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: this https URL

3D 高斯喷墨（3DGS）是由于其出色的视觉效果和渲染速度而变得越来越受欢迎的三维重建技术。我们介绍了 Grendel，这是一个分布式系统，旨在将 3DGS 参数划分并在多个 GPU 上并行计算，以处理高分辨率和大规模的 3D 重建任务。通过在像素分区之间进行稀疏的全对全通信和动态负载平衡，Grendel 能够在多个视图中支持批量训练，以提高渲染质量。在大规模、高分辨率场景的评估中，使用多个 GPU 上的扩展 3DGS 参数，我们在 Rubble 数据集上将测试 PSNR 从单个 GPU 的 11.2 百万高斯值的 26.28 提高到了使用 16 个 GPU 分布的 40.4 百万高斯值的 27.28。Grendel 是一个开源项目，可以在此 https URL 找到。