DTRN: Dual Transformer Residual Network for Remote Sensing Super-Resolution

The synergy of the transformer and the convolutional neural network (CNN) has been well regarded as a promising technique for single image super-resolution (SISR) based on low-quality satellite remote sensing images. In this work, a Dual Transformer Residual Network (DTRN) consisting of one transformer branch and one CNN-based residual branch is proposed. More specifically, the transformer branch is designed to capture the global relationships of feature maps by exploiting three pairs of token embedding blocks and convolutional transformer blocks (CTB). Furthermore, the residual branch employs several residual blocks (resblocks) to effectively learn hierarchical features through global feature fusion. Extensive experiments on a large-scale remote sensing dataset called OLI2MSI confirm the superior performance of the proposed DTRN as compared to the existing SISR methods.