TY - JOUR

T1 - Sequential Cycle Consistency Inference for Eliminating Incorrect Relative Orientations in Structure from Motion

AU - Xiao, Teng

AU - Wang, Xin

AU - Deng, Fei

AU - Heipke, Christian

N1 - Funding Information: We would like to thank Mario Michelini and Helmut Mayer, Universität der Bundeswehr München, for making the church data set available to us. The author Xin Wang would like to thank the China Scholarship Council (No. 201606270207) for financially supporting his Ph.D. study at Leibniz Universität Hannover, Germany. Funding Information: This work was supported in part by the Open Fund of the Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Land and Resources, China, KF-2018–03-025.

PY - 2021/6

Y1 - 2021/6

N2 - The quality of the parameters of relative orientation (ROs) of a stereoscopic pair of images is crucial for the quality of results in structure from motion (SfM). In this paper we focus on improving the robustness and accuracy of SfM by detecting and eliminating incorrect ROs, especially due to repetitive structure, that typically result in incorrectly estimated RO results and thus degrade 3D reconstruction. ROs are represented by a view graph. We develop a novel variant of cycle consistency inference, called sequential cycle consistency inference or SCCI, to infer wrong edges by analyzing the geometric consistency of cycles in the view graph. Our method consists essentially of a two-stage process, an initialization step based on the union of various orthogonal minimum spanning trees (MST) of the graph, followed by an expansion step which incrementally adds edges to this graph. We show by means of experimental studies that our method reaches better robustness and accuracy for data sets containing repetitive structure, compared to state-of-the-art algorithms of RO outlier detection.

AB - The quality of the parameters of relative orientation (ROs) of a stereoscopic pair of images is crucial for the quality of results in structure from motion (SfM). In this paper we focus on improving the robustness and accuracy of SfM by detecting and eliminating incorrect ROs, especially due to repetitive structure, that typically result in incorrectly estimated RO results and thus degrade 3D reconstruction. ROs are represented by a view graph. We develop a novel variant of cycle consistency inference, called sequential cycle consistency inference or SCCI, to infer wrong edges by analyzing the geometric consistency of cycles in the view graph. Our method consists essentially of a two-stage process, an initialization step based on the union of various orthogonal minimum spanning trees (MST) of the graph, followed by an expansion step which incrementally adds edges to this graph. We show by means of experimental studies that our method reaches better robustness and accuracy for data sets containing repetitive structure, compared to state-of-the-art algorithms of RO outlier detection.

KW - Outlier detection

KW - Relative orientations (ROs)

KW - Repetitive structure

KW - Sequential cycle consistency inference

KW - Structure from motion (SfM)

UR - http://www.scopus.com/inward/record.url?scp=85108634219&partnerID=8YFLogxK

U2 - 10.1007/s41064-021-00152-1

DO - 10.1007/s41064-021-00152-1

M3 - Article

AN - SCOPUS:85108634219

VL - 89

SP - 233

EP - 249

JO - PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation Science

JF - PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation Science

SN - 2512-2789

IS - 3

ER -