An Attention-Guided and Wavelet-Constrained Generative Adversarial Network for Infrared and Visible Image Fusion

TL;DR

This paper introduces AWFGAN, a novel GAN-based method for infrared and visible image fusion that employs attention modules and wavelet constraints to enhance focus on key features and details, outperforming existing methods.

Contribution

The paper proposes a new GAN framework with attention-guided discrimination and wavelet-based constraints, addressing limitations of previous dual-discriminator approaches in image fusion.

Findings

Improved focus on target regions via spatial attention modules.

Enhanced high-frequency detail restoration through wavelet subspace discrimination.

Demonstrated superior performance on public datasets.

Abstract

The GAN-based infrared and visible image fusion methods have gained ever-increasing attention due to its effectiveness and superiority. However, the existing methods adopt the global pixel distribution of source images as the basis for discrimination, which fails to focus on the key modality information. Moreover, the dual-discriminator based methods suffer from the confrontation between the discriminators. To this end, we propose an attention-guided and wavelet-constrained GAN for infrared and visible image fusion (AWFGAN). In this method, two unique discrimination strategies are designed to improve the fusion performance. Specifically, we introduce the spatial attention modules (SAM) into the generator to obtain the spatial attention maps, and then the attention maps are utilized to force the discrimination of infrared images to focus on the target regions. In addition, we extend the discrimination range of visible information to the wavelet subspace, which can force the generator to restore the high-frequency details of visible images. Ablation experiments demonstrate the effectiveness of our method in eliminating the confrontation between discriminators. And the comparison experiments on public datasets demonstrate the effectiveness and superiority of the proposed method.