magicleap/SuperPointPretrainedNetwork
A PyTorch implementation of SuperPoint, a fully convolutional deep neural network for real-time interest point detection and descriptor computation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a pretrained SuperPoint model, a fully convolutional deep neural network trained to detect interest points and compute their accompanying descriptors. The model enables image-to-image matching tasks and includes a demo script for sparse optical flow point tracking across video sequences. It uses OpenCV and PyTorch for deployment and was developed by researchers at Magic Leap for visual SLAM and related applications.
Frequently asked
- What is magicleap/SuperPointPretrainedNetwork?
- A PyTorch implementation of SuperPoint, a fully convolutional deep neural network for real-time interest point detection and descriptor computation.
- Is SuperPointPretrainedNetwork open source?
- Yes — magicleap/SuperPointPretrainedNetwork is an open-source project tracked on heatdrop.
- What language is SuperPointPretrainedNetwork written in?
- magicleap/SuperPointPretrainedNetwork is primarily written in Python.
- How popular is SuperPointPretrainedNetwork?
- magicleap/SuperPointPretrainedNetwork has 2.2k stars on GitHub.
- Where can I find SuperPointPretrainedNetwork?
- magicleap/SuperPointPretrainedNetwork is on GitHub at https://github.com/magicleap/SuperPointPretrainedNetwork.