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
用场景坐标嵌入作为跨窗口的全局尺度锚点，配合几何调制注意力做历史尺度传播，可复用到任何存在尺度漂移的单目里程计/SLAM 或长序列位姿估计中。
原文依据 maintains scale consistency through scene coordinate embeddings, which are learned patch-level representations encoding 3D geometric relationships
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目视觉 SLAM 能够从互联网视频中进行三维重建，并可在资源受限平台上实现自主导航，但存在尺度漂移问题，即估计尺度在长序列上逐渐发散。现有的帧到帧方法通过局部优化实现实时性能，但由于独立窗口之间缺乏全局约束而累积尺度漂移。为解决该问题，我们提出 SCE-SLAM，一个通过场景坐标嵌入保持尺度一致性的端到端 SLAM 系统；场景坐标嵌入是学习到的块级表征，在规范尺度参考下编码三维几何关系。该框架包含两个关键模块：几何引导聚合，利用三维空间邻近性，通过几何调制注意力将尺度信息从历史观测中传播；以及场景坐标光束法平差，通过从场景坐标嵌入中解码出的显式三维坐标约束，将当前估计锚定到参考尺度。在 KITTI、Waymo 和 vKITTI 上的实验表明显著提升：与最佳先验方法相比，我们的方法在 KITTI 上将绝对轨迹误差降低 8.36 米，同时保持 36 FPS，并在大规模场景中实现尺度一致性。
英文原文摘要 1308 字符
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.