| Wu, Jingyi, Liu, Yang, Guo, Juncen, Meng, Yuanyuan, Yu, Han, Zhang, Jingyu, Zou, Minghao, Zhou, Wei, Liu, Jing and Song, Liang 2026. Digital human generation for games via tightness-aware multi-cue modeling. IEEE Transactions on Games 10.1109/tg.2026.3708023 |
Abstract
Generating accurate parametric human models from multi-cue observations is a fundamental challenge in producing high-fidelity game characters. Parametric reconstruction is essential for digital character production, animation, and interactive physics simulation within game environments. Existing alignment methods remain unstable under complex clothing, extreme poses, or severe occlusions. The instability severely degrades the generation of high-quality game ready characters. To tackle the challenge, we present a robust character reconstruction framework to systematically resolve the geometric discrepancy between clothing and human skin. Specifically, we propose a tightness-aware mechanism to filter geometric noise from loose garments through localized contact analysis. We subsequently introduce an implicit dense correspondence field to handle incomplete observations. The implicit field establishes a reliable mapping between unstructured inputs and the canonical model. Finally, we design a decoupled training strategy to optimize the undressing and character modeling stages independently. The decoupled approach enables the network to effectively handle diverse outfits. Extensive experiments demonstrate that our proposed model provides a reliable and highly accurate solution for character creation in game development pipelines.
| Item Type: | Article |
|---|---|
| Date Type: | Published Online |
| Status: | In Press |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| ISSN: | 2475-1502 |
| Last Modified: | 06 Jul 2026 15:44 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/187956 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions