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.
We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
Ranked #1 on Camera Localization on Aachen Day-Night benchmark
In this paper, we propose the USIP detector: an Unsupervised Stable Interest Point detector that can detect highly repeatable and accurately localized keypoints from 3D point clouds under arbitrary transformations without the need for any ground truth training data.
By making the sampling of inlier-outlier sets from point-pair correspondences fully differentiable within the keypoint learning framework, we show that are able to simultaneously self-supervise keypoint description and improve keypoint matching.
As an important technology in 3D mapping, autonomous driving, and robot navigation, LiDAR odometry is still a challenging task.
Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the accuracy of MVS systems.
Ranked #1 on Depth Estimation on ScanNetV2