Metraipolis › archive › dc_27bf51d7b67f

PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation — arXiv:2610.07609

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07609
License (as archived)
CC0-1.0
Archived
2026-10-07T13:07:11.433Z
SHA-256 of the archived text
c5538c3919d4b3cc8b6d93006fd2f34340773cf344fcb693a8620cfab33f75c1
Stable URL of this page
https://metraipolis.com/documento/dc_27bf51d7b67f

How to cite

PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation — arXiv:2610.07609 — arXiv (en), https://arxiv.org/abs/2610.07609 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27bf51d7b67f (Metraipolis archive dc_27bf51d7b67f, sha256 c5538c3919d4b3cc8b6d93006fd2f34340773cf344fcb693a8620cfab33f75c1)
BibTeX
@misc{dc27bf51d7b67f,
  title = {PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation — arXiv:2610.07609},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07609},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27bf51d7b67f; sha256 c5538c3919d4b3cc8b6d93006fd2f34340773cf344fcb693a8620cfab33f75c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07609. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3D volumetric meshes is hard: autoregressive methods are susceptible to error accumulation, while direct multi-frame prediction at native resolution is computationally prohibitive. This motivates a compact spatiotemporal latent representation, which is largely unexplored for mesh-based volumetric physics. Meanwhile, it remains unclear whether deterministic regression or generative diffusion is the more appropriate predictive paradigm. To address these coupled challenges, we introduce PhysLDM, a unified latent-diffusion paradigm for one-shot volumetric deformable simulation. Its core is a holistic spatiotemporal VAE that avoids the "staircase" artifacts of standard temporal compression (as in common video VAEs), achieving ~2.48 mm reconstruction precision on meter-scale scenes at up to 78x token compression. Based on this reliable latent space, we systematically compare regression and diffusion methods. Our experiments uncover a key modeling insight: complex deformable dynamics are often chaotic, and in this regime deterministic regression tends to produce non-physical averages, whereas diffusion better models their distribution. Accordingly, we employ a latent diffusion model that effectively learns from the chaotic data to generate physically plausible trajectories. Trained purely kinematically on an Objaverse-scale dataset, a single PhysLDM generalizes zero-shot to unseen OOD datasets (GSO and Toys4K). Its differentiability further enables efficient solution of inverse problems and higher-order design optimization. To our knowledge, PhysLDM is the first high-fidelity spatiotemporal autoencoder and latent-diffusion paradigm for volumetric deformable dynamics, offering a scalable and robust approach to neural simulation.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.07609 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:37:32.893Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).