VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
This work addresses robustness issues in SLAM systems for applications like robotics and AR/VR, but it is incremental as it builds on existing 3D Gaussian Splatting methods by adding inertial integration.
The paper tackles the problem of visual SLAM degradation under challenging conditions like motion blur and low texture by tightly coupling visual and inertial cues, achieving robust real-time tracking and high-fidelity reconstruction with demonstrated superiority over state-of-the-art methods on four datasets.
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