Multi-scale terrain texturing using generative adversarial networks

Jonathan Klein, Stefan Hartmann, Michael Weinmann, Dominik Michels

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

We propose a novel, automatic generation process for detail maps that allows the reduction of tiling artifacts in real-time terrain rendering. This is achieved by training a generative adversarial network (GAN) with a single input texture and subsequently using it to synthesize a huge texture spanning the whole terrain. The low-frequency components of the GAN output are extracted, down-scaled and combined with the high-frequency components of the input texture during rendering. This results in a terrain texture that is both highly detailed and non-repetitive, which eliminates the tiling artifacts without decreasing overall image quality. The rendering is efficient regarding both memory consumption and computational costs. Furthermore, it is orthogonal to other techniques for terrain texture improvements such as texture splatting and can directly be combined with them.

Original languageEnglish (US)
Title of host publication2017 International Conference on Image and Vision Computing New Zealand, IVCNZ 2017
PublisherIEEE Computer Society
Pages1-6
Number of pages6
ISBN (Electronic)9781538642764
DOIs
StatePublished - Jul 3 2018
Event2017 International Conference on Image and Vision Computing New Zealand, IVCNZ 2017 - Christchurch, New Zealand
Duration: Dec 4 2017Dec 6 2017

Publication series

NameInternational Conference Image and Vision Computing New Zealand
Volume2017-December
ISSN (Print)2151-2191
ISSN (Electronic)2151-2205

Conference

Conference2017 International Conference on Image and Vision Computing New Zealand, IVCNZ 2017
CountryNew Zealand
CityChristchurch
Period12/4/1712/6/17

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-scale terrain texturing using generative adversarial networks'. Together they form a unique fingerprint.

Cite this