High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network

TL;DR

This paper introduces a deep memory connected network (DMCN) for remote sensing image super-resolution, effectively combining image details and environmental context to produce high-quality images with improved accuracy and visual quality.

Contribution

The paper presents a novel DMCN architecture with local and global memory connections and downsampling units, enhancing super-resolution performance while reducing parameters.

Findings

Outperforms current state-of-the-art methods in accuracy

Provides better visual quality of super-resolved images

Demonstrates effectiveness across multiple remote sensing datasets

Abstract

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the neural network usually have small receptive fields and ignore the image detail. We propose a novel method named deep memory connected network (DMCN) based on a convolutional neural network to reconstruct high-quality super-resolution images. We build local and global memory connections to combine image detail with environmental information. To further reduce parameters and ease time-consuming, we propose downsampling units, shrinking the spatial size of feature maps. We test DMCN on three remote sensing datasets with different spatial resolution. Experimental results indicate that our method yields promising improvements in both accuracy and visual performance over the current state-of-the-art.