EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting

TL;DR

EntropyGS introduces a novel entropy coding method for 3D Gaussian Splatting that significantly reduces data size while preserving visual quality, enabling efficient storage and transmission.

Contribution

The paper presents a new entropy coding approach tailored for 3DGS Gaussian attributes, leveraging their statistical properties for high compression efficiency.

Findings

Achieves approximately 30x rate reduction on benchmark datasets.

Maintains similar rendering quality with faster encoding/decoding times.

Provides detailed analysis of Gaussian attribute distributions and correlations.

Abstract

As an emerging novel view synthesis approach, 3D Gaussian Splatting (3DGS) demonstrates fast training/rendering with superior visual quality. The two tasks of 3DGS, Gaussian creation and view rendering, are typically separated over time or devices, and thus storage/transmission and finally compression of 3DGS Gaussians become necessary. We begin with a correlation and statistical analysis of 3DGS Gaussian attributes. An inspiring finding in this work reveals that spherical harmonic AC attributes precisely follow Laplace distributions, while mixtures of Gaussian distributions can approximate rotation, scaling, and opacity. Additionally, harmonic AC attributes manifest weak correlations with other attributes except for inherited correlations from a color space. A factorized and parameterized entropy coding method, EntropyGS, is hereinafter proposed. During encoding, distribution parameters of each Gaussian attribute are estimated to assist their entropy coding. The quantization for entropy coding is adaptively performed according to Gaussian attribute types. EntropyGS demonstrates about 30x rate reduction on benchmark datasets while maintaining similar rendering quality compared to input 3DGS data, with a fast encoding and decoding time.