Remote sensing image reconstruction using an asymmetric multi-scale super-resolution network

High-resolution (HR) remote sensing images demonstrate detailed geographical information; however, some remote sensing satellites are incapable of offering HR remote sensing images because of the restriction of hardware resources. The single-image super-resolution (SISR) reconstruction technique is considered as an important method to improve the resolution of remote sensing images; however, most super-resolution (SR) image reconstruction methods are not able to sufficiently extract and utilize image features, and there is much redundancy of network parameters. To address this problem, an asymmetric multi-scale super-resolution network (AMSSRN) is proposed. In this network, a residual multi-scale block (RMSB) and a residual multi-scale dilation block (RMSDB) are designed to extract both shallow and deep features from images. This asymmetric structure enables the deep features to be fully extracted while reducing the redundancy of the modules used to extract shallow features. In this work, a feature-refinement fusion (FRF) module is also established, which can make full use of extracted features to improve network performance. Experimental results indicate that compared with enhanced deep super-resolution (EDSR) network, the proposed AMSSRN can efficiently reduce the redundancy of network parameters and enhance the feature extraction capability: the maximum increases in peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) index can reach 0.23 dB and 0.9782, respectively.