3D Gaussian Splatting (3DGS) has recently demonstrated outstanding performance in 3D reconstruction and real-time rendering. However, its scalability to large scenes remains limited by single-GPU memory constraints. We propose ScaleGS, a scalable distributed training framework for largescale 3DGS with lightweight edge-aware communication. (1) We present a spatial median-guided binary partitioning algorithm that divides the point cloud into balanced, nonoverlapping, and spatially contiguous cuboid regions for efficient multi-GPU management. To ensure global view consistency, each GPU independently grows and updates only its local Gaussians, while cross-GPU Gaussians are accessed only for rendering and loss computation. (2) We design a lightweight edge communication strategy to significantly reduce cross-GPU communication overhead. A greedy GPUTile remapping algorithm leverages the spatial concentration of Gaussians to confine cross-GPU communication to edge regions, effectively decoupling communication complexity from GPU count, with per-GPU complexity remaining O(1). An optimized all-to-all communication scheme is also introduced to eliminate redundant transmissions. (3) Our framework introduces an adaptive edge-refined load balancing mechanism that periodically monitors GPU workloads and selectively migrates Gaussians between neighboring GPUs to maintain balance and spatial continuity with negligible cost. Evaluations on large-scale 4K scenes show that ScaleGS consistently outperforms state-of-the-art methods, achieving up to 20% faster training and approximately 20% model size reduction on 8 Tesla P40 GPUs without compromising reconstruction quality. Project page: https: //aicodeclub.github.io/ScaleGS.
Kou et al. (Tue,) studied this question.