rpautrat/SuperPoint
A Tensorflow and Pytorch implementation of SuperPoint, a self-supervised neural network for detecting and describing interest points in images.
Not currently ranked — collecting fresh signals.
star history
This repository implements SuperPoint, a deep learning paper on self-supervised interest point detection and description. The project provides neural network implementations in both Tensorflow and Pytorch for detecting keypoints in images and generating feature descriptors for matching. It includes pre-trained weights and benchmark results on the HPatches dataset for evaluating detector repeatability and descriptor matching under illumination and viewpoint changes.
Frequently asked
- What is rpautrat/SuperPoint?
- A Tensorflow and Pytorch implementation of SuperPoint, a self-supervised neural network for detecting and describing interest points in images.
- Is SuperPoint open source?
- Yes — rpautrat/SuperPoint is open source, released under the MIT license.
- What language is SuperPoint written in?
- rpautrat/SuperPoint is primarily written in Jupyter Notebook.
- How popular is SuperPoint?
- rpautrat/SuperPoint has 2.5k stars on GitHub.
- Where can I find SuperPoint?
- rpautrat/SuperPoint is on GitHub at https://github.com/rpautrat/SuperPoint.