用像素级通信提升3D高斯溅射训练效率，突破大规模场景重建瓶颈
Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication
- 按像素局部渲染并交换部分像素值，避免全局高斯同步
- 12000万高斯下实现7.6倍加速，通信开销不随场景增大而增长
- 适合需要高效训练超大规模3D场景的研究者与工业应用
3D高斯溅射（3DGS）可实现高保真、实时的3D场景重建，但将训练扩展至大规模场景需在多GPU上优化数亿个高斯。现有分布式方法要么将场景划分为独立区域，导致全局不一致；要么依赖全局高斯级通信，造成跨GPU通信量激增，迅速成为迭代瓶颈。本文提出Splaxel，一种基于像素级局部渲染与全局合成的通信高效分布式3DGS训练框架。各GPU仅渲染本地子集并交换部分像素值，保持数学一致性的同时，使通信开销随场景规模增长趋于稳定。通过几何与透射率可见性预测减少像素冗余，并利用无冲突相机视图合并提升GPU利用率。在最大含1.2亿高斯的大型数据集上评估，Splaxel相比当前最优分布式3DGS框架最高提速7.6倍，同时保持高质量重建效果。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。