---
license: cc-by-nc-nd-4.0
pipeline_tag: image-to-3d
tags:
- 3D
- Avatar
---

# UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections

UP2You is a tuning-free framework for 3D human reconstruction from unconstrained photo collections.


*   **Paper**: [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://arxiv.org/abs/2509.24817)
*   **Project Page**: [https://zcai0612.github.io/UP2You/](https://zcai0612.github.io/UP2You/)
*   **Code**: [https://github.com/zcai0612/UP2You](https://github.com/zcai0612/UP2You)


## Sample Usage

To run the inference pipeline with example images:
```bash
python inference_low_gpu.py \
    --base_model_path stabilityai/stable-diffusion-2-1-base  \
    --segment_model_name briaai/RMBG-2.0 \
    --data_dir examples \
    --output_dir outputs \
```
Alternatively, you can use the provided shell script:
```bash
bash run.sh
```
`examples` is the folder containing your unconstrained photos, and `outputs` is the directory where the generated 3D reconstruction results will be saved.

## Citation

If you find our work useful, please cite:

```bibtex
@article{cai2025up2you,
  title={UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections},
  author={Cai, Zeyu and Li, Ziyang and Li, Xiaoben and Li, Boqian and Wang, Zeyu and Zhang, Zhenyu and Xiu, Yuliang},
  journal={arXiv preprint arXiv:2509.24817},
  year={2025}
}
```