用噪声替换向量量化压缩3D高斯点云，大幅降低存储占用。
Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
- 通过独立构建属性码本，仅存储离散索引替代浮点参数。
- 压缩比达45倍，重建质量仍优于现有方法。
- 兼容主流3DGS查看器，适合实际部署应用。
3D高斯点云（3DGS）在3D重建中表现出色，可实现高质量实时辐射场渲染。但其存储成本高：单场景通常需数百万个高斯点，每个点含59个浮点参数，内存占用约1 GB。为此，本文提出一种压缩方法：分别建立属性码本，仅存储离散码索引。采用噪声替换向量量化技术联合训练码本与模型特征，确保梯度优化与参数离散化一致。实验表明，该方法可实现约45倍的内存压缩，同时在标准3D基准场景上保持优异重建质量。不同码本尺寸的实验揭示了压缩率与图像质量间的权衡。此外，压缩模型与主流3DGS查看器完全兼容，支持更快渲染速度，适用于实际应用。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in 3D reconstruction, achieving high-quality results with real-time radiance field rendering. However, a key challenge is the substantial storage cost: reconstructing a single scene typically requires millions of Gaussian splats, each represented by 59 floating-point parameters, resulting in approximately 1 GB of memory. To address this challenge, we propose a compression method by building separate attribute codebooks and storing only discrete code indices. Specifically, we employ noise-substituted vector quantization technique to jointly train the codebooks and model features, ensuring consistency between gradient descent optimization and parameter discretization. Our method reduces the memory consumption efficiently (around $45\times$) while maintaining competitive reconstruction quality on standard 3D benchmark scenes. Experiments on different codebook sizes show the trade-off between compression ratio and image quality. Furthermore, the trained compressed model remains fully compatible with popular 3DGS viewers and enables faster rendering speed, making it well-suited for practical applications.
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。