Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
| Date | Stars |
|---|---|
| 2026-07-24 | 2125 |
| 2026-07-25 | 2125 |
| 2026-07-28 | 2127 |
| 2026-07-30 | 2127 |
| 2026-08-06 | 2127 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[comment]: <> (# Gaussian Splatting SLAM)
<!-- PROJECT LOGO -->
<p align="center">
<h1 align="center"> Gaussian Splatting SLAM
</h1>
<p align="center">
<a href="https://muskie82.github.io/"><strong>*Hidenobu Matsuki</strong></a>
·
<a href="https://rmurai.co.uk/"><strong>*Riku Murai</strong></a>
·
<a href="https://www.imperial.ac.uk/people/p.kelly/"><strong>Paul H.J. Kelly</strong></a>
·
<a href="https://www.doc.ic.ac.uk/~ajd/"><strong>Andrew J. Davison</strong></a>
</p>
<p align="center">(* Equal Contribution)</p>
<h3 align="center"> CVPR 2024 (Highlight)</h3>
[comment]: <> ( <h2 align="center">PAPER</h2>)
<h3 align="center"><a href="https://arxiv.org/abs/2312.06741">Paper</a> | <a href="https://youtu.be/x604ghp9R_Q?si=nYoWr8h2Xh-6L_KN">Video</a> | <a href="https://rmurai.co.uk/projects/GaussianSplattingSLAM/">Project Page</a></h3>
<div align="center"></div>
<p align="center">
<a href="">
<img src="./media/teaser.gif" alt="teaser" width="100%">
</a>
<a href="">
<img src="./media/gui.jpg" alt="gui" width="100%">
</a>
</p>
<p align="center">
This software implements dense SLAM system presented in our paper <a href="https://arxiv.org/abs/2312.06741">Gaussian Splatting SLAM</a> in CVPR'24.
The method demonstrates the first monocular SLAM solely based on 3D Gaussian Splatting (left), which also supports Stereo/RGB-D inputs (middle/right).
</p>
<br>
# Note
- In an academic paper, please refer to our work as **Gaussian Splatting SLAM** or **MonoGS** for short (this repo's name) to avoid confusion with other works.
- Differential Gaussian Rasteriser with camera pose gradient computation is available [here](https://github.com/rmurai0610/diff-gaussian-rasterization-w-pose.git).
- **[New]** Speed-up version of our code is available in `dev.speedup` branch, It achieves up to 10fps on monocular fr3/office sequence while keeping consistent performance (tested on RTX4090/i9-12900K). The code will be merged into the main branch after further refactoring and testing.
# Getting Started
## Installation
```
git clone https://github.com/muskie82/MonoGS.git --recursive
cd MonoGS
```
Setup the environment.
```
conda env create -f environment.yml
conda activate MonoGS
```
Depending on your setup, please change the dependency version of pytorch/cudatoolkit in `environment.yml` by following [this document](https://pytorch.org/get-started/previous-versions/).
Our test setup were:
- Ubuntu 20.04: `pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6`
- Ubuntu 18.04: `pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3`
## Quick Demo
```
bash scripts/download_tum.sh
python slam.py --config configs/mono/tum/fr3_office.yaml
```
You will see a GUI window pops up.
## Downloading Datasets
Running the following scripts will automatically download datasets to the `./datasets` folder.
### TUM-RGBD dataset
```bash
bash scripts/download_tum.sh
```
### Replica dataset
```bash
bash scripts/download_replica.sh
```
### EuRoC MAV dataset
```bash
bash scripts/download_euroc.sh
```
## Run
### Monocular
```bash
python slam.py --config configs/mono/tum/fr3_office.yaml
```
### RGB-D
```bash
python slam.py --config configs/rgbd/tum/fr3_office.yaml
```
```bash
python slam.py --config configs/rgbd/replica/office0.yaml
```
Or the single process version as
```bash
python slam.py --config configs/rgbd/replica/office0_sp.yaml
```
### Stereo (experimental)
```bash
python slam.py --config configs/stereo/euroc/mh02.yaml
```
## Live demo with Realsense
First, you'll need to install `pyrealsense2`.
Inside the conda environment, run:
```bash
pip install pyrealsense2
```
Connect the realsense camera to the PC on a **USB-3** port and then run:
```bash
python slam.py --config configs/live/realsense.yaml
```
We tested the method with [Intel Realsense d455](https://www.mouser.co.uk/new/intel/intel-realsense-depth-camera-d455/). We recommend using a similar global shutterExcerpt of 6,663 characters
Read on GitHub
18
7
4
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:69f9088669030de5, topic:computer-vision, topic:gaussian-splatting, desc:gaussian splatting
matched fp:69f9088669030de5, topic:robotics, topic:slam, desc:slam