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

Qi Yang, Le Yang, Geert Van der Auwera, Zhu Li

Abstract: Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding. They have long encoding and decoding 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 carry out further data compression and form standard output bitstreams. A simple and effective rate control scheme is proposed to pivot the interpretable data compression scheme. 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 faster encoding and decoding speed. The code is publicly available at https://github.com/Qi-Yangsjtu/HybridGS .

Lay Summary: Current 3D Gaussian Splatting (3DGS) methods suffer from long encoding and decoding times, which make it challenging to be standardized and widely deployed. In this paper, we design a new 3DGS compression pipeline, HybridGS, by combining compact 3DGS generation and point cloud encoders. Our results show that HybridGS can realize comparable compression ratios with SOTA methods, while obviously achieving faster encoding and decoding speeds: from over 1 minute to 0.4~1.6 seconds.

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Link To Code: https://github.com/Qi-Yangsjtu/HybridGS

Primary Area: Applications->Computer Vision

Keywords: 3D Gaussian Splatting, Compression, Sparse Representation

Submission Number: 786