Remote Sensing Image Mode Translation by Spatial Disentangled Representation Based GAN

Resting on the translation framework of spatially separated images, we proposed a cycle-consistent generative adversarial network (GAN) based on spatial disentangled representation to address the large mode difference and difficult translation between synthetic aperture radar images and optical remote sensing images. The proposed model separates images into style and content features by a deeper network layer and jump connection. Furthermore, the content features arc translated by content mapping learning and combined with target style features for image translation. In addition, PatchGAN, as the discriminator, enhances the image detail generation, and target error loss and generation & reconstruction loss arc introduced to limit the translation task to one-to-one mapping, thus reducing the information added and constraining the GAN. The experimental results in SEN1-2, SARptical, and WHU-SEN-City datasets show that compared with other image translation algorithms, the proposed method can translate two types of remote sensing images and generate images of high resolution, complete detail features, and strong authenticity.