HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression

TL;DR

This paper introduces HEMGS, a hybrid entropy model for efficient 3D Gaussian Splatting data compression, combining a variable-rate predictor, hyperprior, and autoregressive network to achieve significant size reduction while preserving quality.

Contribution

The paper presents a novel hybrid entropy model that enables versatile lossy-lossless compression of 3D Gaussian Splatting data with a single model and improved entropy coding.

Findings

Achieves about 40% average size reduction on benchmarks.

Maintains rendering quality comparable to baseline methods.

Sets new state-of-the-art in 3D data compression.

Abstract

In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predictor enables variable-rate compression with a single model and a hyperparameter $\lambda$ by producing a learned Quantization Step feature for versatile lossy compression. Second, to improve lossless compression, the hyperprior network captures both scene-agnostic and scene-specific features to generate a prior feature, while the autoregressive network employs an adaptive context selection algorithm with flexible receptive fields to produce a contextual feature. By integrating these two features, HEMGS can accurately estimate the distribution of the current coding element within each attribute, enabling improved entropy coding and reduced storage. We integrate HEMGS into a compression framework, and experimental results on four benchmarks indicate that HEMGS achieves about a 40% average reduction in size while maintaining rendering quality over baseline methods and achieving state-of-the-art compression results.