TY - GEN
T1 - Automatic Generation of 3D Natural Anime-like Non-Player Characters with Machine Learning
AU - Li, Ruizhe
AU - Nakayama, Masanori
AU - Fujishiro, Issei
N1 - Funding Information:
We thank all the volunteers who participated in the experiment. This work was supported in part by JSPS KAKENHI under Grants-in-Aid for Scientific Research (A) No. 17H00737 and for Challenging Research (Pioneering) No. 19H05576.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - In role-playing games, creators always use specific models to generate non-player characters (NPCs). The prefabricated models are materialized in the scenes, and if more NPCs are included than character models prepared, the players may easily find many NPCs with similar appearances, which makes the scenes unnatural. In this paper, we propose a novel system for generating a rich variety of 3D anime-like NPCs in real time to make the scenes look more natural. We combine a proprietary character customization system with machine learning, where the customizing parameters are treated as feature vectors input in the neural network. The parameters are trained to avoid generating bad-looking models. We demonstrate that the proposed system can generate a natural school classroom scene with a variety of good-looking female student NPCs in a uniform.
AB - In role-playing games, creators always use specific models to generate non-player characters (NPCs). The prefabricated models are materialized in the scenes, and if more NPCs are included than character models prepared, the players may easily find many NPCs with similar appearances, which makes the scenes unnatural. In this paper, we propose a novel system for generating a rich variety of 3D anime-like NPCs in real time to make the scenes look more natural. We combine a proprietary character customization system with machine learning, where the customizing parameters are treated as feature vectors input in the neural network. The parameters are trained to avoid generating bad-looking models. We demonstrate that the proposed system can generate a natural school classroom scene with a variety of good-looking female student NPCs in a uniform.
KW - 3D character modeling
KW - auto-generation
KW - bone driven
KW - neural network
KW - non-player characters
UR - http://www.scopus.com/inward/record.url?scp=85099539224&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099539224&partnerID=8YFLogxK
U2 - 10.1109/CW49994.2020.00023
DO - 10.1109/CW49994.2020.00023
M3 - Conference contribution
AN - SCOPUS:85099539224
T3 - Proceedings - 2020 International Conference on Cyberworlds, CW 2020
SP - 110
EP - 116
BT - Proceedings - 2020 International Conference on Cyberworlds, CW 2020
A2 - Sourin, Alexei
A2 - Charier, Christophe
A2 - Rosenberger, Christophe
A2 - Sourina, Olga
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th International Conference on Cyberworlds, CW 2020
Y2 - 29 September 2020 through 1 October 2020
ER -