VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

2025-12-02

AI Summary

To address the insufficient robustness of 3D Gaussian Splatting (3DGS) SLAM under motion blur, low-texture regions, and exposure variations, this paper proposes VIGS-SLAM—the first tightly coupled visual-inertial 3D Gaussian SLAM system. Methodologically, it introduces a joint optimization framework integrating IMU preintegration, time-varying bias modeling, and loop-closure-consistent Gaussian updates, enabling rapid IMU initialization while jointly optimizing camera poses, scene depth, and inertial states. Its key contribution lies in embedding IMU dynamic constraints directly into the 3DGS map representation and optimization pipeline, thereby significantly enhancing pose tracking stability and reconstruction fidelity. Extensive experiments on four challenging real-world datasets demonstrate that VIGS-SLAM outperforms state-of-the-art methods in both pose accuracy and mapping quality, while maintaining real-time performance.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM methods achieve dense and photorealistic mapping, their purely visual design degrades under motion blur, low texture, and exposure variations. Our method tightly couples visual and inertial cues within a unified optimization framework, jointly refining camera poses, depths, and IMU states. It features robust IMU initialization, time-varying bias modeling, and loop closure with consistent Gaussian updates. Experiments on four challenging datasets demonstrate our superiority over state-of-the-art methods. Project page: https://vigs-slam.github.io

Problem

• Robust real-time tracking in challenging visual conditions
• High-fidelity 3D reconstruction using visual-inertial fusion
• Joint optimization of camera poses, depths, and IMU states

Innovation

• Visual inertial Gaussian splatting for SLAM
• Unified optimization of camera poses and IMU states
• Robust IMU initialization and loop closure