PT Unknown
AU Axel Barroso-Laguna
   Edgar Riba
   Daniel Ponsa
   Krystian Mikolajczyk
TI Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
BT 18th IEEE International Conference on Computer Vision
PY 2019
BP 5835
EP 5843
DI 10.1109/ICCV.2019.00593
AB 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.
ER