Abstract
Structure from motion (SfM) has been treated as a mature technique to carry out the task of image orientation and 3D reconstruction. However, it is an ongoing challenge to obtain correct reconstruction results from image sets consisting of problematic match pairs. This paper investigated two types of problematic match pairs, stemming from repetitive structures and very short baselines. We built a weighted view-graph based on all potential match pairs and propose a progressive SfM method (PRMP-PSfM) that iteratively prioritizes and refines its match pairs (or edges). The method has two main steps: initialization and expansion. Initialization is developed for reliable seed reconstruction. Specifically, we prioritize a subset of match pairs by the union of multiple independent minimum spanning trees and refine them by the idea of cycle consistency inference (CCI), which aims to infer incorrect edges by analyzing the geometric consistency over cycles of the view-graph. The seed reconstruction is progressively expanded by iteratively adding new minimum spanning trees and refining the corresponding match pairs, and the expansion terminates when a certain completeness of the block is achieved. Results from evaluations on several public datasets demonstrate that PRMP-PSfM can successfully accomplish the image orientation task for datasets with repetitive structures and very short baselines and can obtain better or similar accuracy of reconstruction results compared to several state-of-the-art incremental and hierarchical SfM methods.
Highlights
Structure from motion (SfM) can automatically reconstruct sparse 3D points and estimate camera poses from a set of 2D images, and has been extensively employed in photogrammetry [1,2]
We propose an SfM method to obtain correct reconstruction results for image sets with problematic match pairs stemming from repetitive structures and very short baselines
PRMP-PSfM was compared to several state-of-the-art SfM pipelines, including three incremental methods
Summary
Structure from motion (SfM) can automatically reconstruct sparse 3D points and estimate camera poses ( known as image orientation) from a set of 2D images, and has been extensively employed in photogrammetry [1,2]. Most feature-based SfM methods contain modules such as for feature extraction and matching [3], geometric verification [4,5,6], view-graph construction of match pairs [7,8,9], initial camera pose estimation [10,11,12], triangulation [13], and bundle adjustment [2,13,14]. Incremental SfM [10,12,15] typically starts with an initial reconstruction of a match pair or triplet and sequentially adds new images to the block. If a block grows in a wrong way, e.g., visually drifts of the newly oriented images arise, the whole reconstruction may be incorrectly estimated
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.