SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM

IROS 2025

<strong>Siting Zhu</strong></a>
·
<strong>Renjie Qin</strong></a>
·
<strong>Guangming Wang</strong></a>
·
<strong>Jiuming Liu</strong></a>
·
<strong>Hesheng Wang</strong></a>

Paper

Table of Contents

1. Installation
2. Usage
3. Downloads
4. Acknowledgement
5. Citation
6. Developers

Installation

sem_guass_slam has been benchmarked with Python 3.10, Pytorch 1.12.1 & CUDA=11.6. The simplest way to install all dependences is to use anaconda and pip in the following steps:

conda create -n sem_gauss python=3.10
conda activate sem_gauss
conda install -c "nvidia/label/cuda-11.6.0" cuda-toolkit
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6 -c pytorch -c conda-forge
pip install -r requirements.txt

Usage

We will use the replica dataset as an example to show how to use sem_guass_slam. The following steps are similar for other datasets.

To run sem_guass_slam, please use the following command:

python sem_gauss.py configs/replica/replica.py

You should download the corresponding pth file of the dinov2 in here before running the command above.

To see the evaluation of the reconstructed mesh, please use the following command:

python eval_mesh/mesh_eval.py

You should rewrite the path of the reconstructed mesh flie and true mesh file in eval_mesh/mesh_eval.py. And you can download the true mesh file in here.

Downloads

Dataroot is ./data0/replica by default. Please change the input_folder path in the scene-specific config files if datasets are stored somewhere else on your machine.

Replica

Download the replica data on this website:replica. Note that the Replica data is generated by the authors of iMAP (but hosted by the authors of NICE-SLAM). Please cite iMAP if you use the data.

ScanNet

Please follow the data downloading procedure on the ScanNet website, and extract color/depth frames from the .sens file using this code.

Acknowledgement

We thank the authors of the following repositories for their open-source code:

• 3D Gaussians
• Dynamic 3D Gaussians
• 3D Gaussian Splating
• Dataloaders
• GradSLAM & ConceptFusion
• Baselines
• Nice-SLAM
• Point-SLAM
• SplaTAM

Citation

If you find our paper and code useful, please cite us:

@INPROCEEDINGS{zhu2024semgauss,
  author={Zhu, Siting and Qin, Renjie and Wang, Guangming and Liu, Jiuming and Wang, Hesheng},
  booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM}, 
  year={2025},
  pages={21174-21181}
}