SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
This addresses the need for high-quality scene understanding and object-level geometry in visual SLAM systems, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of oversmoothing in neural implicit SLAM systems by developing SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting, which achieves state-of-the-art performance in camera pose estimation, map reconstruction, semantic segmentation, and object-level geometric accuracy while maintaining real-time rendering.
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.