18894443. VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS (ADOBE INC.)
VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS
Organization Name
Inventor(s)
Seoung Wug Oh of San Jose CA US
Joon-Young Lee of San Jose CA US
Yang Zhou of Mountain View CA US
Haoran Cai of Mercer Island WA US
VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS
This abstract first appeared for US patent application 18894443 titled 'VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS
Original Abstract Submitted
A method, apparatus, non-transitory computer readable medium, and system for generating synthetic videos includes obtaining an input prompt describing a video scene. The embodiments then generate a plurality of frame-wise token embeddings corresponding to a sequence of video frames, respectively, based on the input prompt. Subsequently, embodiments generate, using a video generation model, a synthesized video depicting the video scene. The synthesized includes a plurality of images corresponding to the sequence of video frames.