GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting

TL;DR

GS^2 introduces a graph-based optimization method for 3D Gaussian Splatting that significantly reduces memory usage while improving rendering quality through adaptive densification, pruning, and feature-guided point adjustment.

Contribution

The paper presents a novel graph-based spatial distribution optimization framework for 3D Gaussian Splatting, enhancing compactness and quality over prior methods.

Findings

Achieves higher PSNR with only 12.5% of Gaussian points compared to 3DGS.

Outperforms baseline methods in rendering quality and memory efficiency.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering. Nevertheless, its practicality is constrained by the high memory cost due to a huge number of Gaussian points. Many pruning-based 3DGS variants have been proposed for memory saving, but often compromise spatial consistency and may lead to rendering artifacts. To address this issue, we propose graph-based spatial distribution optimization for compact 3D Gaussian Splatting (GS\textasciicircum2), which enhances reconstruction quality by optimizing the spatial distribution of Gaussian points. Specifically, we introduce an evidence lower bound (ELBO)-based adaptive densification strategy that automatically controls the densification process. In addition, an opacity-aware progressive pruning strategy is proposed to further reduce memory consumption by dynamically removing low-opacity Gaussian points. Furthermore, we propose a graph-based feature encoding module to adjust the spatial distribution via feature-guided point shifting. Extensive experiments validate that GS\textasciicircum2 achieves a compact Gaussian representation while delivering superior rendering quality. Compared with 3DGS, it achieves higher PSNR with only about 12.5\% Gaussian points. Furthermore, it outperforms all compared baselines in both rendering quality and memory efficiency.