Abstract
3D Gaussian Splatting (3DGS) has recently gained popularity in SLAM applications due to its fast rendering and high-fidelity representation. However, existing 3DGS-SLAM systems have predominantly focused on indoor environments and relied on active depth sensors, leaving a gap for large-scale outdoor applications. We present BGS-SLAM, the first binocular 3D Gaussian Splatting SLAM system designed for outdoor scenarios. Our approach uses only RGB stereo pairs without requiring LiDAR or active sensors. BGS-SLAM leverages depth estimates from pre-trained deep stereo networks to guide 3D Gaussian optimization with a multi-loss strategy enhancing both geometric consistency and visual quality. Experiments on multiple datasets demonstrate that BGS-SLAM achieves superior tracking accuracy and mapping performance compared to other 3DGS-based solutions in complex outdoor environments.
Abstract (translated)
最近，由于其快速渲染和高保真度表示能力，三维高斯点阵（3D Gaussian Splatting, 3DGS）在SLAM应用中变得越来越受欢迎。然而，现有的基于3DGS的SLAM系统主要集中在室内环境中，并且依赖于主动深度传感器，这使得它们不适用于大规模室外场景的应用。我们提出了BGS-SLAM，这是首个专为户外环境设计的双目三维高斯点阵SLAM系统。我们的方法仅使用RGB立体图像对即可运行，无需激光雷达或其他主动式传感器。 BGS-SLAM利用预训练深度网络生成的深度估计信息来引导3D高斯优化，并采用多损失策略增强几何一致性和视觉质量。在多个数据集上的实验表明，与其它基于3DGS的方法相比，BGS-SLAM在复杂户外环境中实现了更优的跟踪精度和建图性能。
URL
https://arxiv.org/abs/2507.23677
