arXiv 2601.096652026-01-14cs.CV

SCE-SLAM：通过场景坐标嵌入实现尺度一致的单目SLAM

SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings

School of Computer Science and Engineering, State Key Laboratory of Complex & Critical Software Environment, Jiangxi Research Institute, Beihang University（计算机科学与工程学院、复杂与关键软件环境国家重点实验室、江西研究院、北航）；Macquarie University（麦考瑞大学）；Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology（北京半导体神经网络智能感知与计算技术重点实验室）

Yuchen Wu, Jiahe Li, Xiaohan Yu, Lina Yu, Jin Zheng, Xiao Bai

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

SCE-SLAM通过场景坐标嵌入实现单目SLAM的尺度一致性，实验显示在KITTI上轨迹误差减少8.36米，同时保持36 FPS。

摘要：

单目视觉SLAM能够从互联网视频中实现三维重建，并在资源受限平台上实现自主导航，但存在尺度漂移的问题，即在长时间序列中估计的尺度逐渐偏离。现有的帧间方法通过局部优化实现实时性能，但由于缺乏独立窗口之间的全局约束，导致累积尺度漂移。为了解决这一问题，我们提出了SCE-SLAM，一种端到端的SLAM系统，通过场景坐标嵌入保持尺度一致性，这些嵌入是学习到的片段级表示，编码了在标准尺度参考下的3D几何关系。该框架由两个关键模块组成：几何引导的聚合，利用3D空间接近性通过几何调制注意力传播尺度信息，以及场景坐标束调整，通过从场景坐标嵌入中解码的显式3D坐标约束将当前估计锚定到参考尺度。在KITTI、Waymo和vKITTI上的实验显示了显著改进：与最佳先前方法相比，我们的方法在KITTI上将绝对轨迹误差减少了8.36米，同时保持36 FPS并在大规模场景中实现尺度一致性。

英文摘要：

Monocular visual SLAM enables 3D reconstruction from internet video and autonomous navigation on resource-constrained platforms, yet suffers from scale drift, i.e., the gradual divergence of estimated scale over long sequences. Existing frame-to-frame methods achieve real-time performance through local optimization but accumulate scale drift due to the lack of global constraints among independent windows. To address this, we propose SCE-SLAM, an end-to-end SLAM system that maintains scale consistency through scene coordinate embeddings, which are learned patch-level representations encoding 3D geometric relationships under a canonical scale reference. The framework consists of two key modules: geometry-guided aggregation that leverages 3D spatial proximity to propagate scale information from historical observations through geometry-modulated attention, and scene coordinate bundle adjustment that anchors current estimates to the reference scale through explicit 3D coordinate constraints decoded from the scene coordinate embeddings. Experiments on KITTI, Waymo, and vKITTI demonstrate substantial improvements: our method reduces absolute trajectory error by 8.36m on KITTI compared to the best prior approach, while maintaining 36 FPS and achieving scale consistency across large-scale scenes.

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。