代码链接:https://github.com/NKU-MobFly-Robotics/DOGL-SLAM

论文链接:https://ieeexplore.ieee.org/document/11278733

    近期，3D高斯泼溅（3DGS）在视觉同步定位与建图（SLAM）中的建图质量与计算效率均取得显著突破。我们提出 DOGL-SLAM，一种将 3DGS 嵌入核心流程的全新框架，可在动态环境中实现精准的相机位姿跟踪、物体级交互与高保真场景重建。首先，联合图优化模块同时融合稠密高斯与稀疏地标约束，使相机跟踪与建图精确对齐。其次，一致性物体级语义融合模块将类别标签嵌入 3D 高斯，通过语义一致性进行分组，并利用跨视角损失优化分布，以支持场景操控。最后，我们引入分层动态滤除管道，在三条并行线程中完成分割、动态特征剔除、梯度掩膜与可见性感知的高斯剪枝。系统在多个数据集上评估，在动态场景的高质量视角合成方面表现提升。此外，生成的物体级语义地图可赋能高级下游任务，彰显稳健 SLAM 框架的巨大潜力。

    S. Wu, X. Zhang*, S. Zhang, R. Yao, Z. Song, Y. Tong, J. Yuan. Dynamic Object-Level SLAM via Joint Gaussian-Landmark Tracking. IEEE Robotics and Automation Letters (accepted).

Abstract

    Recent advancements in 3D Gaussian Splatting (3DGS) have significantly improved the mapping quality and computational efficiency of visual Simultaneous Localization and Mapping (SLAM). We propose DOGL-SLAM, a novel framework that integrates 3DGS into its core pipeline, enabling accurate camera pose tracking, object-level interaction, and high-fidelity scene reconstruction in dynamic environments. Firstly, a joint graph optimization module incorporates both dense Gaussian and sparse landmark constraints, enabling precise alignment between camera tracking and mapping. Secondly, a consistent object-level semantic fusion module embeds category labels into 3D Gaussians, grouping them via semantic consistency and optimizing distributions through cross-view losses to support scene manipulation. Finally, a hierarchical dynamic filtering pipeline is introduced, consisting of segmentation, dynamic feature exclusion, gradient masking, and visibility-aware Gaussian pruning across three parallel threads. Our system is evaluated across multiple datasets, showing a significant improvement in high-quality view synthesis for dynamic scenes. Additionally, the generated object-level semantic maps facilitate advanced downstream tasks, highlighting the potential of a robust SLAM framework.