DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization,
Yueming Xu*, Haochen Jiang*, Zhongyang Xiao, Jianfeng Feng, Li Zhang
NeurIPS 2024
Official implementation of "DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization".
Please follow the instructions below to install the repo and dependencies.
git clone https://github.com/fudan-zvg/DG-SLAM.git
cd DG-SLAM# Create conda environment
conda create -f environment.ymal
conda activate dgslamIf the front-end fail to execute successfully, please consult the official repository and accompanying guidance DROID-SLAM. The pretrained weights for DROID-SLAM can also be downloaded from this repository. The .path file should be placed in the ./checkpoints folder.
Download 6 dynamic scene sequences of TUM RGB-D dataset into ./data/TUM folder.
bash scripts/download_tum.sh Download 6 dynamic scene sequences of BONN RGB-D dataset into ./data/BONN folder.
bash scripts/download_bonn.sh Please send an official email to request permission for dataset access.
- Semantic Segmentation Mask: Firstly, you should generate semantic motion mask with OneFormer. For guidance on the environmental setup and execution process for this approach, please refer to the instructions provided on the official GitHub page. Secondly, move these generate mask images to the root path of dataset and create the folder named
./seg_mask
You can run DG-SLAM using the code below:
python run_tum.py
If you find our code or paper useful for your research, please consider citing:
@inproceedings{xu2024dgslam,
title={{DG}-{SLAM}: Robust Dynamic Gaussian Splatting {SLAM} with Hybrid Pose Optimization},
author={Yueming Xu and Haochen Jiang and Zhongyang Xiao and Jianfeng Feng and Li Zhang},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=tGozvLTDY3}
}Thanks to previous open-sourced repo: 3D-GS, Point-SLAM, DROID-SLAM, SplaTAM.
Contact Yueming Xu and Haochen Jiang for questions, comments and reporting bugs.