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.
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
| Date | Stars |
|---|---|
| 2026-07-24 | 675 |
| 2026-07-25 | 675 |
| 2026-07-28 | 675 |
| 2026-07-30 | 675 |
| 2026-08-06 | 675 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# GlueStick
[](https://colab.research.google.com/github/cvg/GlueStick/blob/main/gluestick_matching_demo.ipynb) [](https://arxiv.org/abs/2304.02008) [](https://iago-suarez.com/gluestick)
Joint deep matcher for points and lines 🖼️💥🖼️
**Update: we are pleased to announce that the training code has been released within our new training framework, [GlueFactory](https://github.com/cvg/glue-factory).**
This repository contains the official implementation of
[GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://arxiv.org/abs/2304.02008), accepted at ICCV 2023.
## Install 🛠️
To install the software in Ubuntu 22.04 follow these instructions:
```bash
sudo apt-get install build-essential cmake libopencv-dev libopencv-contrib-dev
git clone --recursive https://github.com/cvg/GlueStick.git
cd GlueStick
# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
pip install .
```
## Running GlueStick 🏃
Download the weights of the model:
```
wget https://github.com/cvg/GlueStick/releases/download/v0.1_arxiv/checkpoint_GlueStick_MD.tar -P resources/weights
```
You can execute the inference with it with:
```
python -m gluestick.run -img1 resources/img1.jpg -img2 resources/img2.jpg
```
## Training 🏋️
The training code is available in a separate repository, [GlueFactory](https://github.com/cvg/glue-factory). Within GlueFactory, you can not only train GlueStick, but also other deep matchers such as [LightGlue](https://github.com/cvg/LightGlue), use multiple feature extractors, line extractors, robust estimators, as well as run evaluations on multiple benchmarks.
## Licence 📜
Our code is licenced under [MIT licence](https://github.com/cvg/GlueStick/blob/main/LICENSE).
However, bear in mind that it uses a SuperPoint backbone that has a
[non-commercial licence](https://github.com/magicleap/SuperPointPretrainedNetwork/blob/master/LICENSE).
Therefore, the overall system is non-commercial 😞. We are working on an analogous version based on
[DISK](https://github.com/cvlab-epfl/disk) to avoid this problem.
## Citation 📝
If you use this code in your project, please consider citing the following paper:
```bibtex
@InProceedings{pautrat_suarez_2023_gluestick,
title={{GlueStick}: Robust Image Matching by Sticking Points and Lines Together},
author={Pautrat, R{\'e}mi* and Su{\'a}rez, Iago* and Yu, Yifan and Pollefeys, Marc and Larsson, Viktor},
booktitle={International Conference on Computer Vision (ICCV)},
year={2023}
}
```
Excerpt of 2,859 characters
Read on GitHub
Iago Suárez · Spain
11
11
2
Shaohui Liu · Switzerland
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c8b2dd7ae1b96b14, topic:deep-learning, readme:training framework
matched fp:c8b2dd7ae1b96b14, topic:computer-vision, readme:computer vision