发表机构
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI); Peking University; Tsinghua University（穆罕默德·本·扎耶德人工智能大学; 北京大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SURE-Map提出自校正流式几何基础模型，通过显式跨视图不确定性建模和多时间尺度自校正，在长时程基准上显著降低轨迹误差，实现最先进的在线重建性能。
AI 中文摘要
流式几何基础模型正成为SLAM系统的一种有吸引力的替代方案。然而，这种流式特性引入了一个根本性问题：每次预测都基于有限的上下文进行，容易受到动态物体和弱纹理的影响。小的局部误差会累积成严重的几何畸变和长时程尺度漂移。我们认为，可靠的流式重建要求几何基础模型不仅要具有预测能力，还要具备自校正能力。我们提出了SURE-Map，一个基于两个互补原则构建的自校正框架。首先，我们显式地建模跨视图几何不确定性。与主要反映单视图预测可靠性的传统深度或点置信度不同，我们的不确定性直接度量联合预测的位姿和深度是否产生几何一致的跨视图像素对应关系。其次，由于仅靠局部校正无法消除缓慢累积的尺度误差，我们引入了多时间尺度自校正：快速的连续帧推理保持流式效率，而稀疏的关键帧窗口推理提供更长范围的几何证据，以周期性重新校准近期轨迹的尺度。SURE-Map在长时程基准的在线前馈重建中确立了新的最先进性能，将KITTI上的ATE-RMSE从24.00米降至17.24米，Oxford Spires上从5.11米降至4.74米，VBR上从31.37米降至28.58米，在结合回环闭合细化后进一步改进至15.17米、4.63米和22.12米。项目页面：此https URL。
英文摘要
Streaming geometric foundation models are emerging as a compelling alternative to SLAM systems. Yet this streaming nature introduces a fundamental issue: each prediction is made from limited context, which is vulnerable to dynamic objects and weak textures. Small local errors accumulate into severe geometric distortion and long-horizon scale drift. We argue that reliable streaming reconstruction requires geometric foundation models to be not only predictive, but also self-correcting. We introduce SURE-Map, a self-correcting framework built upon two complementary principles. First, we explicitly model cross-view geometric uncertainty. Unlike conventional depth or point confidence, which primarily reflects the reliability of individual-view prediction, our uncertainty directly measures whether the jointly predicted pose and depth induce geometrically consistent cross-view pixel correspondences. Second, because local correction alone cannot eliminate slowly accumulating scale errors, we introduce multi-timescale self-correction: fast consecutive-frame inference preserves streaming efficiency, while sparse keyframe-window inference provides longer-range geometric evidence to periodically recalibrate the scale of recent trajectories. SURE-Map establishes new state-of-the-art performance for online feed-forward reconstruction across long-horizon benchmarks, reducing ATE-RMSE from 24.00 to 17.24 m on KITTI, 5.11 to 4.74 m on Oxford Spires, and 31.37 to 28.58 m on VBR, with further improvements to 15.17, 4.63, and 22.12 m when incorporating loop-closure refinement. Project page: https://mingkai-liu.github.io/projects/sure-map/.
CommentsCorrected a typo in the title; manuscript content unchanged
