arXiv 2604.128372026-04-14cs.RO

GGD-SLAM：基于通用运动模型的单目3DGS SLAM用于动态环境

GGD-SLAM: Monocular 3DGS SLAM Powered by Generalizable Motion Model for Dynamic Environments

Shenzhen International Graduate School, Tsinghua University（深圳国际研究生院，清华大学）；Thrust of Robotics and Autonomous Systems, The Hong Kong University of Science and Technology (Guangzhou)（机器人与自主系统研究所，香港科技大学（广州））；School of Cyber Science and Technology, Sun Yat-sen University（网络安全科学与技术学院，中山大学）；Central Media Technology Institute, Huawei Incorporated Company（中央媒体技术研究院，华为有限公司）

Yi Liu, Haoxuan Xu, Hongbo Duan, Keyu Fan, Zhengyang Zhang, Peiyu Zhuang, Pengting Luo, Houde Liu

备注：: 8 pages, Accepted by ICRA 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

GGD-SLAM通过通用运动模型解决动态环境下定位和密集建图问题，无需预定义语义标注或深度输入，采用FIFO队列和动态特征增强器提升鲁棒性。

摘要：

视觉SLAM算法通过探索3DGS表示实现了显著提升，尤其在生成高保真密集地图方面表现突出。然而，它们依赖于静态环境假设，在动态环境中性能显著下降。本文提出GGD-SLAM框架，采用通用运动模型解决动态环境中的定位和密集建图挑战。具体而言，系统采用FIFO队列管理输入帧，通过顺序注意力机制实现动态语义特征提取，并整合动态特征增强器以分离静态和动态成分。此外，为减少动态干扰对静态成分的影响，设计了通过静态信息采样填充遮挡区域的方法，并设计了针对动态环境的 distractor-adaptive 结构相似性指数测度（SSIM）损失，显著提升系统鲁棒性。在真实动态数据集上的实验表明，所提系统在动态场景中的相机姿态估计和密集重建方面达到最先进的性能。

英文摘要：

Visual SLAM algorithms achieve significant improvements through the exploration of 3D Gaussian Splatting (3DGS) representations, particularly in generating high-fidelity dense maps. However, they depend on a static environment assumption and experience significant performance degradation in dynamic environments. This paper presents GGD-SLAM, a framework that employs a generalizable motion model to address the challenges of localization and dense mapping in dynamic environments - without predefined semantic annotations or depth input. Specifically, the proposed system employs a First-In-First-Out (FIFO) queue to manage incoming frames, facilitating dynamic semantic feature extraction through a sequential attention mechanism. This is integrated with a dynamic feature enhancer to separate static and dynamic components. Additionally, to minimize dynamic distractors' impact on the static components, we devise a method to fill occluded areas via static information sampling and design a distractor-adaptive Structure Similarity Index Measure (SSIM) loss tailored for dynamic environments, significantly enhancing the system's resilience. Experiments conducted on real-world dynamic datasets demonstrate that the proposed system achieves state-of-the-art performance in camera pose estimation and dense reconstruction in dynamic scenes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。