面向城市场景的双目立体3D高斯溅射SLAM
Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes
AI总结：
针对现有3DGS-SLAM多依赖主动深度传感器、难适配大规模户外场景的问题，提出仅用RGB双目对的BGS-SLAM，借助预训练立体深度网络与多损失策略优化3D高斯，在复杂户外场景下跟踪与建图性能优于同类方案。
摘要：
3D高斯溅射（3D Gaussian Splatting, 3DGS）凭借快速渲染与高保真表示能力，近期在SLAM应用中备受青睐。但现有3DGS-SLAM系统多聚焦室内环境，且依赖主动深度传感器，在大规模户外应用领域存在空白。我们提出BGS-SLAM，这是首个面向户外场景的双目3D高斯溅射SLAM系统。该方法仅使用RGB立体图像对，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输出的深度估计结果指导3D高斯优化，并采用多损失策略同时增强几何一致性与视觉质量。在多个数据集上的实验表明，在复杂户外环境中，BGS-SLAM的跟踪精度与建图性能均优于其他基于3DGS的方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
