Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2021 IEEE Conference on Games, CoG 2021 |
| Herausgeber (Verlag) | IEEE Computer Society |
| ISBN (elektronisch) | 9781665438865 |
| ISBN (Print) | 978-1-6654-4608-2 |
| Publikationsstatus | Veröffentlicht - 2021 |
| Veranstaltung | 2021 IEEE Conference on Games, CoG 2021 - Copenhagen, Dänemark Dauer: 17 Aug. 2021 → 20 Aug. 2021 |
Publikationsreihe
| Name | IEEE Conference on Computatonal Intelligence and Games, CIG |
|---|---|
| Band | 2021-August |
| ISSN (Print) | 2325-4270 |
| ISSN (elektronisch) | 2325-4289 |
Abstract
This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Computergrafik und computergestütztes Design
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
- Informatik (insg.)
- Mensch-Maschine-Interaktion
- Informatik (insg.)
- Software
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2021 IEEE Conference on Games, CoG 2021. IEEE Computer Society, 2021. 175285 (IEEE Conference on Computatonal Intelligence and Games, CIG; Band 2021-August).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - World-GAN
T2 - 2021 IEEE Conference on Games, CoG 2021
AU - Awiszus, Maren
AU - Schubert, Frederik
AU - Rosenhahn, Bodo
N1 - Funding Information: VI. ACKNOWLEDGMENT This work has been supported by the Federal Ministry of Education and Research (BMBF), Germany, under the project LeibnizKILabor (grant no. 01DD20003), the Federal Ministry for Economic Affairs and Energy under the Wipano programme ”NaturalAI” (03THW05K06), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungsgemein-schaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122). Publisher Copyright: © 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.
AB - This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.
KW - GAN
KW - Generation
KW - Level
KW - Minecraft
KW - PCG
KW - Representation
KW - Scales
KW - Sin-GAN
KW - Single Example
KW - Style
UR - http://www.scopus.com/inward/record.url?scp=85120762636&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2106.10155
DO - 10.48550/arXiv.2106.10155
M3 - Conference contribution
AN - SCOPUS:85120762636
SN - 978-1-6654-4608-2
T3 - IEEE Conference on Computatonal Intelligence and Games, CIG
BT - 2021 IEEE Conference on Games, CoG 2021
PB - IEEE Computer Society
Y2 - 17 August 2021 through 20 August 2021
ER -