arXiv:2511.04951cs.CV2025-11中稿 · appear in the 2026…被引 4

让3D高斯点渲染突破显存限制,单张消费级显卡也能处理上亿点云。

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

  • 将高斯点暂存于CPU内存,按需加载到GPU,突破显存瓶颈。
  • 通过优化数据调度策略,实现计算与通信重叠,提升运行效率。
  • 实测可在单张RTX4090上渲染需1亿高斯点的大场景,效果领先。

3D高斯点渲染(3DGS)因其快速渲染和高质量输出而日益流行。然而,其巨大的内存需求使其难以扩展至大型或复杂场景,超出多数GPU的显存容量。本文提出CLM系统,使3DGS能在单张消费级显卡(如RTX4090)上渲染大场景。该系统将高斯点暂存于CPU内存,仅在需要时加载至GPU。为降低性能与通信开销,CLM利用3DGS的内存访问模式,设计新型卸载策略以实现流水线化,从而重叠GPU与CPU间的通信、计算过程。此外,还通过分析访问模式减少通信量。评估表明,该系统可在单张RTX4090上渲染需1亿高斯点的大场景,并达到当前最优重建质量。

原文摘要 · Abstract (English)

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.

3D生成显存优化高斯点

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。