RGBD GS-ICP SLAM (中文注释版)

Paper | Original Github Page | CSDN 配置教程

Environments

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

# 安装pcl,zanshibuxuyao
# pip install pcl
# conda config --add channels conda-forge
# conda install -c sirokujira python-pcl

Also, PCL is needed for fast-gicp submodule.

Install submodules

 cd submodules/
 
git clone https://github.com/Lab-of-AI-and-Robotics/diff-gaussian-rasterization.git
 
git clone https://github.com/Lab-of-AI-and-Robotics/fast_gicp.git
 
git clone https://github.com/camenduru/simple-knn.git


# 然后执行下面代码
conda activate gsicpslam
pip install submodules/diff-gaussian-rasterization
pip install submodules/simple-knn

cd submodules/fast_gicp
mkdir build
cd build
cmake ..
make -j8
cd ..
python setup.py install --user

Datasets

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
```

Run

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

Installing SIBR Viewer

git clone https://github.com/embree/embree.git
mkdir embress/build
cd embree
git checkout v3.1.0
mkdir build
cmake -DCMAKE_INSTALL_PREFIX=/usr \
           -DEMBREE_TUTORIALS=OFF \
			-DEMBREE_ISPC_SUPPORT=OFF \
			-DEMBREE_TASKING_SYSTEM=OFF ..
make -j8
sudo make install


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

Real-time demo

Using rerun.io viewer

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

python -W ignore gs_icp_slam.py --rerun_viewer

Using SIBR 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

Docker

Please see the README.md in the docker_files folder.

lovelyyoshino/RGBD-GS-ICP-SLAM-Comment