A Benchmark for Gaussian Splatting Compression and Quality Assessment Study

TL;DR

This paper introduces GGSC, a novel graph-based compression method for Gaussian splatting data, and creates a new dataset for assessing visual quality, revealing how different distortions impact perceived quality.

Contribution

It proposes GGSC, the first traditional Gaussian splatting compression method based on graph signal processing, and develops a comprehensive dataset for Gaussian splatting quality assessment.

Findings

GGSC effectively compresses Gaussian splatting data with high fidelity.

The dataset reveals how high-frequency clipping and quantization affect visual quality.

Subjective scores correlate with specific distortion types, aiding future compression evaluation.

Abstract

To fill the gap of traditional GS compression method, in this paper, we first propose a simple and effective GS data compression anchor called Graph-based GS Compression (GGSC). GGSC is inspired by graph signal processing theory and uses two branches to compress the primitive center and attributes. We split the whole GS sample via KDTree and clip the high-frequency components after the graph Fourier transform. Followed by quantization, G-PCC and adaptive arithmetic coding are used to compress the primitive center and attribute residual matrix to generate the bitrate file. GGSS is the first work to explore traditional GS compression, with advantages that can reveal the GS distortion characteristics corresponding to typical compression operation, such as high-frequency clipping and quantization. Second, based on GGSC, we create a GS Quality Assessment dataset (GSQA) with 120 samples. A subjective experiment is conducted in a laboratory environment to collect subjective scores after rendering GS into Processed Video Sequences (PVS). We analyze the characteristics of different GS distortions based on Mean Opinion Scores (MOS), demonstrating the sensitivity of different attributes distortion to visual quality. The GGSC code and the dataset, including GS samples, MOS, and PVS, are made publicly available at https://github.com/Qi-Yangsjtu/GGSC.