Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

TL;DR

This paper introduces an effective rank-based regularization technique for 3D Gaussian Splatting that improves geometry and normal reconstruction, reduces artifacts, and can be integrated into existing methods for better 3D reconstruction quality.

Contribution

It proposes using effective rank analysis as a regularization to address shape convergence issues in 3D Gaussian Splatting, enhancing reconstruction quality.

Findings

Improved normal and geometry reconstruction quality.

Reduced needle-like artifacts in 3D Gaussian primitives.

Compatible with existing 3DGS variants for better results.

Abstract

3D reconstruction from multi-view images is one of the fundamental challenges in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a promising technique capable of real-time rendering with high-quality 3D reconstruction. This method utilizes 3D Gaussian representation and tile-based splatting techniques, bypassing the expensive neural field querying. Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals caused by the Gaussians converging into anisotropic shapes with one dominant variance. We propose using the effective rank analysis to examine the shape statistics of 3D Gaussian primitives, and identify the Gaussians indeed converge into needle-like shapes with the effective rank 1. To address this, we introduce the effective rank as a regularization, which constrains the structure of the Gaussians. Our new regularization method enhances normal and geometry reconstruction while reducing needle-like artifacts. The approach can be integrated as an add-on module to other 3DGS variants, improving their quality without compromising visual fidelity. The project page is available at https://junhahyung.github.io/erankgs.github.io.