# CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2511.04951 · HTML: https://mlsanity.com/paper/2511.04951/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [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)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (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)
- [PipeDream: Fast and Efficient Pipeline Parallel DNN Training](https://mlsanity.com/paper/1806.03377/) (2018)
- [Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models](https://mlsanity.com/paper/2104.05158/) (2021)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus](https://mlsanity.com/paper/2405.13943/) (2024)
- [3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes](https://mlsanity.com/paper/2411.14974/) (2024)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions](https://mlsanity.com/paper/2208.01166/) (2022)
- [MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering](https://mlsanity.com/paper/2407.00435/) (2024)
- [Compression in 3D Gaussian Splatting: A Survey of Methods, Trends, and Future Directions](https://mlsanity.com/paper/2502.19457/) (2025)
- [RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians](https://mlsanity.com/paper/2406.11836/) (2024)
- [Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer](https://mlsanity.com/paper/2408.16978/) (2024)
- [NeutronOrch: Rethinking Sample-based GNN Training under CPU-GPU Heterogeneous Environments](https://mlsanity.com/paper/2311.13225/) (2023)
- [Performance Evaluation of Advanced Features in CUDA Unified Memory](https://mlsanity.com/paper/1910.09598/) (2019)

## Built on by (most cited first, 3 of 3)

- [MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes](https://mlsanity.com/paper/2511.19172/) (2025)
- [TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization](https://mlsanity.com/paper/2605.20150/) (2026)
- [From Splats to Silicon: Rethinking Computational Efficiency of 3DGS](https://mlsanity.com/paper/2609.06157/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) is an increasingly popular novel view synthesis approach due to its fast rendering time, and high-quality output. However, scaling 3DGS to large (or intricate) scenes is challenging due to its large memory requirement, which exceed most GPU's memory capacity. In this paper, we describe CLM, a system that allows 3DGS to render large scenes using a single consumer-grade GPU, e.g., RTX4090. It does so by offloading Gaussians to CPU memory, and loading them into GPU memory only when necessary. To reduce performance and communication overheads, CLM uses a novel offloading strategy that exploits observations about 3DGS's memory access pattern for pipelining, and thus overlap GPU-to-CPU communication, GPU computation and CPU computation. Furthermore, we also exploit observation about the access pattern to reduce communication volume. Our evaluation shows that the resulting implementation can render a large scene that requires 100 million Gaussians on a single RTX4090 and achieve state-of-the-art reconstruction quality.