Skip to yearly menu bar Skip to main content


Oral Poster

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

Ruiqi Gao · Aleksander Holynski · Philipp Henzler · Arthur Brussee · Ricardo Martin Brualla · Pratul Srinivasan · Jonathan Barron · Ben Poole

East Exhibit Hall A-C #1610
[ ]
Thu 12 Dec 4:30 p.m. PST — 7:30 p.m. PST
 
Oral presentation: Oral Session 4B: Diffusion-based Models
Thu 12 Dec 3:30 p.m. PST — 4:30 p.m. PST

Abstract:

Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world capture process with a multi-view diffusion model. Given any number of input images and a set of target novel viewpoints, our model generates highly consistent novel views of a scene. These generated views can be used as input to robust 3D reconstruction techniques to produce 3D representations that can be rendered from any viewpoint in real-time. CAT3D can create entire 3D scenes in as little as one minute, and outperforms existing methods for single image and few-view 3D scene creation.

Live content is unavailable. Log in and register to view live content