Search papers, labs, and topics across Lattice.
This paper introduces CAL2M, a novel SLAM framework designed to address geometric distortions in Visual Geometry Foundation Model (VGFM) outputs for kilometer-level mapping. CAL2M uses an "assistant eye" to resolve scale ambiguity without calibration and employs an epipolar-guided correction model to refine intrinsics and poses. By propagating anchors and applying nonlinear transformations for sub-map alignment, CAL2M achieves globally consistent mapping, mitigating trajectory drift and map divergence common in large-scale VGFM-based SLAM.
Forget rigid transforms: CAL2M's elastic sub-map alignment unlocks globally consistent kilometer-scale SLAM with Visual Geometry Foundation Models.
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.
