×

R2D2

swMATH ID: 44010
Software Authors: Jerome Revaud, Philippe Weinzaepfel, César De Souza, Noe Pion, Gabriela Csurka, Yohann Cabon, Martin Humenberger
Description: R2D2: Repeatable and Reliable Detector and Descriptor. Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor. Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection and learning descriptors at the detected keypoint locations. In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description. Furthermore, we claim that descriptors should be learned only in regions for which matching can be performed with high confidence. We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. This allows us to avoid ambiguous areas and leads to reliable keypoint detections and descriptions. Our detection-and-description approach, trained with self-supervision, can simultaneously output sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset. It also establishes a record on the recently released Aachen Day-Night localization dataset.
Homepage: https://arxiv.org/abs/1906.06195
Source Code:  https://github.com/naver/r2d2
Dependencies: Python
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV
Related Software: D2-Net; SuperPoint; HPatches; BRISK; LF-Net; SURF; SIFT; PointNet; SOSNet; L2-Net; Theia; SuperGlue; ORB-SLAM2; ORB-SLAM; MAGSAC++; ContextDesc; ASLFeat; FlowNet; MonoSLAM; Key.Net
Cited in: 3 Documents

Citations by Year