A region-based descriptor network for uniformly sampled keypoints

TL;DR

This paper introduces a region-based descriptor network that leverages context features to improve keypoint matching robustness, especially in flat regions, eliminating the need for extremum point schemes.

Contribution

The proposed descriptor combines deep network context features to enable robust matching without extremum detection, simplifying the keypoint matching process.

Findings

Achieves performance comparable to state-of-the-art methods.

Provides more high-confidence matching points in flat regions.

Eliminates the need for complex extremum point schemes.

Abstract

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.