EUVIMEDEUVIMED entdecken
Crossref

3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model

Jiawei Huang, Yubao Sun, Guiyu Xia, Qingshan Liu, Mohan Kankanhalli

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.05.2026 · 22 (5) · 1-19

DOI: 10.1145/3789508 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 20.04.2026. Verfasst von Jiawei Huang und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Qinglan Project of Jiangsu Province of China, and Jiangsu Provincial Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generating natural and realistic human motion sequences under the constraints of 3D scenes is a highly challenging task, requiring not only the precise modeling of dynamic variations in human joints but also the rigorous consideration of intricate interactions between the human body and the surrounding environment. While recent advances in deep generative models show great potential in tackling these challenges, existing methods often result in unnatural human motions and human–environment penetration during generation. In order to cope with these issues, we propose a novel approach that divides human motion generation into two stages. The first stage employs a bidirectional long short-term memory network incorporated with full-connected layers to generate motion trajectory under the input conditions including the starting and ending positions and orientations of the human model and scene feature point clouds extracted from the surrounding environment. In the second stage, we design a conditional diffusion model, guided by the trajectory generated in the first stage and the embedding of 3D scene information, to generate human motion sequences within 3D scenes. We evaluate our framework through extensive experiments on the PROX datasets, which validates its effectiveness. The results show that our method significantly outperforms existing ones in enhancing human motion naturalness and reasonableness, and reducing human penetration.

Förderung

  • National Natural Science Foundation of China
  • Qinglan Project of Jiangsu Province of China, and Jiangsu Provincial Science and Technology

Zitieren

APA

Huang, J., Sun, Y., Xia, G., Liu, Q., & Kankanhalli, M. (2026). 3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(5), 1-19. https://doi.org/10.1145/3789508

Vancouver

Huang J, Sun Y, Xia G, Liu Q, Kankanhalli M. 3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(5):1-19. doi:10.1145/3789508

BibTeX
@article{Huang2026,
  author = {Huang, Jiawei and Sun, Yubao and Xia, Guiyu and Liu, Qingshan and Kankanhalli, Mohan},
  title = {3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {5},
  pages = {1--19},
  doi = {10.1145/3789508}
}
Kostenlos starten →