SuperPoint: Self-Supervised Interest Point Detection and Description
This work addresses a key bottleneck in computer vision for tasks like 3D reconstruction and image matching, offering a novel self-supervised approach that improves upon traditional methods.
The paper tackles the problem of interest point detection and description for multiple-view geometry in computer vision by introducing a self-supervised framework that uses Homographic Adaptation to boost repeatability and cross-domain adaptation, resulting in state-of-the-art homography estimation on HPatches compared to LIFT, SIFT, and ORB.
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.