HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder

TL;DR

HybridGS introduces a novel 3D Gaussian Splatting data compression method that combines explicit data generation with standardized point cloud encoding, achieving faster processing while maintaining comparable quality to state-of-the-art techniques.

Contribution

It proposes a dual-channel sparse representation and a canonical point cloud encoder for efficient, standardized 3DGS data compression, addressing long coding times and format customization issues.

Findings

Provides comparable reconstruction performance to state-of-the-art methods.

Achieves higher encoding and decoding speeds.

Uses a simple rate control scheme for data compression.

Abstract

Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding. They have long coding times and highly customized data format, making it difficult for widespread deployment. This paper presents a new 3DGS compression framework called HybridGS, which takes advantage of both compact generation and standardized point cloud data encoding. HybridGS first generates compact and explicit 3DGS data. A dual-channel sparse representation is introduced to supervise the primitive position and feature bit depth. It then utilizes a canonical point cloud encoder to perform further data compression and form standard output bitstreams. A simple and effective rate control scheme is proposed to pivot the interpretable data compression scheme. At the current stage, HybridGS does not include any modules aimed at improving 3DGS quality during generation. But experiment results show that it still provides comparable reconstruction performance against state-of-the-art methods, with evidently higher encoding and decoding speed. The code is publicly available at https://github.com/Qi-Yangsjtu/HybridGS.