Score: 1

VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

Published: December 2, 2025 | arXiv ID: 2512.02293v1

By: Zihan Zhu , Wei Zhang , Norbert Haala and more

Potential Business Impact:

Makes robots see clearly in tricky places.

Business Areas:
Image Recognition Data and Analytics, Software

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

Page Count
19 pages

Category
Computer Science:
Robotics