Salvato in:
Dettagli Bibliografici
Autori principali: Han, Mengjiao, Sewell, Andres, Insley, Joseph, Knowles, Janet, Mateevitsi, Victor A., Papka, Michael E., Petruzza, Steve, Rizzi, Silvio
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.05216
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908521398796288
author Han, Mengjiao
Sewell, Andres
Insley, Joseph
Knowles, Janet
Mateevitsi, Victor A.
Papka, Michael E.
Petruzza, Steve
Rizzi, Silvio
author_facet Han, Mengjiao
Sewell, Andres
Insley, Joseph
Knowles, Janet
Mateevitsi, Victor A.
Papka, Michael E.
Petruzza, Steve
Rizzi, Silvio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization
Han, Mengjiao
Sewell, Andres
Insley, Joseph
Knowles, Janet
Mateevitsi, Victor A.
Papka, Michael E.
Petruzza, Steve
Rizzi, Silvio
Distributed, Parallel, and Cluster Computing
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.
title Toward Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2509.05216