TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors

Official code release for the paper: TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors.

Mingwei Li^1,2, Pu Pang^3,2, Hehe Fan¹, Hua Huang⁴, Yi Yang^1,✉

¹Zhejiang University, ²Zhongguancun Academy, Beijing, ³Xi'an Jiaotong University, ⁴Beijing Normal University

News

• [2025-04-18]: 🎉 Our arXiv paper is released! You can find it here. Project page is also live!

We present TSGS, a framework for high-fidelity transparent surface reconstruction from multi-views. (a) We introduce TransLab, a novel dataset for evaluating transparent object reconstruction. (b) Comparative results on TransLab demonstrate the superior capability of TSGS.

Method Overview

(a) The two-stage training process. Stage 1 optimizes 3D Gaussians using geometric priors and de-lighted inputs. Stage 2 refines appearance while fixing opacity. (b) Inference extracts the first-surface depth map for mesh reconstruction. (c) The first-surface depth extraction module uses a sliding window for robust depth calculation.

Installation

1. Clone the repository and setup environment:

   git clone https://github.com/longxiang-ai/TSGS.git
   cd TSGS
   conda create -n tsgs python=3.8 -y
   conda activate tsgs

2. Install dependencies: Install PyTorch matching your CUDA version (see PyTorch website for the correct command). Example for CUDA 11.8:

   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
   # Install other requirements and submodules
   pip install -r requirements.txt
   pip install submodules/diff-trans-surface-rasterization
   pip install submodules/simple-knn

3. Install StableNormal (for input preprocessing): If you need to generate normal and de-lighting maps as input priors, install the StableNormal repository:

   git clone https://github.com/Stable-X/StableNormal.git
   cd StableNormal
   pip install -r requirements.txt
   # Follow the instructions in the StableNormal repository to process your data.
   cd .. # Return to the TSGS directory

TransLab Dataset

We introduce TransLab, a novel dataset specifically designed for evaluating transparent object reconstruction in laboratory settings. It features 8 diverse, high-resolution 360° scenes with challenging transparent glassware.

(Link to download the dataset - Coming Soon)

Results

TSGS significantly improves geometric accuracy and maintains high rendering quality on the TransLab dataset compared to state-of-the-art methods.

• Geometry: 37.3% reduction in Chamfer Distance, 8.0% improvement in F1 Score.
• Appearance: 0.41dB gain in PSNR for novel view synthesis.

TODO

• Release Arxiv paper link.
• Release source code.
• Release TransLab-Synthetic dataset and download link.
• Release TransLab-Real dataset and download link.
• Provide detailed installation and usage instructions.

Acknowledgements

We would like to thank the following open-source projects for their valuable contributions: PGSR, StableNormal, 2DGS, and GroundedSAM.

We also thank Nerfies for their amazing website template.

Star History

Citation

If you find our work useful, please consider citing:

@misc{li2025tsgs,
  title={TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors}, 
  author={Mingwei Li and Pu Pang and Hehe Fan and Hua Huang and Yi Yang},
  year={2025},
  eprint={2504.12799},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2504.12799}, 
}