首个多目视觉3D高斯溅射系统，无需激光雷达即可在户外精准建图。
Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes
- 用双目图像和预训练立体网络估算深度，指导高斯点优化。
- 在多个户外数据集上，定位精度和建图质量优于现有3DGS方法。
- 适合无人车、机器人等无激光雷达的室外场景应用。
3D高斯溅射（3DGS）因其快速渲染和高保真表示，近年来在SLAM中广受关注。然而，现有3DGS-SLAM系统主要聚焦于室内环境，并依赖主动深度传感器，缺乏对大规模户外场景的支持。本文提出BGS-SLAM，首个专为户外城市场景设计的双目3D高斯溅射SLAM系统。该方法仅使用RGB双目图像，无需激光雷达或主动传感器。BGS-SLAM利用预训练深度立体网络生成的深度估计，通过多损失策略引导3D高斯优化，同时提升几何一致性与视觉质量。在多个数据集上的实验表明，BGS-SLAM在复杂户外环境中相比其他3DGS基方法实现了更优的跟踪精度与建图性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。