vix.ing · top · new · best · stats

SuperPoint: Self-Supervised Interest Point Detection and Description

2017/12/20 by Daniel DeTone, DeTone, Daniel, Tomasz Malisiewicz +3 · 1 voice · 252 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1712.07629

Camera-ready version for CVPR 2018 Deep Learning for Visual SLAM Workshop (DL4VSLAM2018)

arxiv published 2017/12/20 · arxiv created 2018/04/19 · arxiv updated 2018/04/20

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.

Cited by

Discussions

Related