Abstract: In this paper, we present a robust and efficient Structure from Motion
pipeline for accurate 3D reconstruction under challenging environments by
leveraging the camera pose information from a visual-inertial odometry.
Specifically, we propose a geometric verification method to filter out
mismatches by considering the prior geometric configuration of candidate image
pairs. Furthermore, we introduce an efficient and scalable reconstruction
approach that relies on batched image registration and robust bundle
adjustment, both leveraging the reliable local odometry estimation. Extensive
experimental results show that our pipeline performs better than the
state-of-the-art SfM approaches in terms of reconstruction accuracy and
robustness for challenging sequential image collections.