TIDI-GS: Floater Suppression in 3D Gaussian Splatting for Enhanced Indoor Scene Fidelity

2026-01-14

AI Summary

This work addresses the issue of floating artifacts commonly encountered in indoor scene reconstruction using 3D Gaussian Splatting, which compromise geometric accuracy and application reliability. To this end, we propose TIDI-GS, a lightweight, plug-and-play framework that seamlessly integrates multi-view consistency, spatial proximity, and learned importance scores to accurately identify and remove floating Gaussians—without altering the original architecture. Additionally, we incorporate a monocular depth supervision loss to refine geometric structure while preserving high-frequency details. Our approach significantly enhances reconstruction quality and geometric completeness, yielding robust digital assets suitable for high-fidelity applications.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

3D Gaussian Splatting (3DGS) is a technique to create high-quality, real-time 3D scenes from images. This method often produces visual artifacts known as floaters--nearly transparent, disconnected elements that drift in space away from the actual surface. This geometric inaccuracy undermines the reliability of these models for practical applications, which is critical. To address this issue, we introduce TIDI-GS, a new training framework designed to eliminate these floaters. A key benefit of our approach is that it functions as a lightweight plugin for the standard 3DGS pipeline, requiring no major architectural changes and adding minimal overhead to the training process. The core of our method is a floater pruning algorithm--TIDI--that identifies and removes floaters based on several criteria: their consistency across multiple viewpoints, their spatial relationship to other elements, and an importance score learned during training. The framework includes a mechanism to preserve fine details, ensuring that important high-frequency elements are not mistakenly removed. This targeted cleanup is supported by a monocular depth-based loss function that helps improve the overall geometric structure of the scene. Our experiments demonstrate that TIDI-GS improves both the perceptual quality and geometric integrity of reconstructions, transforming them into robust digital assets, suitable for high-fidelity applications.

Problem

• 3D Gaussian Splatting
• floaters
• geometric accuracy
• visual artifacts
• indoor scene reconstruction

Innovation

• 3D Gaussian Splatting
• floater suppression
• multi-view consistency
• monocular depth loss
• detail preservation