NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models

TL;DR

NestFuse introduces a novel infrared and visible image fusion method utilizing nest connections and spatial/channel attention models, achieving superior fusion quality through multi-scale feature extraction and reconstruction.

Contribution

The paper presents a new neural network architecture with nest connections and attention mechanisms specifically designed for infrared and visible image fusion.

Findings

Outperforms existing state-of-the-art methods in fusion quality

Demonstrates superior subjective visual results

Achieves higher objective evaluation metrics

Abstract

In this paper we propose a novel method for infrared and visible image fusion where we develop nest connection-based network and spatial/channel attention models. The nest connection-based network can preserve significant amounts of information from input data in a multi-scale perspective. The approach comprises three key elements: encoder, fusion strategy and decoder respectively. In our proposed fusion strategy, spatial attention models and channel attention models are developed that describe the importance of each spatial position and of each channel with deep features. Firstly, the source images are fed into the encoder to extract multi-scale deep features. The novel fusion strategy is then developed to fuse these features for each scale. Finally, the fused image is reconstructed by the nest connection-based decoder. Experiments are performed on publicly available datasets. These exhibit that our proposed approach has better fusion performance than other state-of-the-art methods. This claim is justified through both subjective and objective evaluation. The code of our fusion method is available at https://github.com/hli1221/imagefusion-nestfuse