EUVIMEDEUVIMED entdecken
Crossref

Self-supervised Learning of Latent Space Dynamics

Yue Li, Gene Wei-Chin Lin, Egor Larionov, Aljaz Bozic, Doug Roble, Ladislav Kavan, Stelian Coros, Bernhard Thomaszewski, Tuur Stuyck, Hsiao-Yu Chen

Proceedings of the ACM on Computer Graphics and Interactive Techniques · 31.08.2025 · 8 (4) · 1-18

DOI: 10.1145/3747854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Computer Graphics and Interactive Techniques, online erschienen am 08.08.2025. Verfasst von Yue Li und 9 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 68 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation techniques address this challenge by restricting deformations to a lower-dimensional space, improving performance while maintaining visually compelling results. However, even subspace methods struggle to meet the stringent performance demands of portable devices such as virtual reality headsets and mobile platforms. To overcome this limitation, we introduce a novel subspace simulation framework powered by a neural latent-space integrator. Our approach leverages self-supervised learning to enhance inference stability and generalization. By operating entirely within latent space, our method eliminates the need for full-space computations, resulting in a highly efficient method well-suited for deployment on portable devices. We demonstrate the effectiveness of our approach on challenging examples involving rods, shells, and solids, showcasing its versatility and potential for widespread adoption.

Zitieren

APA

Li, Y., Lin, G. W., Larionov, E., Bozic, A., Roble, D., Kavan, L., Coros, S., Thomaszewski, B., Stuyck, T., & Chen, H. (2025). Self-supervised Learning of Latent Space Dynamics. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 8(4), 1-18. https://doi.org/10.1145/3747854

Vancouver

Li Y, Lin GW, Larionov E, Bozic A, Roble D, Kavan L, et al. Self-supervised Learning of Latent Space Dynamics. Proceedings of the ACM on Computer Graphics and Interactive Techniques. 2025;8(4):1-18. doi:10.1145/3747854

BibTeX
@article{Li2025,
  author = {Li, Yue and Lin, Gene Wei-Chin and Larionov, Egor and Bozic, Aljaz and Roble, Doug and Kavan, Ladislav and Coros, Stelian and Thomaszewski, Bernhard and Stuyck, Tuur and Chen, Hsiao-Yu},
  title = {Self-supervised Learning of Latent Space Dynamics},
  journal = {Proceedings of the ACM on Computer Graphics and Interactive Techniques},
  year = {2025},
  volume = {8},
  number = {4},
  pages = {1--18},
  doi = {10.1145/3747854}
}
Kostenlos starten →