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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kulhanek, Jonas, Rakotosaona, Marie-Julie, Manhardt, Fabian, Tsalicoglou, Christina, Niemeyer, Michael, Sattler, Torsten, Peng, Songyou, Tombari, Federico
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911239940079616
author Kulhanek, Jonas
Rakotosaona, Marie-Julie
Manhardt, Fabian
Tsalicoglou, Christina
Niemeyer, Michael
Sattler, Torsten
Peng, Songyou
Tombari, Federico
author_facet Kulhanek, Jonas
Rakotosaona, Marie-Julie
Manhardt, Fabian
Tsalicoglou, Christina
Niemeyer, Michael
Sattler, Torsten
Peng, Songyou
Tombari, Federico
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23158
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
Kulhanek, Jonas
Rakotosaona, Marie-Julie
Manhardt, Fabian
Tsalicoglou, Christina
Niemeyer, Michael
Sattler, Torsten
Peng, Songyou
Tombari, Federico
Computer Vision and Pattern Recognition
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.
title LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.23158