Technology Category
Computer Vision: 3D Computer VisionSearch and Optimization: Mixed Discrete/Continuous SearchMachine Learning: Deep Generative Models & Autoencoders
PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting
🤖 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
Application Category
📝 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
Research questions and friction points this paper is trying to address.
3D Gaussian Splatting
distractors
multi-view consistency
visual artifacts
robust reconstruction
Innovation
Methods, ideas, or system contributions that make the work stand out.
3D Gaussian Splatting
distractor filtering
multi-view consistency
progressive optimization
robust reconstruction
🔎 Similar Papers
No similar papers found.
