magicleap/SuperGluePretrainedNetwork

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

51
/ 100
Established

This project helps computer vision practitioners find corresponding points between two different images, even if those images were taken from different viewpoints or under varying conditions. It takes in two images, processes them, and outputs a list of matched features, indicating which parts of the first image correspond to which parts of the second. This is ideal for researchers or engineers working on tasks that require understanding spatial relationships between images.

3,967 stars. No commits in the last 6 months.

Use this if you need to precisely identify matching visual features across image pairs for tasks like 3D reconstruction, augmented reality, or object tracking.

Not ideal if you're looking for a general-purpose image classifier or object detection tool that doesn't involve matching features between distinct images.

computer-vision 3d-reconstruction image-matching visual-localization robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

3,967

Forks

762

Language

Python

License

Last pushed

Aug 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/magicleap/SuperGluePretrainedNetwork"

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