ICLR 2024poster630 citations
MVDream: Multi-view Diffusion for 3D Generation
Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, Xiao Yang
Abstract
We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the consistency of 3D renderings. We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods. It can also learn new concepts from a few 2D examples, akin to DreamBooth, but for 3D generation.
Image Generation3D GenerationDiffusion ModelMulti-view consistency
BibTeX
@inproceedings{
shi2024mvdream,
title={{MVD}ream: Multi-view Diffusion for 3D Generation},
author={Yichun Shi and Peng Wang and Jianglong Ye and Long Mai and Kejie Li and Xiao Yang},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=FUgrjq2pbB}
}