Voxel-GS: Quantized Scaffold Gaussian Splatting Compression with Run-Length Coding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Chunyang, Liu, Xiangrui, Wang, Shiqi, Li, Zhu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915686454919168
author Fu, Chunyang
Liu, Xiangrui
Wang, Shiqi
Li, Zhu
author_facet Fu, Chunyang
Liu, Xiangrui
Wang, Shiqi
Li, Zhu
contents Substantial Gaussian splatting format point clouds require effective compression. In this paper, we propose Voxel-GS, a simple yet highly effective framework that departs from the complex neural entropy models of prior work, instead achieving competitive performance using only a lightweight rate proxy and run-length coding. Specifically, we employ a differentiable quantization to discretize the Gaussian attributes of Scaffold-GS. Subsequently, a Laplacian-based rate proxy is devised to impose an entropy constraint, guiding the generation of high-fidelity and compact reconstructions. Finally, this integer-type Gaussian point cloud is compressed losslessly using Octree and run-length coding. Experiments validate that the proposed rate proxy accurately estimates the bitrate of run-length coding, enabling Voxel-GS to eliminate redundancy and optimize for a more compact representation. Consequently, our method achieves a remarkable compression ratio with significantly faster coding speeds than prior art. The code is available at https://github.com/zb12138/VoxelGS.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17528
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Voxel-GS: Quantized Scaffold Gaussian Splatting Compression with Run-Length Coding
Fu, Chunyang
Liu, Xiangrui
Wang, Shiqi
Li, Zhu
Multimedia
Substantial Gaussian splatting format point clouds require effective compression. In this paper, we propose Voxel-GS, a simple yet highly effective framework that departs from the complex neural entropy models of prior work, instead achieving competitive performance using only a lightweight rate proxy and run-length coding. Specifically, we employ a differentiable quantization to discretize the Gaussian attributes of Scaffold-GS. Subsequently, a Laplacian-based rate proxy is devised to impose an entropy constraint, guiding the generation of high-fidelity and compact reconstructions. Finally, this integer-type Gaussian point cloud is compressed losslessly using Octree and run-length coding. Experiments validate that the proposed rate proxy accurately estimates the bitrate of run-length coding, enabling Voxel-GS to eliminate redundancy and optimize for a more compact representation. Consequently, our method achieves a remarkable compression ratio with significantly faster coding speeds than prior art. The code is available at https://github.com/zb12138/VoxelGS.
title Voxel-GS: Quantized Scaffold Gaussian Splatting Compression with Run-Length Coding
topic Multimedia
url https://arxiv.org/abs/2512.17528