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.
Training library for local feature detection and matching
| Date | Stars |
|---|---|
| 2026-07-24 | 1125 |
| 2026-07-25 | 1125 |
| 2026-07-28 | 1127 |
| 2026-07-30 | 1127 |
| 2026-08-06 | 1127 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Glue Factory
Glue Factory is CVG's library for training and evaluating deep neural network that extract and match local visual feature. It enables you to:
- Reproduce the training of state-of-the-art models for point and line matching, like [LightGlue](https://github.com/cvg/LightGlue) and [GlueStick](https://github.com/cvg/GlueStick) (ICCV 2023)
- Train these models on multiple datasets using your own local features or lines
- Evaluate feature extractors or matchers on standard benchmarks like HPatches or MegaDepth-1500
<p align="center">
<a href="https://github.com/cvg/LightGlue"><img src="docs/lightglue_matches.svg" width="60%"/></a>
<a href="https://github.com/cvg/GlueStick"><img src="docs/gluestick_img.svg" width="60%"/></a>
<br /><em>Point and line matching with LightGlue and GlueStick.</em>
</p>
## Installation
Glue Factory runs with Python 3 and [PyTorch](https://pytorch.org/). The following installs the library and its basic dependencies:
```bash
git clone https://github.com/cvg/glue-factory
cd glue-factory
python3 -m pip install -e . # editable mode
```
Some advanced features might require installing the full set of dependencies:
```bash
python3 -m pip install -e .[extra]
```
All models and datasets in gluefactory have auto-downloaders, so you can get started right away!
## License
The code and trained models in Glue Factory are released with an Apache-2.0 license. This includes LightGlue and an [open version of SuperPoint](https://github.com/rpautrat/SuperPoint). Third-party models that are not compatible with this license, such as SuperPoint (original) and SuperGlue, are provided in `gluefactory_nonfree`, where each model might follow its own, restrictive license.
## Evaluation
#### HPatches
Running the evaluation commands automatically downloads the dataset, by default to the directory `data/`. You will need about 1.8 GB of free disk space.
<details>
<summary>[Evaluating LightGlue]</summary>
To evaluate the pre-trained SuperPoint+LightGlue model on HPatches, run:
```bash
python -m gluefactory.eval.hpatches --conf superpoint+lightglue-official --overwrite
```
You should expect the following results
```
{'H_error_dlt@1px': 0.3515,
'H_error_dlt@3px': 0.6723,
'H_error_dlt@5px': 0.7756,
'H_error_ransac@1px': 0.3428,
'H_error_ransac@3px': 0.5763,
'H_error_ransac@5px': 0.6943,
'mnum_keypoints': 1024.0,
'mnum_matches': 560.756,
'mprec@1px': 0.337,
'mprec@3px': 0.89,
'mransac_inl': 130.081,
'mransac_inl%': 0.217,
'ransac_mAA': 0.5378}
```
The default robust estimator is `opencv`, but we strongly recommend to use `poselib` instead:
```bash
python -m gluefactory.eval.hpatches --conf superpoint+lightglue-official --overwrite \
eval.estimator=poselib eval.ransac_th=-1
```
Setting `eval.ransac_th=-1` auto-tunes the RANSAC inlier threshold by running the evaluation with a range of thresholds and reports results for the optimal value.
Here are the results as Area Under the Curve (AUC) of the homography error at 1/3/5 pixels:
| Methods | DLT | [OpenCV](../gluefactory/robust_estimators/homography/opencv.py) | [PoseLib](../gluefactory/robust_estimators/homography/poselib.py) |
| ------------------------------------------------------------ | ------------------ | ------------------ | ------------------ |
| [SuperPoint + SuperGlue](gluefactory/configs/superpoint+superglue-official.yaml) | 32.1 / 65.0 / 75.7 | 32.9 / 55.7 / 68.0 | 37.0 / 68.2 / 78.7 |
| [SuperPoint + LightGlue](gluefactory/configs/superpoint+lightglue-official.yaml) | 35.1 / 67.2 / 77.6 | 34.2 / 57.9 / 69.9 | 37.1 / 67.4 / 77.8 |
</details>
<details>
<summary>[Evaluating GlueStick]</summary>
To evaluate GlueStick on HPatches, run:
```bash
python -m gluefactory.eval.hpatches --conf gluefactory/configs/superpoint+lsd+gluestick.yaml --overwrite
```
You should expect the following results
```
{"mprec@1px": 0.245,
"mprec@3px": 0.838,
"mnum_matches": 1290.5,
"mnuExcerpt of 15,863 characters
Read on GitHub
Philipp Lindenberger · ETH Zurich · Switzerland
20
Paul-Edouard Sarlin · Switzerland
10
2
Iago Suárez · Spain
2
2
1
Johan Edstedt · Computer Vision Laboratory, LiU
1
Ming-Yang Ho · CS PhD Student
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:697b0f3137ef1299, topic:deep-learning
matched fp:697b0f3137ef1299, topic:computer-vision