Remote Sensing Image Colorization Based on Multiscale SEnet GAN

Abstract

Image colorization technique is to colorize the grayscale images or single-channel images. In the research of image colorization, the coloring of remote sensing images is a challenging problem. This paper proposes a new method of remote sensing image colorization method based on Deep Convolution Generative Adversarial Network (DCGAN). We combine multi-scale convolution with Squeeze-and-Excitation Networks (SEnet) to propose a new model that is applied to the generator of DCGAN. Therefore, the generator not only retains the largest image features in the process of the generating images, but also can adjust the channel weights in the training process. We have compared the proposed method with other image colorization methods, and the results show that the proposed method has a good performance on both human vision and image evaluation indicators on the colorization of remote sensing images.