This paper presents a novel Res2Net-based fusion framework for infrared and visible images. The proposed fusion model has three parts: an encoder, a fusion layer and a decoder, respectively. The Res2Net-based encoder is used to extract multi-scale features of source images, the paper introducing a new training strategy for training a Res2Net-based encoder that uses only a single image. Then, a new fusion strategy is developed based on the attention model. Finally, the fused image is reconstructed by the decoder. The proposed approach is also analyzed in detail. Experiments show that our method achieves state-of-the-art fusion performance in objective and subjective assessment by comparing with the existing methods.

翻译：本文提出了一种基于Res2Net的红外与可见光图像融合框架。所提出的融合模型由三部分组成：编码器、融合层和解码器。基于Res2Net的编码器用于提取源图像的多尺度特征，本文引入了一种仅使用单张图像训练Res2Net编码器的新训练策略。随后，基于注意力模型开发了一种新的融合策略。最后，解码器重建出融合图像。本文对所提方法进行了详细分析。实验表明，与现有方法相比，该方法在客观与主观评估中均达到了最先进的融合性能。