DVI-SLAM: A Dual Visual Inertial SLAM Network

TL;DR

DVI-SLAM introduces a deep learning-based visual SLAM network that effectively integrates dual visual factors and IMU data, significantly improving localization accuracy over existing methods through dynamic confidence learning.

Contribution

The paper presents a novel end-to-end deep SLAM network with dual visual factors and the capability to incorporate IMU data, enhancing robustness and accuracy.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Reduces absolute trajectory error by over 45% on EuRoC dataset.

Successfully integrates visual and inertial data in a unified framework.

Abstract

Recent deep learning based visual simultaneous localization and mapping (SLAM) methods have made significant progress. However, how to make full use of visual information as well as better integrate with inertial measurement unit (IMU) in visual SLAM has potential research value. This paper proposes a novel deep SLAM network with dual visual factors. The basic idea is to integrate both photometric factor and re-projection factor into the end-to-end differentiable structure through multi-factor data association module. We show that the proposed network dynamically learns and adjusts the confidence maps of both visual factors and it can be further extended to include the IMU factors as well. Extensive experiments validate that our proposed method significantly outperforms the state-of-the-art methods on several public datasets, including TartanAir, EuRoC and ETH3D-SLAM. Specifically, when dynamically fusing the three factors together, the absolute trajectory error for both monocular and stereo configurations on EuRoC dataset has reduced by 45.3% and 36.2% respectively.