ALEXANDRIA, Va., May 19 -- United States Patent no. 12,633,003, issued on May 19, was assigned to NEC Corp. (Tokyo).

"Video generation with latent diffusion probabilistic models" was invented by Renqiang Min (Princeton, N.J.), Kai Li (Plainsboro, N.J.), Hans Peter Graf (South Amboy, N.J.) and Haomiao Ni (State College, Pa.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems for training a model include training an encoder in an unsupervised fashion based on a backward latent flow between a reference frame and a driving frame taken from a same video. A diffusion model is trained that generates a video sequence responsive to an input image and a text condition, using the trained encoder to deter...