Semantic understanding plays a crucial role in Dense Simultaneous Localization and Mapping (SLAM). Recent advancements that integrate Gaussian Splatting into SLAM systems have demonstrated its effectiveness in generating high-quality renderings. Building on this progress, we propose SGS-SLAM which provides precise 3D semantic segmentation alongside high-fidelity reconstructions. Specifically, we propose to employ multi-channel optimization during the mapping process, integrating appearance, geometric, and semantic constraints with key-frame optimization to enhance reconstruction quality. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, and semantic segmentation. It outperforms existing methods by a large margin meanwhile preserving real-time rendering ability.

翻译：语义理解在密集同时定位与地图构建（SLAM）中起着关键作用。近年来，将高斯泼溅（Gaussian Splatting）集成到SLAM系统中的研究已证实其在生成高质量渲染方面的有效性。基于这一进展，我们提出SGS-SLAM，该方案在实现高保真重建的同时提供精确的三维语义分割。具体而言，我们提出在建图过程中采用多通道优化策略，将外观、几何与语义约束相结合，并通过关键帧优化提升重建质量。大量实验表明，SGS-SLAM在相机位姿估计、地图重建和语义分割方面均达到最先进性能。该方法在保持实时渲染能力的同时，显著优于现有方法。