Keiki: Towards Realistic Danmaku Generation via Sequential GANs

Ziqi WANG; Jialin LIU; Georgios N. YANNAKAKIS

doi:10.1109/CoG52621.2021.9619013

Keiki: Towards Realistic Danmaku Generation via Sequential GANs

Ziqi WANG, Jialin LIU, Georgios N. YANNAKAKIS

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

1 Citation (Scopus)

Abstract

The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games.

Original language	English
Title of host publication	Proceedings of the 2021 IEEE Conference on Games, CoG 2021
Publisher	IEEE Computer Society
Number of pages	4
ISBN (Electronic)	9781665438865
DOIs	https://doi.org/10.1109/CoG52621.2021.9619013
Publication status	Published - 2021
Externally published	Yes
Event	2021 IEEE Conference on Games, CoG 2021 - Copenhagen, Denmark Duration: 17 Aug 2021 → 20 Aug 2021

Publication series

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
Volume	2021-August
ISSN (Print)	2325-4270
ISSN (Electronic)	2325-4289

Conference

Conference	2021 IEEE Conference on Games, CoG 2021
Country/Territory	Denmark
City	Copenhagen
Period	17/08/21 → 20/08/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

This work was supported by the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (Grant No. 2017ZT07X386), the Guangdong Basic and Applied Basic Research Foundation (Grant No. 2021A1515011830), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531) and the Shenzhen Fundamental Research Program (Grant No. JCYJ20190809121403553).

Keywords

bullet hell
generative adversarial net
level generation
Procedural content generation
time-series GAN

Access to Document

10.1109/CoG52621.2021.9619013

Cite this

@inproceedings{1cd85750f3cc4428aade56b5e0aa110b,

title = "Keiki: Towards Realistic Danmaku Generation via Sequential GANs",

abstract = "The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games.",

keywords = "bullet hell, generative adversarial net, level generation, Procedural content generation, time-series GAN",

author = "Ziqi WANG and Jialin LIU and YANNAKAKIS, {Georgios N.}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Conference on Games, CoG 2021 ; Conference date: 17-08-2021 Through 20-08-2021",

year = "2021",

doi = "10.1109/CoG52621.2021.9619013",

language = "English",

series = "IEEE Conference on Computatonal Intelligence and Games, CIG",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of the 2021 IEEE Conference on Games, CoG 2021",

address = "United States",

}

WANG, Z, LIU, J & YANNAKAKIS, GN 2021, Keiki: Towards Realistic Danmaku Generation via Sequential GANs. in Proceedings of the 2021 IEEE Conference on Games, CoG 2021. IEEE Conference on Computatonal Intelligence and Games, CIG, vol. 2021-August, IEEE Computer Society, 2021 IEEE Conference on Games, CoG 2021, Copenhagen, Denmark, 17/08/21. https://doi.org/10.1109/CoG52621.2021.9619013

Keiki: Towards Realistic Danmaku Generation via Sequential GANs. / WANG, Ziqi; LIU, Jialin; YANNAKAKIS, Georgios N.
Proceedings of the 2021 IEEE Conference on Games, CoG 2021. IEEE Computer Society, 2021. (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2021-August).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - Keiki: Towards Realistic Danmaku Generation via Sequential GANs

AU - WANG, Ziqi

AU - LIU, Jialin

AU - YANNAKAKIS, Georgios N.

PY - 2021

Y1 - 2021

N2 - The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games.

AB - The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games.

KW - bullet hell

KW - generative adversarial net

KW - level generation

KW - Procedural content generation

KW - time-series GAN

UR - http://www.scopus.com/inward/record.url?scp=85122938750&partnerID=8YFLogxK

U2 - 10.1109/CoG52621.2021.9619013

DO - 10.1109/CoG52621.2021.9619013

M3 - Conference paper (refereed)

AN - SCOPUS:85122938750

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

BT - Proceedings of the 2021 IEEE Conference on Games, CoG 2021

PB - IEEE Computer Society

T2 - 2021 IEEE Conference on Games, CoG 2021

Y2 - 17 August 2021 through 20 August 2021

ER -

Keiki: Towards Realistic Danmaku Generation via Sequential GANs

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this