1.Installation

June 7, 2026 路 View on GitHub

Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM

Yunsong Wang 路 Gim Hee Lee
National University of Singapore

CVPR 2026 Highlight

Code | Paper | Project Page

PyTorch

Logo

Efficient Dynamic Reconstruction + SLAM: Our Flow4DGS-SLAM solves the complex dynamic mapping and tracking task in a much more efficient pipeline.

News:

  • [2026/04/09] Flow4DGS-SLAM is selected as a Highlight paper 馃殌.
  • [2026/02/21] Flow4DGS-SLAM is accepted to CVPR 2026 馃敟.

1.Installation

git clone https://github.com/wangys16/Flow4DGS-SLAM.git
cd Flow4DGS-SLAM

Setup the environment.

conda create -n dyslam python=3.8
conda activate dyslam
# CUDA 11.7
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117
pip install -r requirements.txt

The simple-knn and diff-gaussian-rasterization libraries use the ones provided by MonoGS.

pip install submodules/simple-knn
pip install submodules/diff-gaussian-rasterization

Use torch-batch-svd speed up (Optional)

git clone https://github.com/KinglittleQ/torch-batch-svd
cd torch-batch-svd
python setup.py install
cd ..

2.Pretrained Models

Download YOLOv9e-seg

cd pretrained
wget https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov9e-seg.pt

Or download it directly from https://docs.ultralytics.com/models/yolov9/

Download RAFT

The model raft-things.pth used in this system can be obtained directly from https://drive.google.com/drive/folders/1sWDsfuZ3Up38EUQt7-JDTT1HcGHuJgvT

3.Datasets

TUM-RGBD dataset

Download the sequence using the following command:

bash scripts/download_tum.sh

BONN dataset

Download the sequence using the following command:

bash scripts/download_bonn.sh

4.Testing

TUM-RGBD dataset

bash scripts/train_tum.sh

BONN dataset

bash scripts/train_bonn.sh

5.Acknowledgement

This work incorporates many open-source codes. We extend our gratitude to the authors of the software.

6.Citation

If you find this code/work useful for your own research, please consider citing:

@article{wang2026flow4dgs,
  title={Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM},
  author={Wang, Yunsong and Lee, Gim Hee},
  journal={arXiv preprint arXiv:2604.22339},
  year={2026}
}