DVI-SLAM: A Dual Visual Inertial SLAM Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Peng, Xiongfeng, Liu, Zhihua, Li, Weiming, Tan, Ping, Cho, SoonYong, Wang, Qiang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914812284370944
author Peng, Xiongfeng
Liu, Zhihua
Li, Weiming
Tan, Ping
Cho, SoonYong
Wang, Qiang
author_facet Peng, Xiongfeng
Liu, Zhihua
Li, Weiming
Tan, Ping
Cho, SoonYong
Wang, Qiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13814
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DVI-SLAM: A Dual Visual Inertial SLAM Network
Peng, Xiongfeng
Liu, Zhihua
Li, Weiming
Tan, Ping
Cho, SoonYong
Wang, Qiang
Computer Vision and Pattern Recognition
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.
title DVI-SLAM: A Dual Visual Inertial SLAM Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.13814