3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks due to memory constraints. We introduce Grendel, a distributed system designed to partition 3DGS parameters and parallelize computation across multiple GPUs. As each Gaussian affects a small, dynamic subset of rendered pixels, Grendel employs sparse all-to-all communication to transfer the necessary Gaussians to pixel partitions and performs dynamic load balancing. Unlike existing 3DGS systems that train using one camera view image at a time, Grendel supports batched training with multiple views. We explore various optimization hyperparameter scaling strategies and find that a simple sqrt(batch size) scaling rule is highly effective. Evaluations using large-scale, high-resolution scenes show that Grendel enhances rendering quality by scaling up 3DGS parameters across multiple GPUs. On the Rubble dataset, we achieve a test PSNR of 27.28 by distributing 40.4 million Gaussians across 16 GPUs, compared to a PSNR of 26.28 using 11.2 million Gaussians on a single GPU. Grendel is an open-source project available at: https://github.com/nyu-systems/Grendel-GS

翻译：3D高斯溅射（3DGS）因其卓越的视觉质量和渲染速度，在三维重建领域日益受到青睐。然而，当前3DGS训练通常在单GPU上进行，受限于内存约束，难以处理高分辨率和大规模的三维重建任务。本文介绍Grendel，一个专为分区3DGS参数并在多GPU间并行化计算而设计的分布式系统。由于每个高斯仅影响渲染像素中一个动态的小子集，Grendel采用稀疏全对全通信机制，将必要的高斯传递至像素分区，并执行动态负载均衡。与现有每次仅使用单一相机视图图像进行训练的3DGS系统不同，Grendel支持多视图的批量训练。我们探索了多种优化超参数缩放策略，发现简单的sqrt(批量大小)缩放规则极为有效。在大规模、高分辨率场景下的评估表明，Grendel通过在多GPU间扩展3DGS参数，显著提升了渲染质量。在Rubble数据集上，通过在16个GPU上分布4040万个高斯，我们实现了27.28的测试PSNR，相比之下，在单GPU上使用1120万个高斯仅获得26.28的PSNR。Grendel是一个开源项目，地址为：https://github.com/nyu-systems/Grendel-GS