SDD-SLAM: Semantic-Driven Dynamic SLAM With Gaussian Splatting

doi:10.1109/LRA.2025.3561565

	SDD-SLAM: Semantic-Driven Dynamic SLAM With Gaussian Splatting
	Liu, Haosong 1; Wang, Long 1; Luo, Haiyong 2; Zhao, Fang 1; Chen, Runze 1; Chen, Yushi 1; Xiao, Mingyu 1; Yan, Jiaquan 1; Luo, Dan 3
	2025-06-01
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
卷号	10 期号:6 页码:5721-5728
摘要	Recently, significant advancements have been made in 3D Gaussian Splatting SLAM for dynamic environments. However, most existing methods primarily address active dynamic objects, such as people and vehicles, and fail to account for the impact of passive dynamic objects on localization and mapping. This results in the presence of numerous artifacts left by dynamic objects in the scene, which diminishes the accuracy of pose estimation. To address these challenges, we propose SDD-SLAM, a semantic-driven SLAM system based on 3D Gaussian Splatting. Extensive experiments conducted on the TUM and BONN datasets demonstrate that the proposed methods, including refined mask expansion, edge noise filtering, object-level dynamic object removal based on semantic Gaussians, and object-level density control strategy for Gaussian ellipsoids, significantly enhance the accuracy of camera pose estimation and the quality of map reconstruction in dynamic environments, achieving state-of-the-art performance.
关键词	Semantics Simultaneous localization and mapping Dynamics Three-dimensional displays Ellipsoids Rendering (computer graphics) Vehicle dynamics Pose estimation Optimization Noise SLAM visual Tracking semantic scene understanding dynamic environments Gaussian splatting
DOI	10.1109/LRA.2025.3561565
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of Chinese Academy of Sciences[XDA28040500] ; National Natural Science Foundation of China[62261042] ; Key Research Projects of the Joint Research Fund for Beijing Natural Science Foundation ; FengtaiRail Transit Frontier Research Joint Fund[L221003] ; Beijing Natural Science Foundation[4232035] ; Yibin City Introduction of High-Level Talent Project[2024YG01] ; China Postdoctoral Science Foundation[2024M750200]
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:001479448500013
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40625
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Luo, Haiyong; Zhao, Fang
作者单位	1.Beijing Univ Posts & Telecommun, Sch Comp Sci, Natl Pilot Software Engn Sch, Beijing 100876, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Beijing Forestry Univ, Sch Artificial Intelligence, Sch Informat Sci & Technol, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Liu, Haosong,Wang, Long,Luo, Haiyong,et al. SDD-SLAM: Semantic-Driven Dynamic SLAM With Gaussian Splatting[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2025,10(6):5721-5728.
APA	Liu, Haosong.,Wang, Long.,Luo, Haiyong.,Zhao, Fang.,Chen, Runze.,...&Luo, Dan.(2025).SDD-SLAM: Semantic-Driven Dynamic SLAM With Gaussian Splatting.IEEE ROBOTICS AND AUTOMATION LETTERS,10(6),5721-5728.
MLA	Liu, Haosong,et al."SDD-SLAM: Semantic-Driven Dynamic SLAM With Gaussian Splatting".IEEE ROBOTICS AND AUTOMATION LETTERS 10.6(2025):5721-5728.