The emergence of 3D Gaussian Splatting (3DGS) has recently sparked a renewed wave of dense visual SLAM research. However, current methods face challenges such as sensitivity to artifacts and noise, sub-optimal selection of training viewpoints, and a lack of light global optimization. In this paper, we propose a dense SLAM system that tightly couples 3DGS with ORB features. We design a joint optimization approach for robust tracking and effectively reducing the impact of noise and artifacts. This involves combining novel geometric observations, derived from accumulated transmittance, with ORB features extracted from pixel data. Furthermore, to improve mapping quality, we propose an adaptive Gaussian expansion and regularization method that enables Gaussian primitives to represent the scene compactly. This is coupled with a viewpoint selection strategy based on the hybrid graph to mitigate over-fitting effects and enhance convergence quality. Finally, our approach achieves compact and high-quality scene representations and accurate localization. GSORB-SLAM has been evaluated on different datasets, demonstrating outstanding performance. The code will be available.

翻译：三维高斯溅射（3DGS）的出现近期引发了密集视觉SLAM研究的新浪潮。然而，现有方法面临诸多挑战，例如对伪影与噪声的敏感性、训练视角选择的次优性，以及缺乏轻量级全局优化。本文提出一种将3DGS与ORB特征紧密耦合的密集SLAM系统。我们设计了一种联合优化方法，用于实现鲁棒跟踪并有效降低噪声与伪影的影响。该方法将源自累积透射率的新型几何观测，与从像素数据中提取的ORB特征相结合。此外，为提升建图质量，我们提出一种自适应高斯扩展与正则化方法，使高斯基元能够紧凑地表示场景。该方法与基于混合图的视角选择策略相结合，以缓解过拟合效应并提升收敛质量。最终，我们的方法实现了紧凑且高质量的场景表示与精确的定位。GSORB-SLAM已在多个数据集上进行评估，展现出卓越的性能。代码将公开提供。