TY  - CONF
AU  - Axel Barroso-Laguna
AU  - Edgar Riba
AU  - Daniel Ponsa
AU  - Krystian Mikolajczyk
A2  - ICCV
PY  - 2019//
TI  - Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
BT  - 18th IEEE International Conference on Computer Vision
SP  - 5835
EP  - 5843
N2  - 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.
UR  - https://ieeexplore.ieee.org/document/9010664
L1  - http://refbase.cvc.uab.es/files/BRP2019.pdf
UR  - http://dx.doi.org/10.1109/ICCV.2019.00593
N1  - MSIAU; 600.122
ID  - Axel Barroso-Laguna2019
ER  -