# rpautrat/SuperPoint

Efficient neural feature detector and descriptor

Repository: https://github.com/rpautrat/SuperPoint
Canonical: https://ross.abutalabs.com/products/superpoint
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2025-05-05T06:57:01+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 20, release rhythm 35, longevity 100
- inputs: {"age_days": 3103, "days_push": 485, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2511, forks 474 (observed 2026-08-28T04:06:57.418333+00:00)

## What it is
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
- artifact type: library
- maturity: stable
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: feature-detection, feature-descriptor, superpoint, tensorflow, pytorch, keypoint-detection, homography-estimation, self-supervised

## Member repositories
- rpautrat/SuperPoint (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.418333+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:23.634084+00:00, confidence not recorded.
  - readme: https://github.com/rpautrat/SuperPoint (fetched 2026-08-28T04:06:57.418333+00:00, sha 66372c30b264)
- Data as of 2026-08-30T08:39:29.467469+00:00.