KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#typescript #ai-agents #cli #claude-code #codex #developer-tools #dsh-plugin #ai-agent #mcp #deepseek-harness #windows #open-source

SGAD-SLAM

★ 22 Open GitHub ↗

[CVPR'26] SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1 align="center">SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM</h1>
  <p align="center">
    <a href="https://pengchongh.github.io/">Pengchong Hu</a>
    ·
    <a href="https://h312h.github.io/">Zhizhong Han</a>

</p>
  <h2 align="center">CVPR 2026</h2>
  <h3 align="center"><a href="https://arxiv.org/pdf/2603.21055">Paper</a> | <a href="https://machineperceptionlab.github.io/SGAD-SLAM-Project/">Project Page</a> </h3>
  <div align="center"></div>
</p>

<details open="open" style='padding: 10px; border-radius:5px 30px 30px 5px; border-width: 1px;'>
  <summary>Table of Contents</summary>
  <ol>
    <li>
      <a href="#installation">Installation</a>
    </li>
    <li>
      <a href="#dataset">Dataset</a>
    </li>
    <li>
      <a href="#run">Run</a>
    </li>
    <li>
      <a href="#evaluation">Evaluation</a>
    </li>
    <li>
      <a href="#acknowledgement">Acknowledgement</a>
    </li>
    <li>
      <a href="#citation">Citation</a>
    </li>
  </ol>
</details>

## Installation
Please install all dependencies by following the instructions here. You can use [anaconda](https://www.anaconda.com/) and [pip](https://pypi.org/project/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.

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

### TUM-RGBD

```bash
bash bash_scripts/download_tum.sh
```

### ScanNet

Please follow the data downloading procedure on [ScanNet](http://www.scan-net.org/) website, and extract color/depth frames from the `.sens` file using this [code](https://github.com/ScanNet/ScanNet/blob/master/SensReader/python/reader.py).

<details>
  <summary>[Directory structure of ScanNet (click to expand)]</summary>
  
  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
                  ├── ...
                  └── ...

```
</details>

### ScanNet++

Please follow the data downloading and image undistortion procedure on the [ScanNet++](https://kaldir.vc.in.tum.de/scannetpp/) website. Additionally, for undistorting the DSLR depth images, we use [a variant of the official ScanNet++ processing code](https://github.com/Nik-V9/scannetpp) from SplaTAM.

## Run

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

```bash
bash scripts/replica.sh
```

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

```bash
bash scripts/tum.sh
```

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

```bash
bash scripts/scannet.sh
```

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

```bash
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](https://github.com/graphdeco-inria/gaussian-splatting), [GradSLAM & ConceptFusion](https://github.com/gradslam/gradslam/tree/conceptfusion), [GS-ICP-SLAM](https://github.com/Lab-of-AI-and-Robotics/GS_ICP_SLAM), [SplaTAM](https://github.com/spla-tam/SplaTAM), [LoopSplat](https://github.com/GradientSpaces/LoopSplat), and [Gaussian-SLAM](https://github.com/VladimirYugay/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
```bibtex
@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}
                }
}
```

SGAD-SLAM

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README