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 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.
PDF Abstract ICCV 2019 PDF ICCV 2019 AbstractCode
Datasets
HPatches
IMC PhotoTourism
Results from the Paper
Ranked #5 on
Image Matching
on IMC PhotoTourism
(using extra training data)
