Jump to content

Adobe inc. (20250117971). VIDEO DIFFUSION USING SUPERPOSITION NETWORK ARCHITECTURE SEARCH

From WikiPatents

VIDEO DIFFUSION USING SUPERPOSITION NETWORK ARCHITECTURE SEARCH

Organization Name

adobe inc.

Inventor(s)

Feng Liu of Beaverton OR US

Zhengang Li of Boston MA US

Yan Kang of Kirkland WA US

Yuchen Liu of Mountain View CA US

Difan Liu of San Jose CA US

Tobias Hinz of Campbell CA US

VIDEO DIFFUSION USING SUPERPOSITION NETWORK ARCHITECTURE SEARCH

This abstract first appeared for US patent application 20250117971 titled 'VIDEO DIFFUSION USING SUPERPOSITION NETWORK ARCHITECTURE SEARCH

Original Abstract Submitted

a method, apparatus, non-transitory computer readable medium, apparatus, and system for video generation include first obtaining a training set including a training video. then, embodiments initialize a video generation model, sample a subnet architecture from an architecture search space, and a identify a subset of the weights of the video generation model based on the sampled subnet architecture. subsequently, embodiments train, based on the training video, a subnet of the video generation model to generate synthetic video data. the subnet includes a subset of the weights of the video generation model.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.