Saved in:
Bibliographic Details
Main Authors: Zhu, Wenkai, Li, Xu, Xu, Qimin, Wang, Benwu, Wei, Kun, Peng, Yiming, Wang, Zihang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915579080736768
author Zhu, Wenkai
Li, Xu
Xu, Qimin
Wang, Benwu
Wei, Kun
Peng, Yiming
Wang, Zihang
author_facet Zhu, Wenkai
Li, Xu
Xu, Qimin
Wang, Benwu
Wei, Kun
Peng, Yiming
Wang, Zihang
contents 3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes and leads to cumulative pose errors and scale ambiguity. To address these challenges, we propose \textbf{LVD-GS}, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system. Motivated by the human chain-of-thought process for information seeking, we introduce a hierarchical collaborative representation module that facilitates mutual reinforcement for mapping optimization, effectively mitigating scale drift and enhancing reconstruction robustness. Furthermore, to effectively eliminate the influence of dynamic objects, we propose a joint dynamic modeling module that generates fine-grained dynamic masks by fusing open-world segmentation with implicit residual constraints, guided by uncertainty estimates from DINO-Depth features. Extensive evaluations on KITTI, nuScenes, and self-collected datasets demonstrate that our approach achieves state-of-the-art performance compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
Zhu, Wenkai
Li, Xu
Xu, Qimin
Wang, Benwu
Wei, Kun
Peng, Yiming
Wang, Zihang
Computer Vision and Pattern Recognition
Artificial Intelligence
3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes and leads to cumulative pose errors and scale ambiguity. To address these challenges, we propose \textbf{LVD-GS}, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system. Motivated by the human chain-of-thought process for information seeking, we introduce a hierarchical collaborative representation module that facilitates mutual reinforcement for mapping optimization, effectively mitigating scale drift and enhancing reconstruction robustness. Furthermore, to effectively eliminate the influence of dynamic objects, we propose a joint dynamic modeling module that generates fine-grained dynamic masks by fusing open-world segmentation with implicit residual constraints, guided by uncertainty estimates from DINO-Depth features. Extensive evaluations on KITTI, nuScenes, and self-collected datasets demonstrate that our approach achieves state-of-the-art performance compared to existing methods.
title LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.22669