LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering

TL;DR

LODGE introduces a hierarchical level-of-detail method for 3D Gaussian Splatting that enables real-time, memory-efficient rendering of large-scale scenes by dynamically selecting and pruning Gaussians based on camera distance.

Contribution

It presents a novel hierarchical LOD representation with importance-based pruning and dynamic loading, significantly reducing rendering time and memory usage for large-scale 3D scenes.

Findings

Achieves state-of-the-art performance on outdoor and indoor datasets.

Reduces GPU memory usage and rendering latency.

Maintains high visual fidelity with importance-based pruning.

Abstract

In this work, we present a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. Our approach introduces a hierarchical LOD representation that iteratively selects optimal subsets of Gaussians based on camera distance, thus largely reducing both rendering time and GPU memory usage. We construct each LOD level by applying a depth-aware 3D smoothing filter, followed by importance-based pruning and fine-tuning to maintain visual fidelity. To further reduce memory overhead, we partition the scene into spatial chunks and dynamically load only relevant Gaussians during rendering, employing an opacity-blending mechanism to avoid visual artifacts at chunk boundaries. Our method achieves state-of-the-art performance on both outdoor (Hierarchical 3DGS) and indoor (Zip-NeRF) datasets, delivering high-quality renderings with reduced latency and memory requirements.