首个基于3D高斯的动态环境实时定位系统，精度显著提升。
DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
- 通过运动掩码与自适应点管理，分离动态物体干扰
- 在动态场景中实现媲美静态场景的位姿估计精度
- 适合需要高保真重建的自动驾驶、机器人导航
在动态场景中实现鲁棒且精确的位姿估计是视觉同步定位与地图构建（SLAM）的重要挑战。近期将高斯泼溅融入SLAM系统的方法利用显式3D高斯模型生成高质量渲染结果，显著提升了环境重建保真度。然而，这些方法依赖静态环境假设，在动态环境中因几何与光照观测不一致而表现受限。为此，本文提出DG-SLAM，首个基于3D高斯的鲁棒动态视觉SLAM系统，可在实现高保真重建的同时提供精确的相机位姿估计。具体包括：运动掩码生成、自适应高斯点管理及混合位姿跟踪算法，有效提升位姿估计的准确性和鲁棒性。大量实验表明，DG-SLAM在动态场景中的位姿估计、地图重建与新视角合成方面均达到领先水平，同时保持实时渲染能力。
原文摘要 · Abstract (English)
Achieving robust and precise pose estimation in dynamic scenes is a significant research challenge in Visual Simultaneous Localization and Mapping (SLAM). Recent advancements integrating Gaussian Splatting into SLAM systems have proven effective in creating high-quality renderings using explicit 3D Gaussian models, significantly improving environmental reconstruction fidelity. However, these approaches depend on a static environment assumption and face challenges in dynamic environments due to inconsistent observations of geometry and photometry. To address this problem, we propose DG-SLAM, the first robust dynamic visual SLAM system grounded in 3D Gaussians, which provides precise camera pose estimation alongside high-fidelity reconstructions. Specifically, we propose effective strategies, including motion mask generation, adaptive Gaussian point management, and a hybrid camera tracking algorithm to improve the accuracy and robustness of pose estimation. Extensive experiments demonstrate that DG-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, and novel-view synthesis in dynamic scenes, outperforming existing methods meanwhile preserving real-time rendering ability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。