SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM

Pengchong Hu · Zhizhong Han

CVPR 2026

Paper | Project Page

Table of Contents

1. Installation
2. Dataset
3. Run
4. Evaluation
5. Acknowledgement
6. Citation

Installation

Please install all dependencies by following the instructions here. You can use anaconda and pip to finish the installation easily. We tested SGAD-SLAM on RTX 4090 GPUs with Python 3.9.21, Torch 2.0.0, and CUDA=11.8.

You can build a conda environment called sgadslam following the instructions below.

git clone https://github.com/MachinePerceptionLab/SGAD-SLAM.git
cd SGAD-SLAM

export CC=<gcc path>
export CXX=<g++ path>

conda create -n sgadslam python==3.9.21
conda activate sgadslam
conda install pip==24.3.1
pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu118

pip install -r requirements.txt
conda install numpy-base=1.26.4
conda install faiss-gpu=1.8.0

# install PCL
pip install pcl
conda config --add channels conda-forge
conda install -c sirokujira python-pcl
conda install -c conda-forge cmake=3.25.0
conda install vtk
conda install -c conda-forge pcl=1.14.*

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

# install simple-knn
cd ../..
pip install submodules/simple-knn

Dataset

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

Replica

Please download the Replica dataset generated by the authors of iMAP into ./dataset/Replica folder. Please cite iMAP if you use the dataset.

bash bash_scripts/download_replica.sh # Released by authors of NICE-SLAM

TUM-RGBD

bash bash_scripts/download_tum.sh

ScanNet

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

[Directory structure of ScanNet (click to expand)]

DATAROOT is ./dataset by default. If a sequence (sceneXXXX_XX) is stored in other places, please change the basedir path in the config file.

  DATAROOT
  └── scannet
      └── scans
          └── scene0000_00
              ├── color
              │   ├── 0.jpg
              │   ├── 1.jpg
              │   ├── ...
              │   └── ...
              ├── depth
              │   ├── 0.png
              │   ├── 1.png
              │   ├── ...
              │   └── ...
              ├── intrinsic
              └── pose
                  ├── 0.txt
                  ├── 1.txt
                  ├── ...
                  └── ...

ScanNet++

Please follow the data downloading and image undistortion procedure on the ScanNet++ website. Additionally, for undistorting the DSLR depth images, we use a variant of the official ScanNet++ processing code from SplaTAM.

Run

Replica

To run SGAD-SLAM on Replica dataset, please use the following command:

bash scripts/replica.sh

TUM-RGBD

To run SGAD-SLAM on TUM-RGBD dataset, please use the following command:

bash scripts/tum.sh

ScanNet

To run SGAD-SLAM on ScanNet dataset, please use the following command:

bash scripts/scannet.sh

ScanNet++

To run SGAD-SLAM on ScanNet++ dataset, please use the following command:

bash scripts/scannetpp.sh

Evaluation

When running SGAD-SLAM using the above commands, we can get the final evaluation results in rendering and tracking.

Acknowledgement

This project was partially supported by an NVIDIA academic award and a Richard Barber research award.

We adapt codes from some awesome repositories, including 3D Gaussian Splatting, GradSLAM & ConceptFusion, GS-ICP-SLAM, SplaTAM, LoopSplat, and Gaussian-SLAM. Thanks for making the code available and for prompt responses to our inquiries regarding the details of their methods.

Citation

If you find our code or paper useful, please cite

@InProceedings{Hu2026sgadslam,
                title = {SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM},
                author = {Hu, Pengchong and Han, Zhizhong},
                booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
                year = {2026}
                }
}