Saved in:
Bibliographic Details
Main Authors: Hung, Sheng-Hsiang, Yen, Ting-Yu, Sun, Wei-Fang, See, Simon, Hung, Shih-Hsuan, Chu, Hung-Kuo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.01767
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910118947323904
author Hung, Sheng-Hsiang
Yen, Ting-Yu
Sun, Wei-Fang
See, Simon
Hung, Shih-Hsuan
Chu, Hung-Kuo
author_facet Hung, Sheng-Hsiang
Yen, Ting-Yu
Sun, Wei-Fang
See, Simon
Hung, Shih-Hsuan
Chu, Hung-Kuo
contents 3D Gaussian Splatting (3DGS) has established itself as an efficient representation for real-time, high-fidelity 3D scene reconstruction. However, scaling 3DGS to large and unbounded scenes such as city blocks remains difficult. Existing divide-and-conquer methods alleviate memory pressure by partitioning the scene into blocks and training on multiple, non-communicating GPUs, but introduce new bottlenecks: (i) partitions suffer from severe load imbalance since uniform or heuristic splits do not reflect actual computational demands, and (ii) coarse-to-fine pipelines fail to exploit the coarse stage efficiently, often reloading the entire model and incurring high overhead. In this work, we introduce LoBE-GS, a novel Load-Balanced and Efficient 3D Gaussian Splatting framework, that re-engineers the large-scale 3DGS pipeline. Specifically, LoBE-GS introduces a load-balanced KD-tree scene partitioning scheme with optimized cutlines that balance per-block camera counts. To accelerate preprocessing, it employs depth-based back-projection for fast camera assignment, reducing processing time from hours to minutes. It further reduces training cost through two lightweight techniques: visibility cropping and selective densification. Evaluations on large-scale urban and outdoor datasets show that LoBE-GS consistently achieves up to 2 times faster end-to-end training time than state-of-the-art baselines, while maintaining reconstruction quality and enabling scalability to scenes infeasible with vanilla 3DGS.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01767
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LoBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction
Hung, Sheng-Hsiang
Yen, Ting-Yu
Sun, Wei-Fang
See, Simon
Hung, Shih-Hsuan
Chu, Hung-Kuo
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has established itself as an efficient representation for real-time, high-fidelity 3D scene reconstruction. However, scaling 3DGS to large and unbounded scenes such as city blocks remains difficult. Existing divide-and-conquer methods alleviate memory pressure by partitioning the scene into blocks and training on multiple, non-communicating GPUs, but introduce new bottlenecks: (i) partitions suffer from severe load imbalance since uniform or heuristic splits do not reflect actual computational demands, and (ii) coarse-to-fine pipelines fail to exploit the coarse stage efficiently, often reloading the entire model and incurring high overhead. In this work, we introduce LoBE-GS, a novel Load-Balanced and Efficient 3D Gaussian Splatting framework, that re-engineers the large-scale 3DGS pipeline. Specifically, LoBE-GS introduces a load-balanced KD-tree scene partitioning scheme with optimized cutlines that balance per-block camera counts. To accelerate preprocessing, it employs depth-based back-projection for fast camera assignment, reducing processing time from hours to minutes. It further reduces training cost through two lightweight techniques: visibility cropping and selective densification. Evaluations on large-scale urban and outdoor datasets show that LoBE-GS consistently achieves up to 2 times faster end-to-end training time than state-of-the-art baselines, while maintaining reconstruction quality and enabling scalability to scenes infeasible with vanilla 3DGS.
title LoBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.01767