EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

L-DGC: LLM-Based Dance Generative Control

Hanha Yoo, Yunsick Sung

Applied Sciences · 07.07.2026 · 16 (13) · 6825

DOI: 10.3390/app16136825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.07.2026. Verfasst von Hanha Yoo und 1 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul RISE Center.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global expansion of K-pop has increased demand for AI-driven choreography learning. However, existing motion recognition models often struggle to capture fine-grained rhythm patterns and dynamic motion transitions across consecutive frames, limiting their ability to provide accurate and objective feedback. To address these challenges, this paper proposes a Large Language Model-based Dance Generative Control (L-DGC), an integrated framework for controllable dance generation and evaluation. The framework comprises four stages: a Visual Analysis Phase (VAP) for skeletal extraction; an Audio Analysis Phase (AAP) for rhythmic synchronization; a Multimodal Data Phase (MDP), which employs Long Short-Term Memory (LSTM) and Transformer architectures to evaluate movement accuracy; and a three-dimensional (3D) Transformation Phase (3TP), which converts two-dimensional (2D) skeletal data into 3D character animations within the Unity engine. Guided by an LLM, the framework performs real-time inference and iterative refinement to optimize choreographic data without requiring subjective expert assessment. By quantifying choreographic components and transforming 2D motion data into 3D representations, L-DGC provides an objective evaluation framework for dance learning. The proposed system has significant potential for artificial intelligence (AI)-based dance education, real-time feedback applications, and automated audition platforms in the entertainment industry.

Förderung

  • Seoul RISE Center

Zitieren

APA

Yoo, H., & Sung, Y. (2026). L-DGC: LLM-Based Dance Generative Control. Applied Sciences, 16(13), 6825. https://doi.org/10.3390/app16136825

Vancouver

Yoo H, Sung Y. L-DGC: LLM-Based Dance Generative Control. Applied Sciences. 2026;16(13):6825. doi:10.3390/app16136825

BibTeX
@article{Yoo2026,
  author = {Yoo, Hanha and Sung, Yunsick},
  title = {L-DGC: LLM-Based Dance Generative Control},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {13},
  pages = {6825},
  doi = {10.3390/app16136825}
}
Kostenlos starten →