Very Large-Scale Global SfM by Distributed Motion Averaging

Siyu Zhu, Runze Zhang, Lei Zhou, Tianwei Shen, Tian Fang, Ping Tan, Long Quan; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4568-4577

Abstract


Global Structure-from-Motion (SfM) techniques have demonstrated superior efficiency and accuracy than the conventional incremental approach in many recent studies. This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images. Specifically, we first divide all images into multiple partitions that preserve strong data association for well posed and parallel local motion averaging. Then, we solve a global motion averaging that determines cameras at partition boundaries and a similarity transformation per partition to register all cameras in a single coordinate frame. Finally, local and global motion averaging are iterated until convergence. Since local camera poses are fixed during the global motion average, we can avoid caching the whole reconstruction in memory at once. This distributed framework significantly enhances the efficiency and robustness of large-scale motion averaging.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhu_2018_CVPR,
author = {Zhu, Siyu and Zhang, Runze and Zhou, Lei and Shen, Tianwei and Fang, Tian and Tan, Ping and Quan, Long},
title = {Very Large-Scale Global SfM by Distributed Motion Averaging},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}