'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views

Pan Ji; Hongdong Li; Yuchao Dai; Ian Reid

doi:10.1109/ICCV.2017.106

'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views

Pan Ji, Hongdong Li, Yuchao Dai, Ian Reid

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

15 Citations (Scopus)

Abstract

Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of 'maximizing rigidity' in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with stateof- the-art accuracy on various 3D reconstruction problems.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	929-937
Number of pages	9
ISBN (Electronic)	9781538610329
DOIs	https://doi.org/10.1109/ICCV.2017.106
Publication status	Published - 22 Dec 2017
Externally published	Yes
Event	16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy Duration: 22 Oct 2017 → 29 Oct 2017

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2017-October
ISSN (Print)	1550-5499

Conference

Conference	16th IEEE International Conference on Computer Vision, ICCV 2017
Country/Territory	Italy
City	Venice
Period	22/10/17 → 29/10/17

Access to Document

10.1109/ICCV.2017.106

Cite this

Ji, P., Li, H., Dai, Y., & Reid, I. (2017). 'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 (pp. 929-937). Article 8237368 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2017.106

Ji, Pan ; Li, Hongdong ; Dai, Yuchao et al. / 'Maximizing Rigidity' Revisited : A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views. Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 929-937 (Proceedings of the IEEE International Conference on Computer Vision).

@inproceedings{7837a554abeb4d00a61df098b152d591,

title = "'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views",

abstract = "Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of 'maximizing rigidity' in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with stateof- the-art accuracy on various 3D reconstruction problems.",

author = "Pan Ji and Hongdong Li and Yuchao Dai and Ian Reid",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 16th IEEE International Conference on Computer Vision, ICCV 2017 ; Conference date: 22-10-2017 Through 29-10-2017",

year = "2017",

month = dec,

day = "22",

doi = "10.1109/ICCV.2017.106",

language = "English",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "929--937",

booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017",

address = "United States",

}

Ji, P, Li, H, Dai, Y & Reid, I 2017, 'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views. in Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017., 8237368, Proceedings of the IEEE International Conference on Computer Vision, vol. 2017-October, Institute of Electrical and Electronics Engineers Inc., pp. 929-937, 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCV.2017.106

'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views. / Ji, Pan; Li, Hongdong; Dai, Yuchao et al.
Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 929-937 8237368 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October).

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

TY - GEN

T1 - 'Maximizing Rigidity' Revisited

T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017

AU - Ji, Pan

AU - Li, Hongdong

AU - Dai, Yuchao

AU - Reid, Ian

PY - 2017/12/22

Y1 - 2017/12/22

N2 - Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of 'maximizing rigidity' in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with stateof- the-art accuracy on various 3D reconstruction problems.

AB - Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of 'maximizing rigidity' in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with stateof- the-art accuracy on various 3D reconstruction problems.

UR - http://www.scopus.com/inward/record.url?scp=85041931199&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2017.106

DO - 10.1109/ICCV.2017.106

M3 - Conference contribution

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 929

EP - 937

BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 22 October 2017 through 29 October 2017

ER -

Ji P, Li H, Dai Y, Reid I. 'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 929-937. 8237368. (Proceedings of the IEEE International Conference on Computer Vision). doi: 10.1109/ICCV.2017.106

'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this