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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00387802" target="_blank" >RIV/68407700:21230/25:00387802 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/25:00387802

Výsledek na webu

<a href="https://openreview.net/pdf?id=Iqu63cYI3z" target="_blank" >https://openreview.net/pdf?id=Iqu63cYI3z</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

In this work, we present a novel level-of-detail (LOD) method for 3D Gaus sian 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 LODlevel 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.

Název v anglickém jazyce

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

Popis výsledku anglicky

In this work, we present a novel level-of-detail (LOD) method for 3D Gaus sian 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 LODlevel 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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advances in Neural Information Processing Systems 38 (NeurIPS 2025)

ISBN

—

ISSN

1049-5258

e-ISSN

—

Počet stran výsledku

22

Strana od-do

—

Název nakladatele

Neural Information Processing Systems Foundation, Inc.

Místo vydání

—

Místo konání akce

San Diego

Datum konání akce

2. 12. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—