PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting

TL;DR

PDF-GS introduces a progressive multi-phase optimization framework that enhances 3D Gaussian Splatting by filtering out distractors, resulting in more robust and high-fidelity 3D reconstructions without extra inference costs.

Contribution

It leverages the inherent self-filtering ability of 3DGS, amplifies it through progressive filtering, and achieves state-of-the-art, robust 3D reconstructions with minimal modifications to existing frameworks.

Findings

Outperforms baselines across diverse datasets and real-world conditions.

Achieves high-fidelity, distractor-free 3D reconstructions.

Requires no architectural changes or additional inference overhead.

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have enabled impressive real-time photorealistic rendering. However, conventional training pipelines inherently assume full multi-view consistency among input images, which makes them sensitive to distractors that violate this assumption and cause visual artifacts. In this work, we revisit an underexplored aspect of 3DGS: its inherent ability to suppress inconsistent signals. Building on this insight, we propose PDF-GS (Progressive Distractor Filtering for Robust 3D Gaussian Splatting), a framework that amplifies this self-filtering property through a progressive multi-phase optimization. The progressive filtering phases gradually remove distractors by exploiting discrepancy cues, while the following reconstruction phase restores fine-grained, view-consistent details from the purified Gaussian representation. Through this iterative refinement, PDF-GS achieves robust, high-fidelity, and distractor-free reconstructions, consistently outperforming baselines across diverse datasets and challenging real-world conditions. Moreover, our approach is lightweight and easily adaptable to existing 3DGS frameworks, requiring no architectural changes or additional inference overhead, leading to a new state-of-the-art performance. The code is publicly available at https://github.com/kangrnin/PDF-GS.