论文/arXiv 2609.15795·1 个月前

SURE-Map：自校正流式几何基础模型

SURE-Map通过跨视角几何不确定性与多时间尺度自校正，解决流式重建误差累积，并在长时程基准验证。

AI 整理

• 感知与导航
• 具身模型
• 端侧部署

原文链接：SURE-Map: Self-Correcting Streaming Geometric Foundation Models（arXiv 2609.15795 · 发布日期：2026-09-14）

SURE-Map: Self-Correcting Streaming Geometric Foundation Models

SURE-Map通过跨视角几何不确定性与多时间尺度自校正，解决流式重建误差累积，并在长时程基准验证。

核心要点

• 流式几何基础模型因上下文有限，易受动态物体和弱纹理影响，局部误差会累积为畸变与尺度漂移。
• 方法显式建模跨视角几何不确定性，衡量预测位姿和深度是否产生一致像素对应。
• 采用连续帧快速推理保持流式效率，并用稀疏关键帧窗口周期性重校近期轨迹尺度。
• 在KITTI、Oxford Spires和VBR上刷新在线前馈重建表现，闭环优化可进一步降低ATE-RMSE。

验证范围与局限：验证范围为KITTI、Oxford Spires和VBR长时程在线前馈重建基准。

英文摘要 (Abstract)

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/.

作者：Mingkai Liu, Hao Zhao, Xingxing Zuo

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.15795：SURE-Map: Self-Correcting Streaming Geometric Foundation Models访问 2026-10-21