Remote Sensing Image Super-Resolution Using Novel Dense-Sampling Networks

Super-resolution (SR) techniques play a crucial role in increasing the spatial resolution of remote sensing data and overcoming the physical limitations of the spaceborne imaging systems. Though the convolutional neural network (CNN)-based methods have obtained good performance, they show limited capacity when coping with large-scale super-resolving tasks. The more complicated spatial distribution of remote sensing data further increases the difficulty in reconstruction. This article develops a dense-sampling super-resolution network (DSSR) to explore the large-scale SR reconstruction of the remote sensing imageries. Specifically, a dense-sampling mechanism, which reuses an upscaler to upsample multiple low-dimension features, is presented to make the network jointly consider multilevel priors when performing reconstruction. A wide feature attention block (WAB), which incorporates the wide activation and attention mechanism, is introduced to enhance the representation ability of the network. In addition, a chain training strategy is proposed to optimize further the performance of the large-scale models by borrowing knowledge from the pretrained small-scale models. Extensive experiments demonstrate the effectiveness of the proposed methods and show that the DSSR outperforms the state-of-the-art models in both quantitative evaluation and visual quality.

I. Introduction

Super-resolution (SR) reconstruction is a key research in the remote sensing community. It aims at enhancing the imagery resolution through reconstructing high-frequency information from low-resolution (LR) observations. In general, the spatial resolution of spaceborne imaging systems is inevitably limited by factors like orbit altitude, revisit cycle, and instantaneous field of view [1], [32]. This is largely different from common imaging devices such as camera. Hence, once a satellite is launched, SR is the most effective postprocessing technique to improve further the spatial resolution.