This repository is intended to substantiate the results reported in the paper. Additional features including visualization tools will be updated soon!

Install requirements

conda create -n gsicpslam python==3.9
conda activate gsicpslam
conda install pytorch==2.0.0 torchvision==0.15.0 torchaudio==2.0.0 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install -r requirements.txt

Also, PCL is needed for fast-gicp submodule.

Install submodules

conda activate gsicpslam
pip install submodules/diff-gaussian-rasterization
pip install submodules/simple-knn

cd submodules/fast_gicp
mkdir build
cd build
cmake ..
make
cd ..
python setup.py install --user

• Replica

  • Download

    bash download_replica.sh

  • Configure

    Please modify the directory structure to ours.

    The original structure

    Replica
        - room0
            - results (contain rgbd images)
                - frame000000.jpg
                - depth000000.jpg
                ...
            - traj.txt
        ...

    Our structure

    Replica
        - room0
            - images (contain rgb images)
                - frame000000.jpg
                ...
            - depth_images (contain depth images)
                - depth000000.jpg
                ...
            - traj.txt
        ...

• TUM-RGBD

  • Download

        bash download_tum.sh

• Limited to 30 FPS

      # Replica
      bash replica.sh
      # TUM
      bash tum.sh

• Unlimited tracking speed

      # Replica
      bash replica_unlimit.sh
      # TUM
      bash tum_unlimit.sh

cd SIBR_viewers
cmake -Bbuild . -DCMAKE_BUILD_TYPE=Release
cmake --build build -j24 --target install

Rerun viewer shows the means of trackable Gaussians, and rendered image from reconstructed 3dgs map.

python -W ignore gs_icp_slam.py --rerun_viewer

python -W ignore gs_icp_slam.py --dataset_path dataset/Replica/office0 --verbose

# In other terminal
cd SIBR_viewers
./install/bin/SIBR_remoteGaussian_app --rendering-size 1280 720

Please see the README.md in the docker_files folder.