Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Wenhua, Su, Chenpeng, Zhu, Siting, Deng, Tianchen, Jiao, Jianhao, Wang, Guangming, Kanoulas, Dimitrios, Liu, Zhe, Wang, Hesheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.19420
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908806575816704
author Wu, Wenhua
Su, Chenpeng
Zhu, Siting
Deng, Tianchen
Jiao, Jianhao
Wang, Guangming
Kanoulas, Dimitrios
Liu, Zhe
Wang, Hesheng
author_facet Wu, Wenhua
Su, Chenpeng
Zhu, Siting
Deng, Tianchen
Jiao, Jianhao
Wang, Guangming
Kanoulas, Dimitrios
Liu, Zhe
Wang, Hesheng
contents Recent advances in neural radiation fields (NeRF) and 3D Gaussian-based SLAM have achieved impressive localization accuracy and high-quality dense mapping in static scenes. However, these methods remain challenged in dynamic environments, where moving objects violate the static-world assumption and introduce inconsistent observations that degrade both camera tracking and map reconstruction. This motivates two fundamental problems: robustly identifying dynamic objects and modeling them online. To address these limitations, we propose CAD-SLAM, a Consistency-Aware Dynamic SLAM framework with dynamic-static decoupled mapping. Our key insight is that dynamic objects inherently violate cross-view and cross-time scene consistency. We detect object motion by analyzing geometric and texture discrepancies between historical map renderings and real-world observations. Once a moving object is identified, we perform bidirectional dynamic object tracking (both backward and forward in time) to achieve complete sequence-wise dynamic recognition. Our consistency-aware dynamic detection model achieves category-agnostic, instantaneous dynamic identification, which effectively mitigates motion-induced interference during localization and mapping. In addition, we introduce a dynamic-static decoupled mapping strategy that employs a temporal Gaussian model for online incremental dynamic modeling. Experiments conducted on multiple dynamic datasets demonstrate the flexible and accurate dynamic segmentation capabilities of our method, along with the state-of-the-art performance in both localization and mapping.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19420
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping
Wu, Wenhua
Su, Chenpeng
Zhu, Siting
Deng, Tianchen
Jiao, Jianhao
Wang, Guangming
Kanoulas, Dimitrios
Liu, Zhe
Wang, Hesheng
Computer Vision and Pattern Recognition
Recent advances in neural radiation fields (NeRF) and 3D Gaussian-based SLAM have achieved impressive localization accuracy and high-quality dense mapping in static scenes. However, these methods remain challenged in dynamic environments, where moving objects violate the static-world assumption and introduce inconsistent observations that degrade both camera tracking and map reconstruction. This motivates two fundamental problems: robustly identifying dynamic objects and modeling them online. To address these limitations, we propose CAD-SLAM, a Consistency-Aware Dynamic SLAM framework with dynamic-static decoupled mapping. Our key insight is that dynamic objects inherently violate cross-view and cross-time scene consistency. We detect object motion by analyzing geometric and texture discrepancies between historical map renderings and real-world observations. Once a moving object is identified, we perform bidirectional dynamic object tracking (both backward and forward in time) to achieve complete sequence-wise dynamic recognition. Our consistency-aware dynamic detection model achieves category-agnostic, instantaneous dynamic identification, which effectively mitigates motion-induced interference during localization and mapping. In addition, we introduce a dynamic-static decoupled mapping strategy that employs a temporal Gaussian model for online incremental dynamic modeling. Experiments conducted on multiple dynamic datasets demonstrate the flexible and accurate dynamic segmentation capabilities of our method, along with the state-of-the-art performance in both localization and mapping.
title CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19420