Metraipolis › archive › dc_5000f4c013dd
Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting — arXiv:2608.28702
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28702
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:17.914Z
- SHA-256 of the archived text
ddce87dcec252d25a92763c096da090abeb8e2ca2ffc254e033ff1a709e8e1fa- Stable URL of this page
https://metraipolis.com/documento/dc_5000f4c013dd
How to cite
Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting — arXiv:2608.28702 — arXiv (en), https://arxiv.org/abs/2608.28702 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5000f4c013dd (Metraipolis archive dc_5000f4c013dd, sha256 ddce87dcec252d25a92763c096da090abeb8e2ca2ffc254e033ff1a709e8e1fa)
BibTeX
@misc{dc5000f4c013dd,
title = {Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting — arXiv:2608.28702},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28702},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5000f4c013dd; sha256 ddce87dcec252d25a92763c096da090abeb8e2ca2ffc254e033ff1a709e8e1fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28702. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deformable 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time. Replacing its MLP with a stack of Closed-form Continuous-time (CfC) cells-a Liquid Neural Network that solves the Liquid Timeconstant ODE in closed form-gives the field continuous-time behaviour at feed-forward cost. That closed form, however, is only the deterministic limit of a noise-driven system, and drops the stochastic term usually credited for the robustness of liquid networks. We put it back: a small Gaussian perturbation is added to the time gate of every CfC cell, turning the deterministic field into a simple stochastic (SDE) one. The noise is used only during training, needs no solver, and reduces exactly to the CfC when switched off. On the synthetic D-NeRF scenes the stochastic field is on par with the deterministic CfC and beats the MLP baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help. The study thus gives both a clean way to read the CfC field as an SDE and an honest account of when a plain noise term helps and when it does not. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28702 — 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 2026-10-17T09:28:47.946Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).