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.
@article{arxiv.2402.03246,
title = {SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM},
author = {Mingrui Li and Shuhong Liu and Heng Zhou and Guohao Zhu and Na Cheng and Tianchen Deng and Hongyu Wang},
journal= {arXiv preprint arXiv:2402.03246},
year = {2024}
}