Super-Resolution of GF-1 Multispectral Wide Field of View Images via a Very Deep Residual Coordinate Attention Network

GF-1 multispectral wide field of view (WFV) images, with a spatial resolution of 16 m, have been widely used in Earth monitoring. However, the spatial details provided by WFV images are not sufficient for many applications. Thus, this letter proposes a novel WFV image super-resolution (SR) algorithm called Gaofen residual coordinate attention network (GFRCAN) based on a very deep residual coordinate attention network. To form a very deep network, the residual-in-residual (RIR) structure consisting of several residual groups (RGs) with long skip connections is used. Meanwhile, the residual coordinate attention block (RCOAB) and adaptive multiscale spatial attention module (AMSA) are incorporated to focus on the high-frequency information and multiscale features adaptive weighted fusion. Besides, the spectral and spatial details of SR images are improved by incorporating peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) into the loss function. Both subjective and objective evaluation results show that the proposed model outperforms the state-of-the-art methods.