Saved in:
Bibliographic Details
Main Authors: Wu, Wenhua, Wang, Guangming, Deng, Ting, Aegidius, Sebastian, Shanks, Stuart, Modugno, Valerio, Kanoulas, Dimitrios, Wang, Hesheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11776
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911800897830912
author Wu, Wenhua
Wang, Guangming
Deng, Ting
Aegidius, Sebastian
Shanks, Stuart
Modugno, Valerio
Kanoulas, Dimitrios
Wang, Hesheng
author_facet Wu, Wenhua
Wang, Guangming
Deng, Ting
Aegidius, Sebastian
Shanks, Stuart
Modugno, Valerio
Kanoulas, Dimitrios
Wang, Hesheng
contents Recent research on Simultaneous Localization and Mapping (SLAM) based on implicit representation has shown promising results in indoor environments. However, there are still some challenges: the limited scene representation capability of implicit encodings, the uncertainty in the rendering process from implicit representations, and the disruption of consistency by dynamic objects. To address these challenges, we propose a real-time dynamic visual SLAM system based on local-global fusion neural implicit representation, named DVN-SLAM. To improve the scene representation capability, we introduce a local-global fusion neural implicit representation that enables the construction of an implicit map while considering both global structure and local details. To tackle uncertainties arising from the rendering process, we design an information concentration loss for optimization, aiming to concentrate scene information on object surfaces. The proposed DVN-SLAM achieves competitive performance in localization and mapping across multiple datasets. More importantly, DVN-SLAM demonstrates robustness in dynamic scenes, a trait that sets it apart from other NeRF-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11776
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding
Wu, Wenhua
Wang, Guangming
Deng, Ting
Aegidius, Sebastian
Shanks, Stuart
Modugno, Valerio
Kanoulas, Dimitrios
Wang, Hesheng
Computer Vision and Pattern Recognition
Recent research on Simultaneous Localization and Mapping (SLAM) based on implicit representation has shown promising results in indoor environments. However, there are still some challenges: the limited scene representation capability of implicit encodings, the uncertainty in the rendering process from implicit representations, and the disruption of consistency by dynamic objects. To address these challenges, we propose a real-time dynamic visual SLAM system based on local-global fusion neural implicit representation, named DVN-SLAM. To improve the scene representation capability, we introduce a local-global fusion neural implicit representation that enables the construction of an implicit map while considering both global structure and local details. To tackle uncertainties arising from the rendering process, we design an information concentration loss for optimization, aiming to concentrate scene information on object surfaces. The proposed DVN-SLAM achieves competitive performance in localization and mapping across multiple datasets. More importantly, DVN-SLAM demonstrates robustness in dynamic scenes, a trait that sets it apart from other NeRF-based methods.
title DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11776