Standard
Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM. / Wulff-Jensen, Andreas; Rant, Niclas Nerup; Møller, Tobias Nordvig; Billeskov, Jonas Aksel.
Interactivity, Game Creation, Design, Learning, and Innovation: 6th International Conference, ArtsIT 2017 and Second International Conference, DLI 2017 Heraklion, Crete, Greece, October 30–31, 2017 Proceedings. ed. / Anthony L Brooks; Eva Brooks; Nikolas Vidakis. Cham : Springer, 2018. p. 85-94 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, Vol. 229).
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Wulff-Jensen, A, Rant, NN, Møller, TN & Billeskov, JA 2018,
Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM. in AL Brooks, E Brooks & N Vidakis (eds),
Interactivity, Game Creation, Design, Learning, and Innovation: 6th International Conference, ArtsIT 2017 and Second International Conference, DLI 2017 Heraklion, Crete, Greece, October 30–31, 2017 Proceedings. Springer, Cham, Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, vol. 229, pp. 85-94, 6th EAI International Conference on Interactivity and Game Creation, ArtsIT 2017 and the 2nd International Conference on Design, Learning and Innovation, DLI 2017, Heraklion, Greece,
30/10/2017.
https://doi.org/10.1007/978-3-319-76908-0_9
APA
Wulff-Jensen, A., Rant, N. N., Møller, T. N., & Billeskov, J. A. (2018).
Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM. In A. L. Brooks, E. Brooks, & N. Vidakis (Eds.),
Interactivity, Game Creation, Design, Learning, and Innovation: 6th International Conference, ArtsIT 2017 and Second International Conference, DLI 2017 Heraklion, Crete, Greece, October 30–31, 2017 Proceedings (pp. 85-94). Springer. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering Vol. 229
https://doi.org/10.1007/978-3-319-76908-0_9
Vancouver
Wulff-Jensen A, Rant NN, Møller TN, Billeskov JA.
Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM. In Brooks AL, Brooks E, Vidakis N, editors, Interactivity, Game Creation, Design, Learning, and Innovation: 6th International Conference, ArtsIT 2017 and Second International Conference, DLI 2017 Heraklion, Crete, Greece, October 30–31, 2017 Proceedings. Cham: Springer. 2018. p. 85-94. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, Vol. 229).
https://doi.org/10.1007/978-3-319-76908-0_9
Author
Wulff-Jensen, Andreas ; Rant, Niclas Nerup ; Møller, Tobias Nordvig ; Billeskov, Jonas Aksel. / Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM. Interactivity, Game Creation, Design, Learning, and Innovation: 6th International Conference, ArtsIT 2017 and Second International Conference, DLI 2017 Heraklion, Crete, Greece, October 30–31, 2017 Proceedings. editor / Anthony L Brooks ; Eva Brooks ; Nikolas Vidakis. Cham : Springer, 2018. pp. 85-94 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, Vol. 229).
Bibtex
@inproceedings{2704b83373f44845b15acbb36663a9f8,
title = "Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM",
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{\textquoteright} perceived realism and videogame usability was pilot tested, showing a promising future for DC-GAN generated 3D landscapes.",
keywords = "Faculty of Science, GAN, Deep Convolutional Generative Adversarial Network, PCG, Procedural generated landscapes, Digital Elevation Maps (DEM), Heightmaps, Games, 3D landscapes",
author = "Andreas Wulff-Jensen and Rant, {Niclas Nerup} and M{\o}ller, {Tobias Nordvig} and Billeskov, {Jonas Aksel}",
note = "(Ekstern); 6th EAI International Conference on Interactivity and Game Creation, ArtsIT 2017 and the 2nd International Conference on Design, Learning and Innovation, DLI 2017 ; Conference date: 30-10-2017 Through 31-10-2017",
year = "2018",
doi = "10.1007/978-3-319-76908-0_9",
language = "English",
isbn = " 978-3-319-76907-3",
series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering",
publisher = "Springer",
pages = "85--94",
editor = "Brooks, {Anthony L} and Eva Brooks and Nikolas Vidakis",
booktitle = "Interactivity, Game Creation, Design, Learning, and Innovation",
address = "Switzerland",
}
RIS
TY - GEN
T1 - Deep convolutional generative adversarial network for procedural 3D landscape generation based on DEM
AU - Wulff-Jensen, Andreas
AU - Rant, Niclas Nerup
AU - Møller, Tobias Nordvig
AU - Billeskov, Jonas Aksel
N1 - (Ekstern)
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
KW - Faculty of Science
KW - GAN
KW - Deep Convolutional Generative Adversarial Network
KW - PCG
KW - Procedural generated landscapes
KW - Digital Elevation Maps (DEM)
KW - Heightmaps
KW - Games
KW - 3D landscapes
U2 - 10.1007/978-3-319-76908-0_9
DO - 10.1007/978-3-319-76908-0_9
M3 - Article in proceedings
SN - 978-3-319-76907-3
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering
SP - 85
EP - 94
BT - Interactivity, Game Creation, Design, Learning, and Innovation
A2 - Brooks, Anthony L
A2 - Brooks, Eva
A2 - Vidakis, Nikolas
PB - Springer
CY - Cham
T2 - 6th EAI International Conference on Interactivity and Game Creation, ArtsIT 2017 and the 2nd International Conference on Design, Learning and Innovation, DLI 2017
Y2 - 30 October 2017 through 31 October 2017
ER -