3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60\% of rendering time, and redundant Gaussian-tile pairs that incur unnecessary processing overhead. To address these limitations, we introduce FilterGS, featuring a parallel filtering mechanism with two complementary filters that select Gaussian elements efficiently without tree traversal. Additionally, we propose a novel GTC metric that quantifies the redundancy of Gaussian-tile key-value pairs. Based on this metric, we introduce a scene-adaptive Gaussian shrinking strategy that effectively reduces redundant pairs. Extensive experiments demonstrate that FilterGS achieves state-of-the-art rendering speeds while maintaining competitive visual quality across multiple large-scale datasets. Project page: https://github.com/xenon-w/FilterGS
@article{arxiv.2603.23891,
title = {FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting},
author = {Yixian Wang and Haolin Yu and Jiadong Tang and Yu Gao and Xihan Wang and Yufeng Yue and Yi Yang},
journal= {arXiv preprint arXiv:2603.23891},
year = {2026}
}