US Patent Issued to Adobe on June 23 for "Systems and techniques to perform 4D-guided video generation with diffusion models" (British, American Inventors)

ALEXANDRIA, Va., July 15 -- United States Patent no. 12,664,751, issued on June 23, was assigned to Adobe Inc. (San Jose, Calif.).

"Systems and techniques to perform 4D-guided video generation with diffusion models" was invented by Shengqu Cai (Stanford, Calif.), Duygu Ceylan Aksit (London), Matheus Gadelha (San Jose, Calif.), Chun-Hao Huang (San Jose, Calif.) and Yangtuanfeng Wang (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments include systems and techniques for receiving a prompt and an input mesh to generate a four-dimensional (4D) video and generating keyframes from a depth map and a UV coordinate map of the input mesh. Embodiments further include extracting features from the...