Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble

Gilad Lerman; Yunpeng Shi

doi:10.1109/CVPR.2018.00303

Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble

Gilad Lerman, Yunpeng Shi

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

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.

Original language	English (US)
Title of host publication	Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Publisher	IEEE Computer Society
Pages	2868-2876
Number of pages	9
ISBN (Electronic)	9781538664209
DOIs	https://doi.org/10.1109/CVPR.2018.00303
State	Published - Dec 14 2018
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States Duration: Jun 18 2018 → Jun 22 2018

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Conference

Conference	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Country	United States
City	Salt Lake City
Period	6/18/18 → 6/22/18

Access

10.1109/CVPR.2018.00303

Fingerprint Dive into the research topics of 'Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble'. Together they form a unique fingerprint.

Cite this

Lerman, G., & Shi, Y. (2018). Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 2868-2876). [8578401] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00303

Estimation of Camera Locations in Highly Corrupted Scenarios : All about that Base, No Shape Trouble. / Lerman, Gilad; Shi, Yunpeng.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 2868-2876 8578401 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lerman, G & Shi, Y 2018, Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018., 8578401, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 2868-2876, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, United States, 6/18/18. https://doi.org/10.1109/CVPR.2018.00303

Lerman G, Shi Y. Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society. 2018. p. 2868-2876. 8578401. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2018.00303

@inproceedings{104624841f4a428993776a56c3130713,

title = "Estimation of Camera Locations in Highly Corrupted Scenarios: All about that Base, No Shape Trouble",

abstract = "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.",

author = "Gilad Lerman and Yunpeng Shi",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

month = dec,

day = "14",

doi = "10.1109/CVPR.2018.00303",

language = "English (US)",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "2868--2876",

booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018",

}

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

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 -