cvg/glue-factory

Training library for local feature detection and matching

54
/ 100
Established

This is a training and evaluation library for deep learning models that find and match visual features in images. It takes raw image data and helps you develop or assess models that can precisely identify points and lines between different views of the same scene. This is ideal for computer vision researchers or engineers working on tasks like 3D reconstruction, augmented reality, or robot navigation.

1,056 stars.

Use this if you need to train new deep learning models or evaluate existing ones for robustly matching visual features across different images, such as for 3D environment understanding.

Not ideal if you are looking for an out-of-the-box application for general image processing or object recognition rather than specialized feature matching.

3D-reconstruction image-matching computer-vision-research robotics-perception augmented-reality
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,056

Forks

146

Language

Python

License

Apache-2.0

Last pushed

Nov 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cvg/glue-factory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.