RGB-IR Cross Input and Sub-Pixel Upsampling Network for Infrared Image Super-Resolution

Deep learning-based image super-resolution has shown significantly good performance inimproving image quality. In this paper, the RGB-IR cross input and sub-pixel upsampling networkis proposed to increase the spatial resolution of an Infrared (IR) image by combining it with a colorimage of higher spatial resolution obtained with a different imaging modality. Specifically, thisis accomplished by fusion of the features map of two RGB-IR inputs in the reconstruction of aninfrared image. To improve the accuracy of feature extraction, deconvolution is replaced by sub-pixelconvolution to upsample image in the network. Then, the guided filter layer is introduced for imagedenoising of IR images, and it can preserve the image detail. In addition, the experimental dataset,which is collected by us, contains large numbers of RGB images and corresponding IR images withthe same scene. Experimental results on our dataset and other datasets demonstrate that the methodis superior to existing methods in accuracy and visual improvement.