Home » Single publication

Deep Terrain Expansion: Terrain Texture Synthesis with Deep Learning

Vasileios Toulatzis and Ioannis Fudos
Computer Graphics & Visual Computing (CGVC) 2019, Bangor, UK

Result of deep terrain expansion

Abstract

In real-world applications terrains play a cardinal role in the field of games and geospatial applications such as Geographic Information Systems (GIS). Furthermore, the textures of a terrain are essential for creating virtual photorealistic environments for users. In many cases, the entire texture of a region is not available in high resolution or is much smaller than the required texture to cover a terrain. Tiling of a texture across a terrain usually fails to provide an acceptable approach for achieving a realistic terrain appearance. Enlargement of texture is an additional inappropriate method for resolving the aforementioned issue due to image quality reduction and the emergent distortion on the output image. As a consequence, high quality texture synthesis is a central issue to such settings. In this paper, we are exploring a novel methodology that extends previous work providing both synthesis and expansion of terrain textures. Our method is also appropriate for other applications beyond artificial terrain construction and for generating smaller sized textures, as well.
View bibtex
View paper
Presentation
Link
@inproceedings {vc.20191262,
booktitle = {Computer Graphics and Visual Computing (CGVC)},
editor = {Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.},
title = {{Deep Terrain Expansion: Terrain Texture Synthesis with Deep Learning}},
author = {Toulatzis, Vasilis and Fudos, Ioannis},
year = {2019},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-096-3},
DOI = {10.2312/cgvc.20191262}
}

close

Go back to Publications