Papers › R2D2: Reliable and Repeatable Detector and Descriptor

R2D2: Reliable and Repeatable Detector and Descriptor

1 Dec 2019NeurIPS 2019 12archive 2025-07-28

Jerome Revaud, Cesar De Souza, Martin Humenberger, Philippe Weinzaepfel

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical approaches 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 or learning descriptors at the detected keypoint locations. In this work, we argue that repeatable regions are not necessarily discriminative and can therefore lead to select suboptimal keypoints. 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 to avoid ambiguous areas, thus leading to reliable keypoint detection and description. Our detection-and-description approach simultaneously outputs sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset and on the recent Aachen Day-Night localization benchmark.

PaperPDFCode

Code

naver/r2d2 officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari GamesCamera LocalizationImage MatchingInterest Point DetectionKeypoint DetectionMetric Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camera Localization Aachen Day-Night benchmark R2D2 WASF N8 (full scale, 10K kpts) Acc @ 0.5m, 2° 45.9 #2 of 2 Archive leaderboard report
Camera Localization Aachen Day-Night benchmark R2D2 WASF N8 (full scale, 10K kpts) Acc @ 1m, 5° 66.3 #2 of 2 Archive leaderboard report
Camera Localization Aachen Day-Night benchmark R2D2 WASF N8 (full scale, 10K kpts) Acc @ 5m, 10° 88.8 #2 of 2 Archive leaderboard report
Image Matching IMC PhotoTourism R2D2 mean average accuracy @ 10 0.56345 #7 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections