Real-World DEM Super-Resolution Based on Generative Adversarial Networks for Improving InSAR Topographic Phase Simulation

Abstract

Topographic phase simulation is important for deformation estimation in differential synthetic aperture radar (SAR) interferometry. The most commonly used 30 m resolution shuttle radar topography mission (SRTM) digital elevation model (DEM) is usually required to be resampled due to its relatively low resolution (LR) comparing to the high resolution (HR) SAR images. Although the WorldDEM with a 12 m resolution achieves global coverage, it is not available freely. Consequently, it is useful to evaluate the practicability of the super-resolution (SR) from LR SRTM DEMs to HR WorldDEM ones, which has not been investigated. Most existing DEM SR models are trained with synthetic datasets in which the LR DEMs are downsampled from their HR counterparts. However, these models become less effective when applied to real-world scenarios due to the domain gap between the synthetic and real LR DEMs. In this article, we constructed a real-world DEM SR dataset, where the LR and HR DEMs were collected from SRTM and WorldDEM, respectively. An enhanced SR generative adversarial network model was adapted to train on the dataset. Considering that the real LR-HR pairs may suffer from misalignment, we introduced the perceptual loss for better optimizing the model. Moreover, a logarithmic normalization was proposed to compress the wide elevation range and adjust the uneven distribution. We also pretrained the model using natural images since collecting sufficient HR DEMs is costly. Experiments demonstrate that the proposed method achieves near 0.69 dB improvement of peak signal-to-noise ratio. In addition, our method is also validated to improve the topographic phase simulation by 23.42% of MSE.

Keywords

• Deep learning
• digital elevation model
• generative adversarial network
• InSAR topographic phase simulation
• super resolution (SR)