SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images

TL;DR

SwinFuse is a novel transformer-based fusion network that effectively combines infrared and visible images by modeling long-range dependencies and using a new feature fusion strategy, outperforming existing methods in quality and efficiency.

Contribution

The paper introduces SwinFuse, a pure transformer-based fusion network with a novel $L_{1}$-norm based fusion strategy, enhancing infrared and visible image fusion performance.

Findings

Outperforms nine state-of-the-art methods in experiments

Achieves strong generalization across datasets

Maintains competitive computational efficiency

Abstract

The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and convolution kernel, which may lose some important contexts and further limit fusion performance. Towards this end, we present a simple and strong fusion baseline for infrared and visible images, namely\textit{ Residual Swin Transformer Fusion Network}, termed as SwinFuse. Our SwinFuse includes three parts: the global feature extraction, fusion layer and feature reconstruction. In particular, we build a fully attentional feature encoding backbone to model the long-range dependency, which is a pure transformer network and has a stronger representation ability compared with the convolutional neural networks. Moreover, we design a novel feature fusion strategy based on $L_{1}$-norm for sequence matrices, and measure the corresponding activity levels from row and column vector dimensions, which can well retain competitive infrared brightness and distinct visible details. Finally, we testify our SwinFuse with nine state-of-the-art traditional and deep learning methods on three different datasets through subjective observations and objective comparisons, and the experimental results manifest that the proposed SwinFuse obtains surprising fusion performance with strong generalization ability and competitive computational efficiency. The code will be available at https://github.com/Zhishe-Wang/SwinFuse.