Visible and Infrared Image Fusion Using Encoder-Decoder Network

TL;DR

This paper introduces a novel convolutional encoder-decoder network for infrared and visible image fusion, achieving superior quality and real-time performance on embedded devices through a learning-based approach.

Contribution

It presents a new learning-based image fusion method using only convolution and pooling layers, with no-reference quality metrics, outperforming existing methods.

Findings

Better fusion quality than state-of-the-art methods.

Real-time performance on embedded devices.

Qualitative and quantitative analysis confirms effectiveness.

Abstract

The aim of multispectral image fusion is to combine object or scene features of images with different spectral characteristics to increase the perceptual quality. In this paper, we present a novel learning-based solution to image fusion problem focusing on infrared and visible spectrum images. The proposed solution utilizes only convolution and pooling layers together with a loss function using no-reference quality metrics. The analysis is performed qualitatively and quantitatively on various datasets. The results show better performance than state-of-the-art methods. Also, the size of our network enables real-time performance on embedded devices. Project codes can be found at \url{https://github.com/ferhatcan/pyFusionSR}.