RU4D-SLAM: Reweighting Uncertainty in Gaussian Splatting SLAM for 4D Scene Reconstruction

2026-02-24

AI Summary

Existing SLAM methods suffer from reconstruction distortions and tracking failures in dynamic environments due to interference from moving objects and low-quality input. This work proposes RU4D-SLAM, which introduces a temporal dimension into the 3D Gaussian splatting representation to construct a 4D scene model. By incorporating pixel-level uncertainty modeling, motion-blur-aware rendering, a semantic-guided uncertainty reweighting mechanism, and learnable opacity optimization, the method achieves adaptive mapping and robust tracking in dynamic scenes. Experimental results demonstrate that RU4D-SLAM significantly outperforms state-of-the-art approaches in both trajectory accuracy and 4D reconstruction quality, particularly excelling in complex dynamic scenarios involving moving objects and image blur.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Combining 3D Gaussian splatting with Simultaneous Localization and Mapping (SLAM) has gained popularity as it enables continuous 3D environment reconstruction during motion. However, existing methods struggle in dynamic environments, particularly moving objects complicate 3D reconstruction and, in turn, hinder reliable tracking. The emergence of 4D reconstruction, especially 4D Gaussian splatting, offers a promising direction for addressing these challenges, yet its potential for 4D-aware SLAM remains largely underexplored. Along this direction, we propose a robust and efficient framework, namely Reweighting Uncertainty in Gaussian Splatting SLAM (RU4D-SLAM) for 4D scene reconstruction, that introduces temporal factors into spatial 3D representation while incorporating uncertainty-aware perception of scene changes, blurred image synthesis, and dynamic scene reconstruction. We enhance dynamic scene representation by integrating motion blur rendering, and improve uncertainty-aware tracking by extending per-pixel uncertainty modeling, which is originally designed for static scenarios, to handle blurred images. Furthermore, we propose a semantic-guided reweighting mechanism for per-pixel uncertainty estimation in dynamic scenes, and introduce a learnable opacity weight to support adaptive 4D mapping. Extensive experiments on standard benchmarks demonstrate that our method substantially outperforms state-of-the-art approaches in both trajectory accuracy and 4D scene reconstruction, particularly in dynamic environments with moving objects and low-quality inputs. Code available: https://ru4d-slam.github.io

Problem

• Gaussian Splatting
• SLAM
• 4D Reconstruction
• Dynamic Environments
• Uncertainty Modeling

Innovation

• 4D Gaussian Splatting
• Uncertainty-aware SLAM
• Motion Blur Rendering
• Semantic-guided Reweighting
• Dynamic Scene Reconstruction