A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer
This addresses DEM super-resolution for remote sensing applications, representing an incremental improvement with a novel hybrid transformer model.
The paper tackles the problem of generating high-resolution Digital Elevation Models (DEMs) using multi-spectral satellite imagery as guidance, achieving superior performance with sharper details and minimal errors compared to baseline methods across 4 datasets.
Digital Elevation Model (DEM) is an essential aspect in the remote sensing (RS) domain to analyze various applications related to surface elevations. Here, we address the generation of high-resolution (HR) DEMs using HR multi-spectral (MX) satellite imagery as a guide by introducing a novel hybrid transformer model consisting of Densely connected Multi-Residual Block (DMRB) and multi-headed Frequency Selective Graph Attention (M-FSGA). To promptly regulate this process, we utilize the notion of discriminator spatial maps as the conditional attention to the MX guide. Further, we present a novel adversarial objective related to optimizing Sinkhorn distance with classical GAN. In this regard, we provide both theoretical and empirical substantiation of better performance in terms of vanishing gradient issues and numerical convergence. Based on our experiments on 4 different DEM datasets, we demonstrate both qualitative and quantitative comparisons with available baseline methods and show that the performance of our proposed model is superior to others with sharper details and minimal errors.