GO-SLAM：用于一致三维即时重建的全局优化
GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
AI总结：
GO-SLAM提出一种基于深度学习的密集视觉SLAM框架，通过全局优化位姿和三维重建，实现实时、鲁棒且一致的建图，并在多种数据集上超越现有方法。
摘要：
神经隐式表示最近在密集同步定位与建图（SLAM）中展现了令人瞩目的结果，但存在相机跟踪误差累积和重建失真的问题。为此，我们提出了GO-SLAM，一种基于深度学习的密集视觉SLAM框架，能够实时全局优化位姿和三维重建。鲁棒的位姿估计是其核心，由高效的闭环检测和在线全捆绑调整支持，这些机制利用输入帧完整历史的全局几何信息逐帧优化位姿。同时，我们即时更新隐式连续表面表示，以确保三维重建的全局一致性。在多种合成和真实世界数据集上的结果表明，GO-SLAM在跟踪鲁棒性和重建精度方面优于现有最先进方法。此外，GO-SLAM具有通用性，可支持单目、立体和RGB-D输入。
英文摘要：
Neural implicit representations have recently demonstrated compelling results on dense Simultaneous Localization And Mapping (SLAM) but suffer from the accumulation of errors in camera tracking and distortion in the reconstruction. Purposely, we present GO-SLAM, a deep-learning-based dense visual SLAM framework globally optimizing poses and 3D reconstruction in real-time. Robust pose estimation is at its core, supported by efficient loop closing and online full bundle adjustment, which optimize per frame by utilizing the learned global geometry of the complete history of input frames. Simultaneously, we update the implicit and continuous surface representation on-the-fly to ensure global consistency of 3D reconstruction. Results on various synthetic and real-world datasets demonstrate that GO-SLAM outperforms state-of-the-art approaches at tracking robustness and reconstruction accuracy. Furthermore, GO-SLAM is versatile and can run with monocular, stereo, and RGB-D input.
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。
