×

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

Citations by Year