🔥 HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

HumanSplat predicts 3D Gaussian Splatting properties from a single input image in a generalizable manner.

📊 Download human datasets (Thuman2.0, 2K2K and Twindom) and organize them as follows:

${ROOT} 
├──📂data/
    ├──📂Thuman2/
       ├── 📂0000/
       ├── 📂...
       ├── 📂0525/
    ├──📂2K2K/
       ├── 📂00003/
       ├── 📂...
       ├── 📂04739/
    ├──📂Twindom/

🔧 Installation

Additionally dependencies include:

bash settings/setup.sh
pip3 install -r settings/requirements.txt 

🤖 Usage

Run ./train.py

python3 train.py --config configs/humansplat.yaml 

Run ./demo.py

python3 eval.py --config configs/humansplat.yaml 

Acknowledgement

We would like to thank sv3d-diffusers's author for open-sourcing their implementation.

📚 Citation

If you find our work useful for your research, please consider citing:

@article{pan2024humansplat,
  title={HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors},
  author={Pan, Panwang and Su, Zhuo and Lin, Chenguo and Fan, Zhen and Zhang, Yongjie and Li, Zeming and Shen, Tingting and Mu, Yadong and Liu, Yebin},
  journal={arXiv preprint arXiv:2406.12459},
  year={2024}
}