Multiscale Residual Dense Network for the Super-Resolution of Remote Sensing Images

Super-resolution (SR) reconstruction of remote sensing images (RSIs) aims to improve image resolution while ensuring accurate spatial texture information. In most multiscale SR methods, the feature fusion at each layer contains only the multiscale features of the current layer. However, this approach does not optimally use these multiscale features over different layers, leading to their gradual disappearance during the process of transmission. To address this problem, we propose a multiscale residual dense network (MRDN) for SR. The feature fusion of each layer in MRDN contains multiscale features from all preceding layers, rather than only fusing the features of the current layer. Specifically, MRDN concatenates the output of each layer and passes it to the subsequent multiscale layers to facilitate feature fusion. MRDN maximizes the utilization of hierarchical features from the original low-resolution images (LRIs), enabling adaptive learning of more effective features. In addition, efficient MRDN does not necessitate a substantial increase in network depth and complexity to achieve high performance. Experimental results indicate that MRDN outperforms the state-of-the-art methods on three remote sensing (RS) datasets. To demonstrate the generalizability of MRDN, we extend its application to three relevant tasks: natural image SR, real-world image SR, and small object recognition. MRDN achieves competitive results on these tasks, confirming its generalizability.