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

2026-02-05

AI Summary

This work addresses the scale drift and zero-motion drift issues prevalent in uncalibrated monocular SLAM over long sequences, which stem from motion-agnostic segmentation. To mitigate these challenges, the authors propose a motion-aware submap construction mechanism that integrates optical flow–guided adaptive segmentation with a turn-encapsulation strategy. They innovatively design a feature-matching-free, anchor-driven direct Sim(3) dense registration method and incorporate a lightweight submap pose-graph optimization to achieve globally consistent trajectory estimation with linear computational complexity. The proposed approach significantly improves trajectory accuracy and computational efficiency in long-range, zero-shot scenarios, establishing state-of-the-art performance in uncalibrated monocular SLAM.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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.

Problem

• scale drift
• calibration-free monocular SLAM
• long-range consistency
• zero-motion drift
• computational efficiency

Innovation

• motion-aware submap
• calibration-free monocular SLAM
• direct Sim(3) registration
• anchor-driven alignment
• long-range consistency