A Review of Image Super-Resolution Approaches Based on Deep Learning and Applications in Remote Sensing

Abstract

At present, with the advance of satellite image processing technology, remote sensing images are becoming more widely used in real scenes. However, due to the limitations of current remote sensing imaging technology and the influence of the external environment, the resolution of remote sensing images often struggles to meet application requirements. In order to obtain high-resolution remote sensing images, image super-resolution methods are gradually being applied to the recovery and reconstruction of remote sensing images. The use of image super-resolution methods can overcome the current limitations of remote sensing image acquisition systems and acquisition environments, solving the problems of poor-quality remote sensing images, blurred regions of interest, and the requirement for high-efficiency image reconstruction, a research topic that is of significant relevance to image processing. In recent years, there has been tremendous progress made in image super-resolution methods, driven by the continuous development of deep learning algorithms. In this paper, we provide a comprehensive overview and analysis of deep-learning-based image super-resolution methods. Specifically, we first introduce the research background and details of image super-resolution techniques. Second, we present some important works on remote sensing image super-resolution, such as training and testing datasets, image quality and model performance evaluation methods, model design principles, related applications, etc. Finally, we point out some existing problems and future directions in the field of remote sensing image super-resolution.

comprehensive review of image super-resolution metrics: classical and AI-based approaches

“…MISR techniques use multiple low-resolution images of the same scene to reconstruct a high-resolution image. Classical super-resolution techniques can be interpolation-based (e.g., bicubic interpolation, resampling) or model-based (e.g., sparse coding, dictionary learning) [3].…”

“…However, acquiring high-resolution images directly can be difficult due to hardware limitations, imaging conditions, and other factors. SR overcomes this challenge by reconstructing HR images from LR inputs using sophisticated algorithms to infer and restore the missing details [3].…”

A Novel Implicit Neural Representation for Volume Data

“…For some of the deep learning techniques in SR, overfitting is highly likely and models can be so big to be stored. To address these issues, a deeply recursive convolutional network (DRCN) [36] is suggested. In DRCN, a convolutional layer is repeated many times and the number of parameters depends on the number of applied recursions.…”

A Lightweight Image Super-Resolution Reconstruction Algorithm Based on the Residual Feature Distillation Mechanism

“…To address this inverse problem, numerous super-resolution reconstruction methods have been proposed. Currently, SISR (single-image super-resolution) algorithms can be broadly classified into three categories: interpolation methods [ 5 , 6 , 7 , 8 ], reconstruction methods [ 9 , 10 , 11 , 12 ], and learning-based approaches [ 13 , 14 ]. Interpolation-based methods utilize surrounding pixel information to predict unknown pixels based on the assumption of image continuity.…”