{"ID":2874306,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05216","arxiv_id":"2509.05216","title":"Toward Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization","abstract":"We present a multi-GPU extension of the 3D Gaussian Splatting (3D-GS) pipeline for scientific visualization. Building on previous work that demonstrated high-fidelity isosurface reconstruction using Gaussian primitives, we incorporate a multi-GPU training backend adapted from Grendel-GS to enable scalable processing of large datasets. By distributing optimization across GPUs, our method improves training throughput and supports high-resolution reconstructions that exceed single-GPU capacity. In our experiments, the system achieves a 5.6X speedup on the Kingsnake dataset (4M Gaussians) using four GPUs compared to a single-GPU baseline, and successfully trains the Miranda dataset (18M Gaussians) that is an infeasible task on a single A100 GPU. This work lays the groundwork for integrating 3D-GS into HPC-based scientific workflows, enabling real-time post hoc and in situ visualization of complex simulations.","short_abstract":"We present a multi-GPU extension of the 3D Gaussian Splatting (3D-GS) pipeline for scientific visualization. Building on previous work that demonstrated high-fidelity isosurface reconstruction using Gaussian primitives, we incorporate a multi-GPU training backend adapted from Grendel-GS to enable scalable processing of...","url_abs":"https://arxiv.org/abs/2509.05216","url_pdf":"https://arxiv.org/pdf/2509.05216v1","authors":"[\"Mengjiao Han\",\"Andres Sewell\",\"Joseph Insley\",\"Janet Knowles\",\"Victor A. Mateevitsi\",\"Michael E. Papka\",\"Steve Petruzza\",\"Silvio Rizzi\"]","published":"2025-09-05T16:19:25Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[]","has_code":false}