Scene-Aware Feature Matching

TL;DR

This paper introduces SAM, a scene-aware feature matching model that uses attentional grouping to improve robustness and interpretability in challenging scenes, achieving state-of-the-art results.

Contribution

The paper proposes a novel scene-aware feature matching approach with attentional grouping, enhancing robustness and interpretability over traditional point-level methods.

Findings

Achieves state-of-the-art performance on homography and pose estimation tasks.

Improves robustness in scenes with large viewpoint and illumination changes.

Provides more interpretable feature matching results.

Abstract

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when handling challenging scenes such as scenes with large viewpoint and illumination changes. To tackle this problem, we propose a novel model named SAM, which applies attentional grouping to guide Scene-Aware feature Matching. SAM handles multi-level features, i.e., image tokens and group tokens, with attention layers, and groups the image tokens with the proposed token grouping module. Our model can be trained by ground-truth matches only and produce reasonable grouping results. With the sense-aware grouping guidance, SAM is not only more accurate and robust but also more interpretable than conventional feature matching models. Sufficient experiments on various applications, including homography estimation, pose estimation, and image matching, demonstrate that our model achieves state-of-the-art performance.