Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting

TL;DR

This paper identifies the cause of floating artifacts in 3D Gaussian Splatting and introduces EFA-GS, a method that expands under-optimized Gaussians to reduce artifacts and improve 3D reconstruction quality.

Contribution

The paper provides a frequency-domain analysis of floating artifacts and proposes EFA-GS, a novel approach that dynamically refines Gaussian expansion to eliminate artifacts in 3D Gaussian Splatting.

Findings

EFA-GS significantly reduces floating artifacts in 3D reconstructions.

EFA-GS achieves a 1.68 dB PSNR improvement over baseline methods.

The approach preserves high-frequency details while removing artifacts.

Abstract

3D Gaussian Splatting (3DGS) is a powerful and computationally efficient representation for 3D reconstruction. Despite its strengths, 3DGS often produces floating artifacts, which are erroneous structures detached from the actual geometry and significantly degrade visual fidelity. The underlying mechanisms causing these artifacts, particularly in low-quality initialization scenarios, have not been fully explored. In this paper, we investigate the origins of floating artifacts from a frequency-domain perspective and identify under-optimized Gaussians as the primary source. Based on our analysis, we propose \textit{Eliminating-Floating-Artifacts} Gaussian Splatting (EFA-GS), which selectively expands under-optimized Gaussians to prioritize accurate low-frequency learning. Additionally, we introduce complementary depth-based and scale-based strategies to dynamically refine Gaussian expansion, effectively mitigating detail erosion. Extensive experiments on both synthetic and real-world datasets demonstrate that EFA-GS substantially reduces floating artifacts while preserving high-frequency details, achieving an improvement of 1.68 dB in PSNR over baseline method on our RWLQ dataset. Furthermore, we validate the effectiveness of our approach in downstream 3D editing tasks. Project Website: https://jcwang-gh.github.io/EFA-GS