GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting

CVPR 2025 Highlight

Shujuan Li · Yu-Shen Liu · Zhizhong Han

Paper | Project Page

Preprocessed Datasets & Pretrained Meshes

Our preprocessed datasets are provided in This link. For DTU dataset, download the pair file for the warp loss. Please organize all files as follows:

data
├── deepfashion_rendering_fov60
│   ├── 30
│   │   ├── images
│   │   ├── mask
│   │   ├── sparse
│   │   ├── cameras_sphere.npz
│   │   ├── 30_pc_swap.ply
│   │   └── ...
│   ├──...
├── dtu
│   ├── scan24
│   │   ├── depths
│   │   ├── images
│   │   ├── mask
│   │   ├── sparse
│   │   └── cameras.npz
│   └── ...
├── DTU_GTpoints 
│   │   ├── Points
│   │   │   └── stl
│   │   └── ObsMask
│   └── ...
├── dtu_pair
│   ├── scan24
│   │   ├── pairs.txt
│   └── ...

Pretrained meshes are provided in This link.

Setup

Installation

git clone git@github.com:lisj575/GaussianUDF.git
cd GaussianUDF

conda env create --file environment.yml
conda activate gs-udf

# extract udf
cd custom_mc
python setup.py build_ext --inplace
cd ..

Training and Evaluation

# DF3D dataset
python run_df3d.py

# DTU 
python run_dtu.py

Acknowledgements

This project is built upon 2DGS, Neural-Pull and CAP-UDF. We thank all the authors for their great repos.

Citation

If you find our code or paper useful, please consider citing

@inproceedings{li2025gaussianudf,
  title={Gaussianudf: Inferring unsigned distance functions through 3d gaussian splatting},
  author={Li, Shujuan and Liu, Yu-Shen and Han, Zhizhong},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={27113--27123},
  year={2025}
}