Skip to content

CAT4D

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

How it works

Given an input monocular video, we generate multi-view videos at novel viewpoints using our multi-view video diffusion model. These generated videos are then used to reconstruct the dynamic 3D scene as deforming 3D Gaussians.

Howitworks_cat4d.gif

See also

Favorite site