用紧凑表示提升3D高斯点云的存储效率与渲染质量
Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting
- 通过八叉树位置编码建模空间局部性，优化特征表达
- 结合熵压缩与递归体素层次，实现存储量级降低
- 适合需要高效3D重建的移动端或实时应用
我们提出Smol-GS，一种学习3D高斯点云（3DGS）紧凑表示的新方法。该方法学习高效的逐点特征以建模三维空间，捕捉颜色、不透明度、变换及材质等抽象属性。提出基于八叉树的位置编码，显式建模空间局部性，提升表示效率；进一步采用基于熵的压缩技术挖掘特征冗余，并利用递归体素层次压缩点坐标。该设计实现存储量级降低，同时保持表示灵活性。Smol-GS在标准基准上达到当前最优压缩性能，且渲染质量保持高水平。
原文摘要 · Abstract (English)
We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space, which capture abstracted cues, including color, opacity, transformation, and material properties. We propose octree-derived positional encoding, which explicitly models spatial locality and enhances representation efficiency. We further apply entropy-based compression to exploit feature redundancy and compress splat coordinates using a recursive voxel hierarchy. This design enables orders-of-magnitude reduction in storage while preserving representation flexibility. Smol-GS achieves state-of-the-art compression performance on standard benchmarks with high-level rendering 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。