README.md

---
license: mit
library_name: diffusers
pipeline_tag: image-to-3d
tags:
- 3D scene generation
base_model:
- alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera
---
<div align="left">
<h1>
<span style="color:#F3E969">G</span><span style="color:#D6E67B">e</span><span style="color:#93D89A">n</span><span style="color:#69D5C9">3</span><span style="color:#55B5CA">R</span>: 3D Scene Generation Meets Feed-Forward Reconstruction
</h1>

[Jiaxin Huang](https://jaceyhuang.github.io/), [Yuanbo Yang](https://github.com/freemty), [Bangbang Yang](https://ybbbbt.com/), [Lin Ma](https://scholar.google.com/citations?user=S4HGIIUAAAAJ&hl=en),  [Yuewen Ma](https://scholar.google.com/citations?user=VG_cdLAAAAAJ), [Yiyi Liao](https://yiyiliao.github.io/)

<a href="https://xdimlab.github.io/Gen3R/"><img src="https://img.shields.io/badge/Project_Page-yellowgreen" alt="Project Page"></a>
<a href="https://arxiv.org/abs/2601.04090"><img src="https://img.shields.io/badge/arXiv-2601.04090-b31b1b" alt="arXiv"></a>
<a href="https://github.com/JaceyHuang/Gen3R"><img src="https://img.shields.io/github/stars/JaceyHuang/Gen3R?style=default&label=GitHub%20%E2%98%85&logo=github" alt="GitHub"></a>

<p align="left">
This model represents the official checkpoint of the paper titled "Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction".
</p>

</div>

## 🎓 Citation
Please cite our paper if you find this repository useful:

```bibtex
@misc{huang2026gen3r3dscenegeneration,
      title={Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction}, 
      author={Jiaxin Huang and Yuanbo Yang and Bangbang Yang and Lin Ma and Yuewen Ma and Yiyi Liao},
      year={2026},
      eprint={2601.04090},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2601.04090}, 
}
```