SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction

TL;DR

This paper introduces SafeguardGS, a pruning method for 3D Gaussian Splatting that effectively reduces primitives while maintaining quality, by focusing on pixel-level pruning with a color similarity score function, enabling high compression with minimal quality loss.

Contribution

The paper categorizes 3DGS pruning techniques, highlights the effectiveness of pixel-level pruning, and proposes a novel score function based on color similarity for optimal primitive pruning.

Findings

Pixel-level pruning maintains high rendering quality with minimal performance loss.

SafeguardGS achieves 10x compression by retaining only 10% of primitives.

Color similarity score function outperforms other methods in primitive importance assessment.

Abstract

3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis. However, its suboptimal densification process results in the excessively large number of Gaussian primitives, which impacts frame-per-second and increases memory usage, making it unsuitable for low-end devices. To address this issue, many follow-up studies have proposed various pruning techniques with score functions designed to identify and remove less important primitives. Nonetheless, a comprehensive discussion of their effectiveness and implications across all techniques is missing. In this paper, we are the first to categorize 3DGS pruning techniques into two types: Scene-level pruning and Pixel-level pruning, distinguished by their scope for ranking primitives. Our subsequent experiments reveal that, while scene-level pruning leads to disastrous quality drops under extreme decimation of Gaussian primitives, pixel-level pruning not only sustains relatively high rendering quality with minuscule performance degradation but also provides an inherent boundary of pruning, i.e., a safeguard of Gaussian pruning. Building on this observation, we further propose multiple variations of score functions based on the factors of rendering equations and discover that assessing based on color similarity with blending weight is the most effective method for discriminating insignificant primitives. In our experiments, our SafeguardGS with the optimal score function shows the highest PSNR-per-primitive performance under an extreme pruning setting, retaining only about 10% of the primitives from the original 3DGS scene (i.e., 10x compression ratio). We believe our research provides valuable insights for optimizing 3DGS for future works.