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

2026-04-14

AI Summary

Traditional 3D Gaussian Splatting (3DGS) suffers from limited robustness and often produces artifacts when input images contain outliers that violate multi-view consistency. To address this, this work proposes PDF-GS, a novel framework that systematically exploits and enhances the inherent self-filtering capability of 3DGS. PDF-GS introduces a lightweight, progressive optimization mechanism that requires no architectural modifications and incurs no additional inference overhead. It progressively removes outliers through multi-stage discrepancy cues while simultaneously refining geometric details via view-consistent reconstruction. Evaluated across diverse datasets and complex real-world scenes, the method significantly improves both reconstruction robustness and fidelity, achieving state-of-the-art performance in outlier-free, high-fidelity 3D reconstruction.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• 3D Gaussian Splatting
• distractors
• multi-view consistency
• visual artifacts
• robust reconstruction

Innovation

• 3D Gaussian Splatting
• distractor filtering
• multi-view consistency
• progressive optimization
• robust reconstruction