Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
Xijie Yang, Linning Xu, Lihan Jiang, Dahua Lin, Bo Dai

TL;DR
This paper introduces Virtualized 3D Gaussians (V3DG), a hierarchical level-of-detail system that accelerates real-time rendering of large-scale 3D Gaussian scenes by dynamically selecting relevant clusters, enabling efficient composition of complex digital worlds.
Contribution
We propose a novel cluster-based LOD system for 3D Gaussian splatting that improves rendering speed while maintaining visual quality in large-scale scene compositions.
Findings
Balances rendering efficiency and visual quality
Handles scenes with up to 0.1 billion Gaussians
Enables real-time rendering of complex, large-scale scenes
Abstract
3D Gaussian Splatting (3DGS) enables the reconstruction of intricate digital 3D assets from multi-view images by leveraging a set of 3D Gaussian primitives for rendering. Its explicit and discrete representation facilitates the seamless composition of complex digital worlds, offering significant advantages over previous neural implicit methods. However, when applied to large-scale compositions, such as crowd-level scenes, it can encompass numerous 3D Gaussians, posing substantial challenges for real-time rendering. To address this, inspired by Unreal Engine 5's Nanite system, we propose Virtualized 3D Gaussians (V3DG), a cluster-based LOD solution that constructs hierarchical 3D Gaussian clusters and dynamically selects only the necessary ones to accelerate rendering speed. Our approach consists of two stages: (1) Offline Build, where hierarchical clusters are generated using a local…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
