EUVIMEDEUVIMED entdecken
Crossref

Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field

Haoqin Hong, Ding Fan, Fubin Dou, Zhi-Li Zhou, Haoran Sun, Congcong Zhu, Jingrun Chen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4725-4733

DOI: 10.1609/aaai.v40i6.42474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Haoqin Hong und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, 3D Gaussian Splatting (3DGS), an explicit scene representation technique, has shown significant promise for dynamic novel-view synthesis from monocular video input. However, purely data-driven 3DGS often struggles to capture the diverse physics-driven motion patterns in dynamic scenes. To fill this gap, we propose Physics‑Informed Deformable Gaussian Splatting (PIDG), which treats each Gaussian particle as a Lagrangian material point with time-varying constitutive parameters and is supervised by 2D optical flow via motion projection. Specifically, we adopt static-dynamic decoupled 4D decomposed hash encoding to reconstruct geometry and motion efficiently. Subsequently, we impose the Cauchy momentum residual as a physics constraint, enabling independent prediction of each particle’s velocity and constitutive stress via a time-evolving material field. Finally, we further supervise data fitting by matching Lagrangian particle flow to camera-compensated optical flow, which accelerates convergence and improves generalization. Experiments on a custom physics-driven dataset as well as on standard synthetic and real-world datasets demonstrate significant gains in physical consistency and monocular dynamic reconstruction quality.

Zitieren

APA

Hong, H., Fan, D., Dou, F., Zhou, Z., Sun, H., Zhu, C., & Chen, J. (2026). Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4725-4733. https://doi.org/10.1609/aaai.v40i6.42474

Vancouver

Hong H, Fan D, Dou F, Zhou Z, Sun H, Zhu C, et al. Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4725-4733. doi:10.1609/aaai.v40i6.42474

BibTeX
@article{Hong2026,
  author = {Hong, Haoqin and Fan, Ding and Dou, Fubin and Zhou, Zhi-Li and Sun, Haoran and Zhu, Congcong and Chen, Jingrun},
  title = {Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4725--4733},
  doi = {10.1609/aaai.v40i6.42474}
}
Kostenlos starten →