Automatic Generation of 3D Natural Anime-like Non-Player Characters with Machine Learning

Ruizhe Li, Masanori Nakayama, Issei Fujishiro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2020 International Conference on Cyberworlds, CW 2020
EditorsAlexei Sourin, Christophe Charier, Christophe Rosenberger, Olga Sourina
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages110-116
Number of pages7
ISBN (Electronic)9781728164977
DOIs
Publication statusPublished - 2020 Sep
Event19th International Conference on Cyberworlds, CW 2020 - Virtual, Caen, France
Duration: 2020 Sep 292020 Oct 1

Publication series

NameProceedings - 2020 International Conference on Cyberworlds, CW 2020

Conference

Conference19th International Conference on Cyberworlds, CW 2020
CountryFrance
CityVirtual, Caen
Period20/9/2920/10/1

Keywords

  • 3D character modeling
  • auto-generation
  • bone driven
  • neural network
  • non-player characters

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Media Technology
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Automatic Generation of 3D Natural Anime-like Non-Player Characters with Machine Learning'. Together they form a unique fingerprint.

Cite this