EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies

Pengyu Long, Weirui Wang, Qingcheng Zhao, Xiaoyang Guo, Xiaoyu Pan, Qixuan Zhang, Jiaqing Zhou, Tianlei Hu, Wei Yang, Lan Xu, Jingyi Yu

ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-20

DOI: 10.1145/3811392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Pengyu Long und 10 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Central Guided Local Science and Technology Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in generative models have democratized the creation of high-quality static 3D assets, yet animating these meshes remains a labor-intensive bottleneck. Traditional pipelines fracture this process into sequential stages—rigging, skinning, and motion synthesis—ignoring the inherent coupling between morphological structure and motor function. To bridge this gap, we introduce ACT, a unified generative framework that reformulates rigging and animation not as independent tasks, but as complementary views of a single hyper-kinematic process. Our key insight is to model the joint distribution of skeletal topology and temporal motion within a shared latent space. ACT utilizes a Vision Language Model (VLM) to extract semantic topological priors from arbitrary meshes, which then condition a Diffusion Transformer (DiT) backbone. By treating static rest poses and dynamic trajectories as a unified sequence, our model employs a task-aware masking strategy to flexibly perform zero-shot rigging, text-guided motion generation, and motion completion within a single end-to-end architecture. Furthermore, a geometry-guided decoder ensures that surface deformations are tightly coupled with the generated kinematics. Extensive experiments demonstrate that ACT generalizes robustly to diverse, non-humanoid characters without retraining. By replacing brittle cascaded pipelines with a holistic prior, our method enables novel applications such as semantic-driven topology editing and generative in-betweening, offering a versatile and efficient solution for automating 3D character animation.

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Central Guided Local Science and Technology Foundation of China

Zitieren

APA

Long, P., Wang, W., Zhao, Q., Guo, X., Pan, X., Zhang, Q., Zhou, J., Hu, T., Yang, W., Xu, L., & Yu, J. (2026). ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies. ACM Transactions on Graphics, 45(4), 1-20. https://doi.org/10.1145/3811392

Vancouver

Long P, Wang W, Zhao Q, Guo X, Pan X, Zhang Q, et al. ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies. ACM Transactions on Graphics. 2026;45(4):1-20. doi:10.1145/3811392

BibTeX
@article{Long2026,
  author = {Long, Pengyu and Wang, Weirui and Zhao, Qingcheng and Guo, Xiaoyang and Pan, Xiaoyu and Zhang, Qixuan and Zhou, Jiaqing and Hu, Tianlei and Yang, Wei and Xu, Lan and Yu, Jingyi},
  title = {ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {4},
  pages = {1--20},
  doi = {10.1145/3811392}
}
Kostenlos starten →