Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 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
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.