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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Qiao, Zhang, Yu, Zhao, Zijing, Zhang, Jian, Zhang, Shunli
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910459461894144
author Yang, Qiao
Zhang, Yu
Zhao, Zijing
Zhang, Jian
Zhang, Shunli
author_facet Yang, Qiao
Zhang, Yu
Zhao, Zijing
Zhang, Jian
Zhang, Shunli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14997
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network
Yang, Qiao
Zhang, Yu
Zhao, Zijing
Zhang, Jian
Zhang, Shunli
Computer Vision and Pattern Recognition
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.
title IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.14997