用字典学习压缩3D高斯点云，不重训练也能提速省空间
Smaller and Faster 3DGS via Post-Training Dictionary Learning
- 后训练阶段通过字典学习压缩3DGS模型
- 平均压缩3.95倍，渲染速度提升23%以上
- 无需修改原模型，适合部署在低端设备
3D高斯点阵（3DGS）是一种有前景的实时渲染神经场景表示方法，但训练后的模型通常内存占用大，限制了在低性能设备上的部署。现有压缩技术常引入多个可训练参数，虽实现高压缩比，但图像质量明显下降。本文提出首个基于字典学习的3DGS压缩框架。所提后训练压缩流程可应用于任意3DGS模型，无需重新训练或修改原有结构。该方法实现简单，却具备显著压缩能力，保持图像质量并提升实时渲染性能。在13个基准场景上，对3DGS、3DGS-MCMC和PixelGS分别实现平均3.95倍、3.10倍和4.55倍压缩，相应渲染速度提升23.3%、24.3%和25.3%，且图像质量无损失。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) is a promising neural scene representation for real-time rendering, but trained models often suffer from large memory footprints, limiting deployment on less powerful devices. Existing compression techniques often lead to architectures with several additional trainable parameters. While achieving outstanding compression ratios, they introduce noticeable drops in image quality. In this work, we introduce the first dictionary-learning-based compression framework for 3DGS. The proposed post-training compression pipeline can be deployed in virtually any 3DGS model without the need for re-training or modifications to existing 3DGS models. Our compression framework is straightforward to implement, yet provides significant compression capabilities, preserves image quality, and improves real-time rendering performance. Across 13 benchmark scenes, our approach achieves an average compression ratio of 3.95x, 3.10x, and 4.55x when applied to 3DGS, 3DGS-MCMC, and PixelGS, respectively. This yields consistent rendering speedups of 23.3%, 24.3%, and 25.3%, while maintaining image quality.
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。