一句话：提出 CLM，通过按需卸载高斯到 CPU 内存并重叠通信与计算，使单张消费级 GPU 渲染亿级高斯大场景。
3D Gaussian Splatting（3DGS）渲染速度快且质量高，但大场景或复杂场景所需内存常超出多数 GPU 容量，难以扩展。CLM 提出一种单卡可渲染大场景的系统：将高斯点卸载到 CPU 内存，仅在需要时载入 GPU，并基于 3DGS 的内存访问模式设计新的卸载策略。该策略支持高效流水线，使 GPU 到 CPU 的通信、GPU 计算和 CPU 计算相互重叠，同时利用访问模式减少通信量。评估表明，CLM 能在单张消费级 RTX4090 上渲染需要 1.02 亿个高斯点的大场景，并达到当前最优的重建质量；代码已开源。
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 substantial memory requirement, which exceeds the memory capacity of most GPUs. 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 improve performance and reduce communication overheads, CLM uses a novel offloading strategy based on insights into 3DGS's memory access patterns. This strategy enables efficient pipelining, which overlaps GPU-to-CPU communication, GPU computation and CPU computation. Furthermore, CLM exploits these access patterns to reduce communication volume. Our evaluation shows that the resulting implementation can render a large scene that requires 102 million Gaussians on a single RTX4090 and achieve state-of-the-art reconstruction quality. The code is open-sourced at: https://github.com/nyu-systems/CLM-GS
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2511-04951,
title = {CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting},
author = {Hexu Zhao and Xiwen Min and Xiaoteng Liu and Moonjun Gong and Yiming Li and Ang Li and Saining Xie and Jinyang Li and Aurojit Panda},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790140}
}