针对动态场景中的3D高斯溅射跟踪漂移问题，提出新方法提升实时精度与重建质量。
GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM
- 在前端直接对高斯点进行动态分割，通过金字塔网络实现精准动态点识别
- 对动态高斯点施加渲染惩罚并动态更新，避免误删导致的建模错误
- 实测显示跟踪更稳定、重建画面更清晰，适合真实动态环境下的定位建图
基于3D高斯溅射（3DGS）的SLAM系统因在实时高保真渲染方面表现优异而受到广泛关注。然而，在存在动态物体的真实环境中，现有3DGS-based SLAM系统常出现地图误差和跟踪漂移问题。为此，我们提出GARAD-SLAM，一种面向动态场景的实时3DGS-based SLAM系统。在跟踪阶段，不同于传统方法，我们直接对高斯点进行动态分割，并通过高斯金字塔网络将动态标签映射回前端，实现精确动态点剔除与鲁棒跟踪。在建图阶段，对动态标记的高斯点施加渲染惩罚，通过网络动态更新，避免因简单删除造成的不可逆错误。在真实数据集上的实验结果表明，本方法在跟踪性能上优于基线方法，生成的渲染结果更少伪影，重建质量更高。
原文摘要 · Abstract (English)
The 3D Gaussian Splatting (3DGS)-based SLAM system has garnered widespread attention due to its excellent performance in real-time high-fidelity rendering. However, in real-world environments with dynamic objects, existing 3DGS-based SLAM systems often face mapping errors and tracking drift issues. To address these problems, we propose GARAD-SLAM, a real-time 3DGS-based SLAM system tailored for dynamic scenes. In terms of tracking, unlike traditional methods, we directly perform dynamic segmentation on Gaussians and map them back to the front-end to obtain dynamic point labels through a Gaussian pyramid network, achieving precise dynamic removal and robust tracking. For mapping, we impose rendering penalties on dynamically labeled Gaussians, which are updated through the network, to avoid irreversible erroneous removal caused by simple pruning. Our results on real-world datasets demonstrate that our method is competitive in tracking compared to baseline methods, generating fewer artifacts and higher-quality reconstructions in rendering.
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。