We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, and object-level geometry. We introduce a unique semantic feature loss that effectively compensates for the shortcomings of traditional depth and color losses in object optimization. Through a semantic-guided keyframe selection strategy, we prevent erroneous reconstructions caused by cumulative errors. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, precise semantic segmentation, and object-level geometric accuracy, while ensuring real-time rendering capabilities.

翻译：我们提出了SGS-SLAM，首个基于高斯泼溅的语义视觉SLAM系统。它通过多通道优化融合了外观、几何与语义特征，解决了神经隐式SLAM系统在高保真渲染、场景理解与物体级几何重建中存在的过度平滑问题。我们引入了一种独特的语义特征损失函数，有效弥补了传统深度与颜色损失在物体优化中的不足。通过语义引导的关键帧选择策略，我们避免了累积误差导致的错误重建。大量实验表明，SGS-SLAM在相机位姿估计、地图重建、精确语义分割及物体级几何精度方面均达到最先进性能，同时保证了实时渲染能力。