EUVIMEDEUVIMED entdecken
Crossref

Controllable 3D Dance Generation Using Diffusion-Based Transformer U-Net

Puyuan Guo, Tuo Hao, Wenxin Fu, Yingming Gao, Ya Li

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 3284-3292

DOI: 10.1609/aaai.v39i3.32339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Puyuan Guo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, dance generation has attracted increasing interest. In particular, the success of diffusion models in image generation has led to the emergence of dance generation systems based on the diffusion framework. However, these systems lack controllability, which limits their practical applications. In this paper, we propose a controllable dance generation method based on the diffusion model, which can generate 3D dance motions controlled by 2D keypoint sequences. Specifically, we design a transformer-based U-Net model to predict actual motions. Then, we fix the parameters of the U-Net model and train an additional control network, enabling the generated motions to be controlled by 2D keypoints. We conduct extensive experiments and compared our method with existing works on the widely used AIST++ dataset, demonstrating that our approach has certain advantages and controllability. Moreover, we also test our model on in-the-wild videos and find that it is capable of generating dance movements similar to the motions in the videos as well.

Zitieren

APA

Guo, P., Hao, T., Fu, W., Gao, Y., & Li, Y. (2025). Controllable 3D Dance Generation Using Diffusion-Based Transformer U-Net. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 3284-3292. https://doi.org/10.1609/aaai.v39i3.32339

Vancouver

Guo P, Hao T, Fu W, Gao Y, Li Y. Controllable 3D Dance Generation Using Diffusion-Based Transformer U-Net. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):3284-3292. doi:10.1609/aaai.v39i3.32339

BibTeX
@article{Guo2025,
  author = {Guo, Puyuan and Hao, Tuo and Fu, Wenxin and Gao, Yingming and Li, Ya},
  title = {Controllable 3D Dance Generation Using Diffusion-Based Transformer U-Net},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {3284--3292},
  doi = {10.1609/aaai.v39i3.32339}
}
Kostenlos starten →