WildGS-SLAM：动态环境下的单目高斯溅射SLAM系统

WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

April 4, 2025

作者: Jianhao Zheng, Zihan Zhu, Valentin Bieri, Marc Pollefeys, Songyou Peng, Iro Armeni

cs.AI

摘要

我们提出了WildGS-SLAM，一种稳健且高效的单目RGB SLAM系统，旨在通过利用不确定性感知的几何映射来处理动态环境。与假设场景静态的传统SLAM系统不同，我们的方法整合了深度和不确定性信息，以在存在移动物体的情况下增强跟踪、建图和渲染性能。我们引入了一种由浅层多层感知器和DINOv2特征预测的不确定性地图，用于在跟踪和建图过程中指导动态物体的移除。这种不确定性地图增强了密集束调整和高斯地图优化，提高了重建精度。我们的系统在多个数据集上进行了评估，并展示了无伪影的视图合成效果。结果表明，与最先进的方法相比，WildGS-SLAM在动态环境中表现出卓越的性能。

English

We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth and uncertainty information to enhance tracking, mapping, and rendering performance in the presence of moving objects. We introduce an uncertainty map, predicted by a shallow multi-layer perceptron and DINOv2 features, to guide dynamic object removal during both tracking and mapping. This uncertainty map enhances dense bundle adjustment and Gaussian map optimization, improving reconstruction accuracy. Our system is evaluated on multiple datasets and demonstrates artifact-free view synthesis. Results showcase WildGS-SLAM's superior performance in dynamic environments compared to state-of-the-art methods.