Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 98% Match Research Paper 3D Graphics Developers,VR/AR Engineers,Game Developers,Researchers in Neural Rendering 5 days ago

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

computer-vision › 3d-vision
📄 Abstract

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.
Authors (8)
Jonas Kulhanek
Marie-Julie Rakotosaona
Fabian Manhardt
Christina Tsalicoglou
Michael Niemeyer
Torsten Sattler
+2 more
Submitted
May 29, 2025
arXiv Category
cs.CV
arXiv PDF

Key Contributions

Presents a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. It introduces a hierarchical representation, spatial partitioning, and dynamic loading to significantly reduce rendering time and memory usage while maintaining visual fidelity.

Business Value

Enables the creation and rendering of highly detailed, large-scale 3D environments for VR/AR experiences, gaming, and virtual production, making complex scenes accessible on consumer hardware.