Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Arxiv 2023

Xiaoxiao Long1,3,6,*, Yuan-Chen Guo2,3,*, Cheng Lin1, Yuan Liu1, Zhiyang Dou1,
Lingjie Liu4, Yuexin Ma5, Song-Hai Zhang2, Marc Habermann6, Christian Theobalt6, Wenping Wang7

*Equal contributions   
1The University of Hong Kong    2Tsinghua University    3VAST   
4University of Pennsylvania      5Shanghai Tech University      6MPI Informatik      7Texas A&M University


Wonder3D produces consistent multi-view normal maps and correpsonding color images,
and thus reconstructs high-fidelity textured mesh from a single image in only 2~3 minutes.

In this work, we introduce Wonder3D, a novel method for generating high-fidelity textured meshes from single-view images with remarkable efficiency. Recent methods based on the Score Distillation Sampling (SDS) loss methods have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure consistency, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and remarkable efficiency compared to prior works.


Overview of Wonder3D.

Combine Wonder3D and Houdini to create lego-style objects

Many thanks to Allen Zhang for creating the video.

Use Wonder3D to create hundreds of 3D assets

Many thanks to Allen Zhang for creating the video.

Use Wonder3D for 3D printing

3D printing

Many thanks to RichViip for creating objects.

2D design to 3D model

Animal images to 3D

More results


  title={Wonder3D: Single Image to 3D using Cross-Domain Diffusion},
  author={Long, Xiaoxiao and Guo, Yuan-Chen and Lin, Cheng and Liu, Yuan and Dou, Zhiyang and Liu, Lingjie and Ma, Yuexin and Zhang, Song-Hai and Habermann, Marc and Theobalt, Christian and others},
  journal={arXiv preprint arXiv:2310.15008},