README.md

---
library_name: shape-for-motion
license: other
license_name: shape-for-motion
license_link: https://github.com/Tencent-Hunyuan/HunyuanWorld-Voyager/blob/main/LICENSE
language:
- en
- zh
tags:
- video_editing
pipeline_tag: video-to-video
extra_gated_eu_disallowed: true
base_model:
- model-hub/stable-video-diffusion-img2vid
---
<div align="center">
  <a href="https://shapeformotion.github.io/"><img src="https://img.shields.io/static/v1?label=Project%20Page&message=Web&color=green"></a> &ensp;
  <a href="https://arxiv.org/pdf/2506.22432"><img src="https://img.shields.io/static/v1?label=Tech%20Report&message=Arxiv&color=red"></a> &ensp;
  <a href="https://huggingface.co/LeoLau/Shape-for-Motion"><img src="https://img.shields.io/static/v1?label=shape_for-motion&message=HuggingFace&color=yellow"></a>
</div>

We introduce Shape-for-Motion, a 3D-aware video editing framework to support precise and consistent video object manipulation by reconstructing an editable 3D mesh to serve as control signals for video generation.

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6351463b8445bbe32e944f6c/YZmUUrADUPSoWx_1-jyiE.jpeg)

## 🔗 BibTeX

If you find [Shape-for-Motion](https://arxiv.org/abs/2506.22432) useful for your research and applications, please cite using this BibTeX:

```BibTeX
@article{liu2025shape,
  title={Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy},
  author={Liu, Yuhao and Wang, Tengfei and Liu, Fang and Wang, Zhenwei and Lau, Rynson WH},
  journal={arXiv preprint arXiv:2506.22432},
  year={2025}
}
```



## Acknowledgements

We would like to thank [DG-Mesh](https://github.com/Isabella98Liu/DG-Mesh), [Deformable 3DGS](https://ingra14m.github.io/Deformable-Gaussians), and [Diffusers](https://github.com/huggingface/diffusers) for their open research and exploration.