We present Stable Video 3D (SV3D) - a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object.
Recent work on 3D generation propose techniques to adapt 2D generative models for novel view synthesis (NVS) and 3D optimization. However, these methods have several disadvantages due to either limited views or inconsistent NVS, thereby affecting the performance of 3D object generation.
In this work, we propose SV3D that adapts image-to-video diffusion model for novel multi-view synthesis and 3D generation, thereby leveraging the generalization and multi-view consistency of the video models, while further adding explicit camera control for NVS. We also propose improved 3D optimization techniques to use SV3D and its NVS outputs for image-to-3D generation. Extensive experimental results on multiple datasets with 2D and 3D metrics as well as user study demonstrate SV3D's state-of-the-art performance on NVS as well as 3D reconstruction compared to prior works.
Results on diverse images.
Comparing our results on novel multi-view synthesis with Stable Zero 123 and Zero123 XL.
SV3D (ours)
Stable Zero123
Zero123 XL
Ground-Truth
3D meshes from diverse images.
Click on the individual images to view the 3D model.
@article{voleti2024sv3d,
author = {Voleti, Vikram and Yao, Chun-Han and Boss, Mark and Letts, Adam and Pankratz, David and Tochilkin, Dmitrii and Laforte, Christian and Rombach, Robin and Jampani, Varun},
title = {{SV3D}: Novel Multi-view Synthesis and {3D} Generation from a Single Image using Latent Video Diffusion},
journal = {arXiv},
year = {2024},
}