yuefanhao/SuperPoint-SuperGlue-TensorRT

SuperPoint and SuperGlue with TensorRT. Deploy with C++.

46
/ 100
Emerging

This project helps robotics engineers or computer vision developers quickly and efficiently find corresponding points between two images. It takes a pair of images as input and outputs a list of matched features, indicating which parts of the images correspond to each other. This is crucial for tasks like object tracking or 3D reconstruction in real-time.

366 stars. No commits in the last 6 months.

Use this if you need to perform high-speed, accurate image feature matching for applications like robotics navigation, augmented reality, or visual odometry on NVIDIA GPUs.

Not ideal if you are looking for a general-purpose image recognition library or if you are not working with NVIDIA hardware for deployment.

robotics computer-vision real-time-processing 3d-reconstruction feature-matching
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

366

Forks

58

Language

C++

License

Apache-2.0

Last pushed

Apr 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yuefanhao/SuperPoint-SuperGlue-TensorRT"

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