LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
By: Wenkai Zhu , Xu Li , Qimin Xu and more
Potential Business Impact:
Maps moving outdoor places accurately, even with changing objects.
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.
Similar Papers
Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction
Graphics
Makes moving things look real in 3D.
VIM-GS: Visual-Inertial Monocular Gaussian Splatting via Object-level Guidance in Large Scenes
CV and Pattern Recognition
Creates realistic 3D views from single photos.
Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
CV and Pattern Recognition
Makes 3D pictures look real in messy places.