Generation of Synthetic Elevation Models and Realistic Surface Images of River Deltas and Coastal Terrains Using cGANs

Terrain generation aims to automatize the procedure of creating landscapes using a computer system. The models must follow different terrains' topographical features, such as areas with river deltas and other regions where water bodies affect natural landscapes. It is possible generate more realistic terrains thanks improvements in graphics techniques deep learning that use specific hardware. However, advance on include deltas, fjords, waterfalls has not had same pace studied Therefore, contribution research terrain generative models, this paper presents DRCA2020 dataset, which useful for supervised training. proposed dataset contains eight types real-world satellite images. These images are grouped by geographical location. There 13,184 groups; each one three RGB surface images, coverage map, binarizations coverage, digital elevation model (DEM). Additionally, proposes cGAN composite model, trained generating synthetic DEMs from therefore, create texture promising validation results.