A New Split Algorithm for 3D Gaussian Splatting

TL;DR

This paper introduces a novel 3D Gaussian splitting algorithm that enhances the uniformity and surface adherence of Gaussian splatting models, improving their suitability for editing and point cloud extraction.

Contribution

A new 3D Gaussian splitting algorithm with a simple closed-form solution that produces more uniform and surface-bounded Gaussian splatting models.

Findings

Produces more uniform Gaussian splatting models

Improves surface adherence and reduces artifacts

Applicable to any 3D Gaussian model

Abstract

3D Gaussian splatting models, as a novel explicit 3D representation, have been applied in many domains recently, such as explicit geometric editing and geometry generation. Progress has been rapid. However, due to their mixed scales and cluttered shapes, 3D Gaussian splatting models can produce a blurred or needle-like effect near the surface. At the same time, 3D Gaussian splatting models tend to flatten large untextured regions, yielding a very sparse point cloud. These problems are caused by the non-uniform nature of 3D Gaussian splatting models, so in this paper, we propose a new 3D Gaussian splitting algorithm, which can produce a more uniform and surface-bounded 3D Gaussian splatting model. Our algorithm splits an $N$-dimensional Gaussian into two N-dimensional Gaussians. It ensures consistency of mathematical characteristics and similarity of appearance, allowing resulting 3D Gaussian splatting models to be more uniform and a better fit to the underlying surface, and thus more suitable for explicit editing, point cloud extraction and other tasks. Meanwhile, our 3D Gaussian splitting approach has a very simple closed-form solution, making it readily applicable to any 3D Gaussian model.