A Prediction-to-Prediction Remote Sensing Image Super-Resolution Network under a Multi-Level Supervision Paradigm

Super-resolution enhances the spatial resolution of remote sensing images, yielding clearer data for diverse satellite applications. However, existing methods often lose true detail and produce pseudo-detail in reconstructed images due to an insufficient number of ground truth images for supervision. To address this issue, a prediction-to-prediction super-resolution (P2P-SR) network under a multi-level supervision paradigm was proposed. First, a multi-level supervision network structure was proposed to increase the number of supervisions by introducing more ground truth images, which made the network always predict the next level based on the super-resolution reconstruction results of the previous level. Second, a super-resolution component combining a convolutional neural network and Transformer was designed with a flexible super-resolution scale factor to facilitate the construction of multi-level supervision networks. Finally, a method of dividing the super-resolution overall scale factor was proposed, enabling an investigation into the impact of diverse numbers of components and different scale factors of components on the performance of the multi-level supervision network. Additionally, a new remote sensing dataset containing worldwide scenes was also constructed for the super-resolution task in this paper. The experiment results on three datasets demonstrated that our P2P-SR network outperformed the state-of-the-art (SOTA) methods.