ScaleGS: Scalable Distributed Framework for Large-Scale 3D Gaussian Splatting with Edge Communication
ACM SIGMETRICS Performance Evaluation Review · 31.03.2026 · 53 (4) · 16-17
DOI: 10.1145/3797823.3797830 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM SIGMETRICS Performance Evaluation Review, online erschienen am 31.03.2026. Verfasst von Yong Kou und 4 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Kou, Y., He, J., Yuan, X., Luo, D., & Zhang, Y. (2026). ScaleGS: Scalable Distributed Framework for Large-Scale 3D Gaussian Splatting with Edge Communication. ACM SIGMETRICS Performance Evaluation Review, 53(4), 16-17. https://doi.org/10.1145/3797823.3797830
Vancouver
Kou Y, He J, Yuan X, Luo D, Zhang Y. ScaleGS: Scalable Distributed Framework for Large-Scale 3D Gaussian Splatting with Edge Communication. ACM SIGMETRICS Performance Evaluation Review. 2026;53(4):16-17. doi:10.1145/3797823.3797830
BibTeX
@article{Kou2026,
author = {Kou, Yong and He, Jinlong and Yuan, Xia and Luo, Dening and Zhang, Yanci},
title = {ScaleGS: Scalable Distributed Framework for Large-Scale 3D Gaussian Splatting with Edge Communication},
journal = {ACM SIGMETRICS Performance Evaluation Review},
year = {2026},
volume = {53},
number = {4},
pages = {16--17},
doi = {10.1145/3797823.3797830}
}
EUVIMED