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

TL;DR

VGGT-Motion is a novel calibration-free monocular SLAM system that uses motion-aware partitioning and anchor-driven registration to achieve accurate, efficient, and scalable long-range 3D mapping without prior calibration.

Contribution

It introduces a motion-aware submap construction and an anchor-driven direct registration strategy for robust long-range SLAM without calibration.

Findings

Significantly reduces scale drift on long sequences.

Achieves state-of-the-art accuracy in long-range calibration-free monocular SLAM.

Enables scalable, efficient global consistency with linear complexity.

Abstract

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.