English

GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations

Graphics 2026-04-09 v1 Artificial Intelligence

Abstract

Exploring ensemble simulations is increasingly important across many scientific domains. However, supporting flexible post-hoc exploration remains challenging due to the trade-off between storing the expensive raw data and flexibly adjusting visualization settings. Existing visualization surrogate models have improved this workflow, but they either operate in image space without an explicit 3D representation or rely on neural radiance fields that are computationally expensive for interactive exploration and encode all parameter-driven variations within a single implicit field. In this work, we introduce GS-Surrogate, a deformable Gaussian Splatting-based visualization surrogate for parameter-space exploration. Our method first constructs a canonical Gaussian field as a base 3D representation and adapts it through sequential parameter-conditioned deformations. By separating simulation-related variations from visualization-specific changes, this explicit formulation enables efficient and controllable adaptation to different visualization tasks, such as isosurface extraction and transfer function editing. We evaluate our framework on a range of simulation datasets, demonstrating that GS-Surrogate enables real-time and flexible exploration across both simulation and visualization parameter spaces.

Keywords

Cite

@article{arxiv.2604.06358,
  title  = {GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations},
  author = {Ziwei Li and Rumali Perera and Angus Forbes and Ken Moreland and Dave Pugmire and Scott Klasky and Wei-Lun Chao and Han-Wei Shen},
  journal= {arXiv preprint arXiv:2604.06358},
  year   = {2026}
}