Papers › Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

1 Apr 2019ICCV 2019 10arXiv:1904.00889archive 2025-07-28

Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk

We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show that our approach outperforms state-of-the-art detectors in terms of repeatability, matching performance and complexity.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

axelBarroso/Key.Net officialmentioned in papermentioned on GitHubtf report
axelBarroso/Key.Net_Pytorch mentioned on GitHubpytorch report
bluedream1121/Key.Net_PyTorch mentioned on GitHubpytorch 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

Image MatchingKeypoint Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matching IMC PhotoTourism Key.Net-SOSNet mean average accuracy @ 10 0.60285 #5 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