IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network

TL;DR

This paper introduces IAIFNet, a novel image fusion network that enhances infrared and visible images by considering illumination conditions, resulting in clearer, more prominent targets for improved downstream vision tasks.

Contribution

The paper proposes a new illumination-aware fusion network with an illumination enhancement module, adaptive differential fusion, and salient target modules, advancing infrared-visible image fusion techniques.

Findings

Outperforms five state-of-the-art fusion methods

Produces images with clearer, more prominent targets

Enhances fusion quality in low-light environments

Abstract

Infrared and visible image fusion (IVIF) is used to generate fusion images with comprehensive features of both images, which is beneficial for downstream vision tasks. However, current methods rarely consider the illumination condition in low-light environments, and the targets in the fused images are often not prominent. To address the above issues, we propose an Illumination-Aware Infrared and Visible Image Fusion Network, named as IAIFNet. In our framework, an illumination enhancement network first estimates the incident illumination maps of input images. Afterwards, with the help of proposed adaptive differential fusion module (ADFM) and salient target aware module (STAM), an image fusion network effectively integrates the salient features of the illumination-enhanced infrared and visible images into a fusion image of high visual quality. Extensive experimental results verify that our method outperforms five state-of-the-art methods of fusing infrared and visible images.