Local Feature Extraction from Salient Regions by Feature Map Transformation
This addresses a key problem in computer vision applications like localization and 3D reconstruction, though it appears incremental as it builds on existing feature extraction approaches.
The paper tackles the challenge of accurately matching local feature points across varying camera viewpoints and illumination conditions by proposing a framework that suppresses illumination variations and focuses on structural information. Their method achieved higher accuracy than state-of-the-art methods on public datasets like HPatches, Aachen Day-Night, and ETH.
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.