Multimodal Dance Generation With Multi‐Granularity Style Control and Text Guidance
Computer Animation and Virtual Worlds · 2026-01 · 37 (1)
DOI: 10.1002/cav.70097 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Animation and Virtual Worlds, online erschienen am 25.01.2026. Verfasst von Mengmeng Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Dance generation is a significant research area in computer arts and artificial intelligence. This study proposes a novel framework to enhance dance controllability and personalization through multimodal and multi‐granularity control. The framework establishes global choreographic control of long sequences via music and dance style factors, while accommodating local style variations. Simultaneously, it enables fine‐grained local control using style, text, and temporal factors for motion refinement. We develop two cross‐modal Transformers: the LS‐M2D model merges music and dance style features for local style‐controllable dance generation, and the LT‐SM2D model integrates textual guidance with music and dance style features for time‐constrained local control. Experimental results demonstrate enhanced motion quality, effective multi‐granularity style control, and precise text‐guided flexibility. This provides valuable technical support for personalized intelligent dance generation systems.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, M., Wan, L., Peng, B., Xu, W., & Wang, S. (2026). Multimodal Dance Generation With Multi‐Granularity Style Control and Text Guidance. Computer Animation and Virtual Worlds, 37(1). https://doi.org/10.1002/cav.70097
Vancouver
Wang M, Wan L, Peng B, Xu W, Wang S. Multimodal Dance Generation With Multi‐Granularity Style Control and Text Guidance. Computer Animation and Virtual Worlds. 2026;37(1). doi:10.1002/cav.70097
BibTeX
@article{Wang2026,
author = {Wang, Mengmeng and Wan, Lili and Peng, Bo and Xu, Wanru and Wang, Shenghui},
title = {Multimodal Dance Generation With Multi‐Granularity Style Control and Text Guidance},
journal = {Computer Animation and Virtual Worlds},
year = {2026},
volume = {37},
number = {1},
doi = {10.1002/cav.70097}
}
EUVIMED