Structured Image-based Coding for Efficient Gaussian Splatting Compression

TL;DR

This paper introduces GSICO, a novel image-based compression method for Gaussian Splatting models that significantly reduces file size while maintaining high visual quality, enabling practical multimedia applications.

Contribution

The paper presents a new structured image-based coding scheme for GS models, including a mapping algorithm and conventional image codec, achieving high compression with minimal quality loss.

Findings

Achieves an average of 20.2x compression with minimal perceptual quality loss.

Outperforms existing GS compression methods in rate-distortion trade-offs.

Effective on multiple datasets including Tanks and Temples, Deep Blending, and Mip-NeRF360.

Abstract

Gaussian Splatting (GS) has recently emerged as a state-of-the-art representation for radiance fields, combining real-time rendering with high visual fidelity. However, GS models require storing millions of parameters, leading to large file sizes that impair their use in practical multimedia systems. To address this limitation, this paper introduces GS Image-based Compression (GSICO), a novel GS codec that efficiently compresses pre-trained GS models while preserving perceptual fidelity. The core contribution lies in a mapping procedure that arranges GS parameters into structured images, guided by a novel algorithm that enhances spatial coherence. These GS parameter images are then encoded using a conventional image codec. Experimental evaluations on Tanks and Temples, Deep Blending, and Mip-NeRF360 datasets show that GSICO achieves average compression factors of 20.2x with minimal loss in visual quality, as measured by PSNR, SSIM, and LPIPS. Compared with state-of-the-art GS compression methods, the proposed codec consistently yields superior rate-distortion (RD) trade-offs.