MrFDDGAN: Multireceptive Field Feature Transfer and Dual Discriminator-Driven Generative Adversarial Network for Infrared and Color Visible Image Fusion

Most of the previous infrared and visible image fusion methods based on deep learning were on the basis of gray-scale images and used the single convolution kernel receptive field to extract deep features, which would inevitably cause information loss in the process of feature transfer. Accordingly, this article proposes a new generative adversarial network fusion architecture based on multireceptive field feature transfer and dual discriminator, which is named MrFDDGAN. It is applied to infrared and color visible image fusion. First, three different receptive fields are used to extract multiscale and multilevel deep features of multimodal images on three channels, so as to obtain significant features of source images from multiview and multiperspective in a more comprehensive way. Second, a feature interaction module is introduced in the encoder to realize the information interaction and information prefusion among the three feature channels. Third, the multilevel features fused in the encoder are cascaded with the deep features in the decoder to enhance feature transfer and feature reuse. Finally, this experiment adopts a dual discriminator adversarial network structure to keep the balance of infrared image intensity and visible image texture preserved by fusion results. Qualitative and quantitative experimental analyses are carried out on two public datasets of gray-scale infrared and visible images, and one dataset of infrared and color visible images. The experimental results prove that the proposed MrFDDGAN algorithm has a better subjective visual effect and objective performance than the existing state-of-the-art fusion methods.