Terrain Self-Similarity-Based Transformer for Generating Super Resolution DEMs
Xin Zheng, Zelun Bao, Qian Yin
Abstract
High-resolution digital elevation models (DEMs) are important for relevant geoscience research and practical applications. Compared with traditional hardware-based methods, super-resolution (SR) reconstruction techniques are currently low-cost and feasible methods used for obtaining high-resolution DEMs. Single-image super-resolution (SISR) techniques have become popular in DEM SR in recent years. However, DEM super-resolution has not yet utilized reference-based image super-resolution (RefSR) techniques. In this paper, we propose a terrain self-similarity-based transformer (SSTrans) to generate super-resolution DEMs. It is a reference-based image super-resolution method that automatically acquires reference images using terrain self-similarity. To verify the proposed model, we conducted experiments on four distinct types of terrain and compared them to the results from the bicubic, SRGAN, and SRCNN approaches. The experimental results show that the SSTrans method performs well in all four terrains and has outstanding advantages in complex and uneven surface terrains.