360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming

3DV 2025

Jiayang Bai Letian Huang Jie Guo^* Wen Gong Yuanqi Li Yanwen Guo
Nanjing University

TODO List

• Dataset preparation.

• Release the code.

Dataset

Please read the README.

Installation

Clone the repository and create an anaconda environment:

git clone https://github.com/LeoDarcy/360GS.git --recursive
cd 360GS/submodules/

SET DISTUTILS_USE_SDK=1 # Windows only
conda env create --file environment.yml
conda activate op43dgs
pip install submodules/diff-gaussian-rasterization-panorama

Train

python train.py -s

while withholding a test set for evaluation, use the --eval flag. This way, you can render training/test sets and produce error metrics as follows:

python train.py -s <path to dataset> --room_id <room_id> --use_layout --use_layout_densify --lambda_dxyz 0.01 --eval 

Acknowledgements

This project is built upon 3DGS. Please follow the license of 3DGS. We thank all the authors for their great work and repos.

Citation

If you find this work useful in your research, please cite:

@article{bai2024360,
  title={360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming},
  author={Bai, Jiayang and Huang, Letian and Guo, Jie and Gong, Wen and Li, Yuanqi and Guo, Yanwen},
  journal={arXiv preprint arXiv:2402.00763},
  year={2024}
}
@article{huang2024erroranalysis3dgaussian,
    title={On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy},
    author={Letian Huang and Jiayang Bai and Jie Guo and Yuanqi Li and Yanwen Guo},
    journal={arXiv preprint arXiv:2402.00752},
    year={2024}
}