DenseFuse: A Fusion Approach to Infrared and Visible Images

TL;DR

DenseFuse introduces a deep learning architecture with dense connections for infrared and visible image fusion, achieving state-of-the-art results in both objective and subjective evaluations.

Contribution

The paper proposes a novel dense convolutional network architecture specifically designed for infrared and visible image fusion, improving feature extraction and fusion performance.

Findings

Achieves state-of-the-art fusion quality in experiments.

Outperforms existing methods in objective metrics.

Provides open-source code and pre-trained models.

Abstract

In this paper, we present a novel deep learning architecture for infrared and visible images fusion problem. In contrast to conventional convolutional networks, our encoding network is combined by convolutional layers, fusion layer and dense block in which the output of each layer is connected to every other layer. We attempt to use this architecture to get more useful features from source images in encoding process. And two fusion layers(fusion strategies) are designed to fuse these features. Finally, the fused image is reconstructed by decoder. Compared with existing fusion methods, the proposed fusion method achieves state-of-the-art performance in objective and subjective assessment. Code and pre-trained models are available at https://github.com/hli1221/imagefusion_densefuse