用球形高斯替换球谐函数，大幅降低3D高斯点云的显存占用。
MEGS$^{2}$: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning
- 用可任意朝向的球形高斯作为颜色表示，替代传统球谐函数。
- 提出统一软剪枝框架，同时优化点数和每点参数量，显存降低50%。
- 适合部署在边缘设备上的高效3D新视角合成方案，尤其关注渲染显存瓶颈。
3D高斯点云（3DGS）已成为主流的新视角合成技术，但其高显存消耗严重限制了在边缘设备上的应用。尽管已有众多压缩方法被提出以提升效率，但多数仅关注存储压缩，未能解决渲染时显存占用这一关键瓶颈。为此，我们提出MEGS²，一种新型内存高效的框架，通过联合优化两个核心因素——总基元数量与每个基元的参数量，实现前所未有的内存压缩。具体而言，我们用轻量且可任意朝向的球形高斯瓣（spherical Gaussian lobes）替代内存密集型的球谐函数作为颜色表示。更重要的是，我们提出一种统一的软剪枝框架，将基元数量与瓣数剪枝建模为单一约束优化问题。实验表明，相较于现有方法，MEGS²在静态显存上减少50%，渲染显存减少40%，同时保持相当的渲染质量。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has emerged as a dominant novel-view synthesis technique, but its high memory consumption severely limits its applicability on edge devices. A growing number of 3DGS compression methods have been proposed to make 3DGS more efficient, yet most only focus on storage compression and fail to address the critical bottleneck of rendering memory. To address this problem, we introduce MEGS$^{2}$, a novel memory-efficient framework that tackles this challenge by jointly optimizing two key factors: the total primitive number and the parameters per primitive, achieving unprecedented memory compression. Specifically, we replace the memory-intensive spherical harmonics with lightweight, arbitrarily oriented spherical Gaussian lobes as our color representations. More importantly, we propose a unified soft pruning framework that models primitive-number and lobe-number pruning as a single constrained optimization problem. Experiments show that MEGS$^{2}$ achieves a 50% static VRAM reduction and a 40% rendering VRAM reduction compared to existing methods, while maintaining comparable rendering quality. Project page: https://megs-2.github.io/
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。