MAVIS: Multi-Camera Augmented Visual-Inertial SLAM using SE2(3) Based Exact IMU Pre-integration

TL;DR

MAVIS is a multi-camera visual-inertial SLAM system that leverages wide field-of-view cameras and an advanced IMU pre-integration based on SE2(3), achieving state-of-the-art performance in challenging scenarios.

Contribution

The paper introduces a novel IMU pre-integration method using SE2(3) automorphism and extends multi-camera SLAM techniques, significantly improving tracking accuracy and robustness.

Findings

Won first place in Hilti SLAM Challenge 2023 vision-IMU tracks.

Outperformed second place by 1.7 times in challenge scores.

Demonstrated effectiveness on public datasets in challenging scenarios.

Abstract

We present a novel optimization-based Visual-Inertial SLAM system designed for multiple partially overlapped camera systems, named MAVIS. Our framework fully exploits the benefits of wide field-of-view from multi-camera systems, and the metric scale measurements provided by an inertial measurement unit (IMU). We introduce an improved IMU pre-integration formulation based on the exponential function of an automorphism of SE_2(3), which can effectively enhance tracking performance under fast rotational motion and extended integration time. Furthermore, we extend conventional front-end tracking and back-end optimization module designed for monocular or stereo setup towards multi-camera systems, and introduce implementation details that contribute to the performance of our system in challenging scenarios. The practical validity of our approach is supported by our experiments on public datasets. Our MAVIS won the first place in all the vision-IMU tracks (single and multi-session SLAM) on Hilti SLAM Challenge 2023 with 1.7 times the score compared to the second place.