保持冷静：通过视觉几何基础模型实现无校准的千米级SLAM
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
AI总结：
本文提出CAL2M框架，通过引入'助手眼'消除尺度模糊，利用epipolar引导模型修正内参和姿态，结合锚点传播实现全局一致的映射，解决传统方法在千米级SLAM中的精度问题。
摘要：
视觉几何基础模型（VGFMs）在局部重建中表现出显著的零样本能力。然而，将其应用于千米级同时定位与建图（SLAM）仍具挑战性。当前方法主要依赖线性变换（如Sim3和SL4）进行子地图对齐，但单一线性变换无法建模VGFMs输出中的复杂非线性几何失真。强制刚性对齐会导致未校正残差快速累积，最终导致轨迹漂移和地图发散。为此，我们提出CAL2M（无校准助手眼基于的大规模定位与建图），一个兼容任意VGFMs的即插即用框架。与传统系统不同，CAL2M引入'助手眼'仅利用常数物理间距的先验知识，有效消除尺度模糊，无需任何时间或空间预校准。进一步，基于准确特征匹配的假设，我们提出epipolar引导的内参和姿态校正模型。通过在线内参搜索模块，可有效校正由不准确内参引起的旋转和翻译误差。最后，为确保准确映射，我们引入基于锚点传播的全局一致映射策略。通过在轨迹上构建和融合锚点，建立局部到全局的映射关系。这使非线性变换能够弹性对齐子地图，有效消除几何不对齐，确保全局一致的重建。CAL2M的源代码将在https://github.com/IRMVLab/CALM公开发布。
英文摘要：
Visual Geometry Foundation Models (VGFMs) demonstrate remarkable zero-shot capabilities in local reconstruction. However, deploying them for kilometer-level Simultaneous Localization and Mapping (SLAM) remains challenging. In such scenarios, current approaches mainly rely on linear transforms (e.g., Sim3 and SL4) for sub-map alignment, while we argue that a single linear transform is fundamentally insufficient to model the complex, non-linear geometric distortions inherent in VGFM outputs. Forcing such rigid alignment leads to the rapid accumulation of uncorrected residuals, eventually resulting in significant trajectory drift and map divergence. To address these limitations, we present CAL2M (Calibration-free Assistant-eye based Large-scale Localization and Mapping), a plug-and-play framework compatible with arbitrary VGFMs. Distinct from traditional systems, CAL2M introduces an "assistant eye" solely to leverage the prior of constant physical spacing, effectively eliminating scale ambiguity without any temporal or spatial pre-calibration. Furthermore, leveraging the assumption of accurate feature matching, we propose an epipolar-guided intrinsic and pose correction model. Supported by an online intrinsic search module, it can effectively rectify rotation and translation errors caused by inaccurate intrinsics through fundamental matrix decomposition. Finally, to ensure accurate mapping, we introduce a globally consistent mapping strategy based on anchor propagation. By constructing and fusing anchors across the trajectory, we establish a direct local-to-global mapping relationship. This enables the application of nonlinear transformations to elastically align sub-maps, effectively eliminating geometric misalignments and ensuring a globally consistent reconstruction. The source code of CAL2M will be publicly available at https://github.com/IRMVLab/CALM.
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。
