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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiong, Zhuang, Zhang, Chen, Xu, Qingshan, Tao, Wenbing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917250907242496
author Xiong, Zhuang
Zhang, Chen
Xu, Qingshan
Tao, Wenbing
author_facet Xiong, Zhuang
Zhang, Chen
Xu, Qingshan
Tao, Wenbing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05508
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
Xiong, Zhuang
Zhang, Chen
Xu, Qingshan
Tao, Wenbing
Computer Vision and Pattern Recognition
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.
title VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.05508