Key.Net swMATH ID: 31202 Software Authors: Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk Description: Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters. 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 this http URL 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. Homepage: https://arxiv.org/abs/1904.00889 Source Code: https://github.com/axelBarroso/Key.Net Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Keypoint Detection; CNN Filters; handcrafted; learned Related Software: SuperPoint; FlowNet; HPatches; PointNet; BRISK; SOSNet; L2-Net; Theia; R2D2; SuperGlue; ImageNet; PyTorch; ORB-SLAM2; DTAM; ORB-SLAM; MAGSAC++; D2-Net; ContextDesc; ASLFeat; Adam Cited in: 3 Publications Standard Articles 1 Publication describing the Software Year Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk 2019 all top 5 Cited by 8 Authors 1 Fan, Aoxiang 1 Jiang, Junjun 1 Jiang, Xingyu 1 Ma, Jiayi 1 Pavelyeva, E. A. 1 Protsenko, M. A. 1 Szeliski, Richard 1 Yan, Junchi Cited in 3 Serials 1 Computational Mathematics and Modeling 1 International Journal of Computer Vision 1 Texts in Computer Science Cited in 2 Fields 3 Computer science (68-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year