LoFLAT: Local Feature Matching using Focused Linear Attention Transformer

TL;DR

LoFLAT introduces a novel focused linear attention transformer for local feature matching that improves accuracy and efficiency over existing methods by capturing detailed local interactions with low computational cost.

Contribution

The paper proposes LoFLAT, a new local feature matching method using focused linear attention, enhancing detail capture while maintaining low complexity.

Findings

LoFLAT outperforms LoFTR in accuracy.

LoFLAT achieves higher efficiency in feature matching.

Experimental results validate the robustness of LoFLAT.

Abstract

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges due to the quadratic computational complexity of attention mechanisms, especially at high resolutions. However, while existing Transformer-based detector-free local feature matching methods have reduced computational costs using linear attention mechanisms, they still struggle to capture detailed local interactions, which affects the accuracy and robustness of precise local correspondences. In order to enhance representations of attention mechanisms while preserving low computational complexity, we propose the LoFLAT, a novel Local Feature matching using Focused Linear Attention Transformer in this paper. Our LoFLAT consists of three main modules: the Feature Extraction Module, the Feature Transformer Module, and the Matching Module. Specifically, the Feature Extraction Module firstly uses ResNet and a Feature Pyramid Network to extract hierarchical features. The Feature Transformer Module further employs the Focused Linear Attention to refine attention distribution with a focused mapping function and to enhance feature diversity with a depth-wise convolution. Finally, the Matching Module predicts accurate and robust matches through a coarse-to-fine strategy. Extensive experimental evaluations demonstrate that the proposed LoFLAT outperforms the LoFTR method in terms of both efficiency and accuracy.