Global Structure-from-Motion Revisited

TL;DR

This paper introduces GLOMAP, a new global Structure-from-Motion system that surpasses current methods in speed and matches or exceeds their accuracy and robustness, offering a scalable alternative to incremental approaches.

Contribution

GLOMAP is a novel global SfM system that outperforms existing methods in accuracy, robustness, and speed, providing an efficient alternative to incremental SfM.

Findings

GLOMAP achieves accuracy comparable or superior to COLMAP.

GLOMAP is significantly faster than existing global SfM methods.

The system is open-source and publicly available.

Abstract

Recovering 3D structure and camera motion from images has been a long-standing focus of computer vision research and is known as Structure-from-Motion (SfM). Solutions to this problem are categorized into incremental and global approaches. Until now, the most popular systems follow the incremental paradigm due to its superior accuracy and robustness, while global approaches are drastically more scalable and efficient. With this work, we revisit the problem of global SfM and propose GLOMAP as a new general-purpose system that outperforms the state of the art in global SfM. In terms of accuracy and robustness, we achieve results on-par or superior to COLMAP, the most widely used incremental SfM, while being orders of magnitude faster. We share our system as an open-source implementation at {https://github.com/colmap/glomap}.