SuperPoint: Self-Supervised Interest Point Detection and Description

TL;DR

This paper introduces a self-supervised, fully-convolutional interest point detector and descriptor that improves repeatability and accuracy in multi-view geometry tasks, achieving state-of-the-art results on homography estimation.

Contribution

It proposes Homographic Adaptation for boosting interest point detection and a fully-convolutional model for joint detection and description, trained on MS-COCO.

Findings

Outperforms traditional detectors like SIFT and ORB in homography estimation.

Detects a richer set of interest points with higher repeatability.

Achieves state-of-the-art results on HPatches dataset.

Abstract

This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.