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. See our project page for results and interactive demos at https://cat3d.github.io .
@article{arxiv.2405.10314,
title = {CAT3D: Create Anything in 3D with Multi-View Diffusion Models},
author = {Ruiqi Gao and Aleksander Holynski and Philipp Henzler and Arthur Brussee and Ricardo Martin-Brualla and Pratul Srinivasan and Jonathan T. Barron and Ben Poole},
journal= {arXiv preprint arXiv:2405.10314},
year = {2024}
}