machine-learning models" was invented by Sohrab Amirghodsi (Seattle), Lingzhi Zhang (Philadelphia), Connelly Barnes (Seattle), Elya Shechtman (Seattle), Yuqian Zhou (Urbana, Ill.) and Zhe Lin (Fremont, 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 for inpainting digital images utilizing mask-robust machine-learning models. In particular, in one or more embodiments, the disclosed systems obtain an initial mask for an object depicted in a di...