VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency

Despite recent progress in calibration-free monocular SLAM via 3D vision foundation models, scale drift remains severe on long sequences. Motion-agnostic partitioning breaks contextual coherence and causes zero-motion drift, while conventional geometric alignment is computationally expensive. To address these issues, we propose VGGT-Motion, a calibration-free SLAM system for efficient and robust global consistency over kilometer-scale trajectories. Specifically, we first propose a motion-aware submap construction mechanism that uses optical flow to guide adaptive partitioning, prune static redundancy, and encapsulate turns for stable local geometry. We then design an anchor-driven direct Sim(3) registration strategy. By exploiting context-balanced anchors, it achieves search-free, pixel-wise dense alignment and efficient loop closure without costly feature matching. Finally, a lightweight submap-level pose graph optimization enforces global consistency with linear complexity, enabling scalable long-range operation. Experiments show that VGGT-Motion markedly improves trajectory accuracy and efficiency, achieving state-of-the-art performance in zero-shot, long-range calibration-free monocular SLAM.

Monocular SLAM allows a computer to estimate a camera's motion and build a map of the surrounding scene using only a single camera. This is useful for robots, autonomous vehicles, and augmented reality systems, but it becomes difficult over long distances because small errors can accumulate and cause the estimated trajectory to drift. Our work introduces VGGT-Motion, a system that uses motion information to divide long videos into better local segments and then aligns them efficiently. By reducing unnecessary frames, preserving important turning motions, and improving the alignment between segments, VGGT-Motion produces more consistent trajectories over long sequences without requiring camera calibration. Experiments on multiple driving datasets show that our method is more accurate and scalable than previous foundation-model-based monocular SLAM systems.