LAUSR

Remote sensing images are essential in many fields, such as land cover classification and building extraction. The huge difference between the directly acquired remote sensing images and the actual scene, due to the complex degradation process and hardware limitations, seriously affects the performance achieved by the same classification or segmentation model. Therefore, using super-resolution (SR) algorithms to improve image quality and achieve better results is an effective method. However, current SR methods only focus on the similarity of pixel values between SR and high-resolution (HR) images without considering perceptual similarities, which usually leads to the problem of oversmoothed and blurred edge details. Moreover, there is little attention to human visual habits and machine vision applications for remote sensing images. In this work, we propose the context aware edge-enhanced generative adversarial network (CEEGAN) SR framework to reconstruct visually pleasing images that can be practically applied in actual scenarios. In the generator of CEEGAN, we build an edge feature enhanced module (EFEM) to enhance the edges by combining the edge features with context information. Edge restoration block is designed to fuse multiscale edge features enhanced by EFEM and reconstruct a refined edge map. Furthermore, we designed an edge loss function to constrain the generated SR and HR similarity at the edge domain. Experimental results show that our proposed method can obtain SR images with a better reconstruction performance. Meanwhile, CEEGAN can achieve the best results on classification and semantic segmentation datasets for machine vision applications.