Matching keypoint pairs of different images is a basic task of computer vision. Most methods require customized extremum point schemes to obtain the coordinates of feature points with high confidence, which often need complex algorithmic design or a network with higher training difficulty and also ignore the possibility that flat regions can be used as candidate regions of matching points. In this paper, we design a region-based descriptor by combining the context features of a deep network. The new descriptor can give a robust representation of a point even in flat regions. By the new descriptor, we can obtain more high confidence matching points without extremum operation. The experimental results show that our proposed method achieves a performance comparable to state-of-the-art.
@article{arxiv.2103.01780,
title = {A region-based descriptor network for uniformly sampled keypoints},
author = {Kai Lv and Zongqing Lu and Qingmin Liao},
journal= {arXiv preprint arXiv:2103.01780},
year = {2021}
}