TY - GEN
T1 - Estimation of Camera Locations in Highly Corrupted Scenarios
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
AU - Lerman, Gilad
AU - Shi, Yunpeng
N1 - Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - We propose a strategy for improving camera location estimation in structure from motion. Our setting assumes highly corrupted pairwise directions (i.e., normalized relative location vectors), so there is a clear room for improving current state-of-the-art solutions for this problem. Our strategy identifies severely corrupted pairwise directions by using a geometric consistency condition. It then selects a cleaner set of pairwise directions as a preprocessing step for common solvers. We theoretically guarantee the successful performance of a basic version of our strategy under a synthetic corruption model. Numerical results on artificial and real data demonstrate the significant improvement obtained by our strategy.
AB - We propose a strategy for improving camera location estimation in structure from motion. Our setting assumes highly corrupted pairwise directions (i.e., normalized relative location vectors), so there is a clear room for improving current state-of-the-art solutions for this problem. Our strategy identifies severely corrupted pairwise directions by using a geometric consistency condition. It then selects a cleaner set of pairwise directions as a preprocessing step for common solvers. We theoretically guarantee the successful performance of a basic version of our strategy under a synthetic corruption model. Numerical results on artificial and real data demonstrate the significant improvement obtained by our strategy.
UR - http://www.scopus.com/inward/record.url?scp=85051180455&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051180455&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00303
DO - 10.1109/CVPR.2018.00303
M3 - Conference contribution
AN - SCOPUS:85051180455
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2868
EP - 2876
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
Y2 - 18 June 2018 through 22 June 2018
ER -