Smol-GS: 抽象3D高斯溅射的紧凑表示
Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting
AI总结:
提出Smol-GS方法,通过八叉树位置编码和熵压缩学习高效溅射特征,实现3D高斯溅射的紧凑表示,在保持渲染质量的同时大幅降低存储。
摘要:
我们提出Smol-GS,一种学习3D高斯溅射(3DGS)紧凑表示的新方法。我们的方法学习高效的逐溅射特征来建模3D空间,这些特征捕获抽象线索,包括颜色、不透明度、变换和材质属性。我们提出八叉树导出的位置编码,显式建模空间局部性并增强表示效率。我们进一步应用基于熵的压缩来利用特征冗余,并使用递归体素层次压缩溅射坐标。这种设计在保持表示灵活性的同时,实现了数量级的存储减少。Smol-GS在标准基准测试上以高渲染质量实现了最先进的压缩性能。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。