# A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory

arXiv: https://arxiv.org/abs/2507.01110 · HTML: https://mlsanity.com/paper/2507.01110/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024)
- [Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset](https://mlsanity.com/paper/2107.04286/) (2021)
- [Grid-guided Neural Radiance Fields for Large Urban Scenes](https://mlsanity.com/paper/2303.14001/) (2023)
- [CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes](https://mlsanity.com/paper/2411.00771/) (2024)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes](https://mlsanity.com/paper/2412.01745/) (2024)
- [FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Rendering](https://mlsanity.com/paper/2408.12894/) (2024)
- [LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering](https://mlsanity.com/paper/2505.23158/) (2025)
- [NeRF-XL: Scaling NeRFs with Multiple GPUs](https://mlsanity.com/paper/2404.16221/) (2024)
- [RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians](https://mlsanity.com/paper/2406.11836/) (2024)
- [A Hierarchical Compression Technique for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2411.06976/) (2024)
- [OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering](https://mlsanity.com/paper/2503.16177/) (2025)
- [Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes](https://mlsanity.com/paper/2505.06523/) (2025)
- [ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistency](https://mlsanity.com/paper/2412.01402/) (2024)

## Built on by (most cited first, 2 of 2)

- [Budgeted-GS: Real-Time Large-Scale Gaussian Splatting via Factoring LOD](https://mlsanity.com/paper/2610.03162/) (2026)
- [Efficient Confidence-Aware Densification for 3DGS](https://mlsanity.com/paper/2610.13541/) (2026)

## Abstract (arXiv)

Gaussian Splatting has emerged as a high-performance technique for novel view synthesis, enabling real-time rendering and high-quality reconstruction of small scenes. However, scaling to larger environments has so far relied on partitioning the scene into chunks -- a strategy that introduces artifacts at chunk boundaries, complicates training across varying scales, and is poorly suited to unstructured scenarios such as city-scale flyovers combined with street-level views. Moreover, rendering remains fundamentally limited by GPU memory, as all visible chunks must reside in VRAM simultaneously. We introduce A LoD of Gaussians, a framework for training and rendering ultra-large-scale Gaussian scenes on a single consumer-grade GPU -- without partitioning. Our method stores the full scene out-of-core (e.g., in CPU memory) and trains a Level-of-Detail (LoD) representation directly, dynamically streaming only the relevant Gaussians. A hybrid data structure combining Gaussian hierarchies with Sequential Point Trees enables efficient, view-dependent LoD selection, while a lightweight caching and view scheduling system exploits temporal coherence to support real-time streaming and rendering. Together, these innovations enable seamless multi-scale reconstruction and interactive visualization of complex scenes -- from broad aerial views to fine-grained ground-level details.