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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Ruiqi, Holynski, Aleksander, Henzler, Philipp, Brussee, Arthur, Martin-Brualla, Ricardo, Srinivasan, Pratul, Barron, Jonathan T., Poole, Ben
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910449887346688
author Gao, Ruiqi
Holynski, Aleksander
Henzler, Philipp
Brussee, Arthur
Martin-Brualla, Ricardo
Srinivasan, Pratul
Barron, Jonathan T.
Poole, Ben
author_facet Gao, Ruiqi
Holynski, Aleksander
Henzler, Philipp
Brussee, Arthur
Martin-Brualla, Ricardo
Srinivasan, Pratul
Barron, Jonathan T.
Poole, Ben
contents 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 .
format Preprint
id arxiv_https___arxiv_org_abs_2405_10314
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CAT3D: Create Anything in 3D with Multi-View Diffusion Models
Gao, Ruiqi
Holynski, Aleksander
Henzler, Philipp
Brussee, Arthur
Martin-Brualla, Ricardo
Srinivasan, Pratul
Barron, Jonathan T.
Poole, Ben
Computer Vision and Pattern Recognition
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 .
title CAT3D: Create Anything in 3D with Multi-View Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.10314