Abstract
Game creators always use prefabricated models as non-player characters (NPCs) to create an atmosphere for game scenes. However, players are likely to see different NPCs with the same 3D models. We introduced a neural network, Gaussian mixture models, a Bayesian network to control their facial appearances, colors of hair and clothes, and outfits, respectively. It is demonstrated that the proposed approach can maintain the variety and stability of the generated characters.
More details in [J-1].
Members
Name | Affiliation | Web site |
---|---|---|
Ruizhe Li | Keio University | |
Ryo Oji | Keio University | |
Masanori Nakayama | Keio University |
Publications
Journals
- Ruizhe Li, Ryo Oji, Issei Fujishiro: “Controllable automatic generation of non-player crowd in 3D anime style,” Computer Animation and Virtual Worlds, No. e2047, April 2022 [doi: 10.1002/cav.2047].
International conferences/symposiums
- Ruizhe Li, Masanori Nakayama, Issei Fujishiro, “Automatic generation of 3D natural anime-like non-player characters with machine learning,” 2020 International Conference on Cyberworlds, pp. 110—116, Caen, France, September 29—October 1, 2020 [doi: 10.1109/CW49994.2020.00023].