VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

TL;DR

VIGS-SLAM introduces a real-time visual-inertial SLAM system utilizing Gaussian Splatting for high-fidelity 3D mapping, robustly handling challenging conditions through joint optimization of visual and inertial data.

Contribution

The paper presents a novel visual-inertial SLAM framework that tightly integrates Gaussian Splatting with inertial data, improving robustness and reconstruction quality over existing methods.

Findings

Outperforms state-of-the-art SLAM methods on challenging datasets.

Achieves robust real-time tracking and high-fidelity 3D reconstruction.

Effectively handles motion blur, low texture, and exposure variations.

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 challenging conditions such as motion blur, low texture, and exposure variations. Our method tightly couples visual and inertial cues within a unified optimization framework, jointly optimizing camera poses, depths, and IMU states. It features robust IMU initialization, time-varying bias modeling, and loop closure with consistent Gaussian updates. Experiments on five challenging datasets demonstrate our superiority over state-of-the-art methods. Project page: https://vigs-slam.github.io