Local Feature Extraction from Salient Regions by Feature Map Transformation

TL;DR

This paper introduces a robust local feature extraction framework that enhances feature matching accuracy across varying viewpoints and illumination conditions by focusing on salient regions and structural information.

Contribution

It presents a novel method that suppresses illumination effects and emphasizes structural features to improve local feature matching accuracy.

Findings

Achieved higher accuracy than state-of-the-art methods on public datasets.

Effectively handles highly variant viewpoints and illumination conditions.

Reduces incorrect feature matches by focusing on salient regions.

Abstract

Local feature matching is essential for many applications, such as localization and 3D reconstruction. However, it is challenging to match feature points accurately in various camera viewpoints and illumination conditions. In this paper, we propose a framework that robustly extracts and describes salient local features regardless of changing light and viewpoints. The framework suppresses illumination variations and encourages structural information to ignore the noise from light and to focus on edges. We classify the elements in the feature covariance matrix, an implicit feature map information, into two components. Our model extracts feature points from salient regions leading to reduced incorrect matches. In our experiments, the proposed method achieved higher accuracy than the state-of-the-art methods in the public dataset, such as HPatches, Aachen Day-Night, and ETH, which especially show highly variant viewpoints and illumination.