DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching

Understand

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes.

• In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods.
• The key insight is that local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features.
• Based on this, we propose a Slimming Transformer (SlimFormer) dedicated for DeepMatcher, which leverages vector-based attention to model relevance among all keypoints and achieves long-range context aggregation in an efficient and effective manner.