EUVIMEDEUVIMED entdecken
Crossref

AMD: Autoregressive Motion Diffusion

Bo Han, Hao Peng, Minjing Dong, Yi Ren, Yixuan Shen, Chang Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (3) · 2022-2030

DOI: 10.1609/aaai.v38i3.27973 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Bo Han und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple motion patterns, they encounter difficulties when dealing with long prompts or complex motions. The challenges are two-fold: 1) the scarcity of human motion-captured data for long prompts and complex motions. 2) the high diversity of human motions in the temporal domain and the substantial divergence of distributions from conditional modalities, leading to a many-to-many mapping problem when generating motion with complex and long texts. In this work, we address these gaps by 1) elaborating the first dataset pairing long textual descriptions and 3D complex motions (HumanLong3D), and 2) proposing an autoregressive motion diffusion model (AMD). Specifically, AMD integrates the text prompt at the current timestep with the text prompt and action sequences at the previous timestep as conditional information to predict the current action sequences in an iterative manner. Furthermore, we present its generalization for X-to-Motion with “No Modality Left Behind”, enabling for the first time the generation of high-definition and high-fidelity human motions based on user-defined modality input.

Zitieren

APA

Han, B., Peng, H., Dong, M., Ren, Y., Shen, Y., & Xu, C. (2024). AMD: Autoregressive Motion Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2022-2030. https://doi.org/10.1609/aaai.v38i3.27973

Vancouver

Han B, Peng H, Dong M, Ren Y, Shen Y, Xu C. AMD: Autoregressive Motion Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2022-2030. doi:10.1609/aaai.v38i3.27973

BibTeX
@article{Han2024,
  author = {Han, Bo and Peng, Hao and Dong, Minjing and Ren, Yi and Shen, Yixuan and Xu, Chang},
  title = {AMD: Autoregressive Motion Diffusion},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {3},
  pages = {2022--2030},
  doi = {10.1609/aaai.v38i3.27973}
}
Kostenlos starten →