rpautrat/SuperPoint

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2511 stars · 474 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow (with PyTorch conversion) implementation of the SuperPoint self-supervised interest point detector and descriptor network. It provides pretrained weights and evaluation tooling for feature detection, description, and homography estimation on benchmarks like HPatches.

Use cases

• detect keypoints in images with a neural network
• compute feature descriptors for image matching
• estimate homographies between image pairs
• run SuperPoint pretrained weights in PyTorch
• evaluate feature detectors on HPatches
• build visual odometry or SLAM front-ends
• replace SIFT/ORB with learned features

When to choose

• you need an MIT-licensed SuperPoint implementation
• you want learned keypoints/descriptors outperforming classical methods in benchmarks
• you need both TensorFlow and PyTorch model weights

When to avoid

• you need real-time performance on embedded hardware without GPU
• you only need classical, dependency-free feature detectors like ORB
• you need a maintained production pipeline rather than research code

Facets

library · maturity stable

machine-learning computer-vision image-processing computer-vision machine-learning deep-learning python cross-platform feature-detection feature-descriptor superpoint tensorflow pytorch keypoint-detection homography-estimation self-supervised

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rpautrat/SuperPoint")