Deep Convolutional Generative Adversarial Network for Procedural 3D Landscape Generation Based on DEM

Research output: Contribution to journalConference article in JournalResearchpeer-review

Abstract

This paper proposes a novel framework for improving procedural generation of 3D landscapes using machine learning. We utilized a Deep Convolutional Generative Adversarial Network (DC-GAN) to generate heightmaps. The network was trained on a dataset consisting of Digital Elevation Maps (DEM) of the alps. During map generation, the batch size and learning rate were optimized for the most efficient and satisfying map production. The diversity of the final output was tested against Perlin noise using Mean Square Error [1] and Structure Similarity Index [2]. Perlin noise is especially interesting as it has been used to generate game maps in previous productions [3, 4]. The diversity test showed the generated maps had a significantly greater diversity than the Perlin noise maps. Afterwards the heightmaps was converted to 3D maps in Unity3D. The 3D maps’ perceived realism and videogame usability was pilot tested, showing a promising future for DC-GAN generated 3D landscapes.
Close

Details

This paper proposes a novel framework for improving procedural generation of 3D landscapes using machine learning. We utilized a Deep Convolutional Generative Adversarial Network (DC-GAN) to generate heightmaps. The network was trained on a dataset consisting of Digital Elevation Maps (DEM) of the alps. During map generation, the batch size and learning rate were optimized for the most efficient and satisfying map production. The diversity of the final output was tested against Perlin noise using Mean Square Error [1] and Structure Similarity Index [2]. Perlin noise is especially interesting as it has been used to generate game maps in previous productions [3, 4]. The diversity test showed the generated maps had a significantly greater diversity than the Perlin noise maps. Afterwards the heightmaps was converted to 3D maps in Unity3D. The 3D maps’ perceived realism and videogame usability was pilot tested, showing a promising future for DC-GAN generated 3D landscapes.
Original languageEnglish
JournalLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume229
Issue number1
Pages (from-to)85-94
Number of pages10
ISSN1867-8211
DOI
StatePublished - 7 Mar 2018
Publication categoryResearch
Peer-reviewedYes
Event6th EAI International Conference on Arts and Technology, Interactivity & Game Creation - Heraklion, Greece
Duration: 30 Oct 201731 Oct 2017
http://artsit.org/2017/show/home

Conference

Conference6th EAI International Conference on Arts and Technology, Interactivity & Game Creation
CountryGreece
CityHeraklion
Period30/10/201731/10/2017
Internet address

    Research areas

  • GAN, Deep Convolutional Generative Adversarial Network, PCG, procedural generated landscapes, Digital Elevation Maps, DEM, heightmaps, games, 3D landscapes

Map

Download statistics

No data available
ID: 272397392