Toward Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization

2025-09-05

AI Summary

To address the memory bottleneck of 3D Gaussian Splatting (3D-GS) on single GPUs—hindering high-resolution isosurface visualization of large-scale scientific data—this paper proposes the first multi-GPU distributed 3D-GS training framework tailored for in-situ visualization. Built upon the Grendel-GS backend, it introduces distributed Gaussian parameter partitioning, cross-GPU gradient synchronization, and dynamic load balancing to overcome per-GPU memory constraints. The framework enables efficient collaborative training of up to 18 million Gaussians—the largest scale demonstrated to date—achieving a 5.6× speedup on the Kingsnake dataset (4M Gaussians) and successfully reconstructing isosurfaces of the Miranda dataset, which is infeasible on a single GPU. This work establishes a scalable, high-performance computing paradigm for real-time, high-fidelity in-situ visualization of ultra-large volumetric datasets.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Distributed Machine Learning & Federated Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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.

Problem

• Extending 3D Gaussian Splatting for multi-GPU scientific visualization
• Enabling scalable high-resolution isosurface reconstruction
• Overcoming single-GPU limitations for large dataset processing

Innovation

• Multi-GPU distributed training backend
• Scalable processing for large datasets
• High-resolution isosurface reconstruction optimization