Abstract
Robust covariant local feature detectors are important
for detecting local features that are (1) discriminative of the
image content and (2) can be repeatably detected at consistent locations when the image undergoes diverse transformations. Such detectors are critical for applications such
as image search and scene reconstruction. Many learningbased local feature detectors address one of these two problems while overlooking the other. In this work, we propose
a novel learning-based method to simultaneously address
both issues. Specifically, we extend the covariant constraint
proposed by Lenc and Vedaldi [8] by defining the concepts
of “standard patch” and “canonical feature” and leverage these to train a novel robust covariant detector. We
show that the introduction of these concepts greatly simpli-
fies the learning stage of the covariant detector, and also
makes the detector much more robust. Extensive experiments show that our method outperforms previous handcrafted and learning-based detectors by large margins in
terms of repeatability