DGS-SLAM：动态环境中的高斯溅射SLAM
DGS-SLAM: Gaussian Splatting SLAM in Dynamic Environment
AI总结：
本文提出DGS-SLAM，首个基于Gaussian Splatting的动态SLAM框架，通过鲁棒过滤、掩码生成与回环感知窗口选择机制处理动态物体，在相机跟踪与新视角合成任务上达到SOTA。
摘要：
我们介绍了Dynamic Gaussian Splatting SLAM (DGS-SLAM)，这是第一个建立在Gaussian Splatting基础上的动态SLAM框架。尽管近期在稠密SLAM领域的进展已利用Gaussian Splatting来增强场景表示，但大多数方法假设环境是静态的，这使得它们容易受到由动态物体引起的光度与几何不一致性的影响。为了应对这些挑战，我们将Gaussian Splatting SLAM与一个鲁棒的过滤过程相结合，以在整个流程中处理动态物体，包括高斯插入和关键帧选择。在该框架内，为了进一步提高动态物体移除的准确性，我们引入了一种鲁棒的掩码生成方法，该方法强制跨关键帧的光度一致性，减少了由不准确的分割和阴影等伪影引起的噪声。此外，我们提出了回环感知窗口选择机制，该机制利用3D高斯的唯一关键帧ID来检测当前帧与过去帧之间的回环，从而促进当前相机位姿与高斯地图的联合优化。DGS-SLAM在各种动态SLAM基准上的相机跟踪和新视角合成方面均达到了最先进的性能，证明了其在处理真实世界动态场景方面的有效性。
英文摘要：
We introduce Dynamic Gaussian Splatting SLAM (DGS-SLAM), the first dynamic SLAM framework built on the foundation of Gaussian Splatting. While recent advancements in dense SLAM have leveraged Gaussian Splatting to enhance scene representation, most approaches assume a static environment, making them vulnerable to photometric and geometric inconsistencies caused by dynamic objects. To address these challenges, we integrate Gaussian Splatting SLAM with a robust filtering process to handle dynamic objects throughout the entire pipeline, including Gaussian insertion and keyframe selection. Within this framework, to further improve the accuracy of dynamic object removal, we introduce a robust mask generation method that enforces photometric consistency across keyframes, reducing noise from inaccurate segmentation and artifacts such as shadows. Additionally, we propose the loop-aware window selection mechanism, which utilizes unique keyframe IDs of 3D Gaussians to detect loops between the current and past frames, facilitating joint optimization of the current camera poses and the Gaussian map. DGS-SLAM achieves state-of-the-art performance in both camera tracking and novel view synthesis on various dynamic SLAM benchmarks, proving its effectiveness in handling real-world 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。
