Linear embeddings in Non-Rigid structure from motion

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

Linear embeddings in Non-Rigid structure from motion. / Rabaud, Vincent; Belongie, Serge.

I: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, 2009, s. 2427-2434.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Rabaud, V & Belongie, S 2009, 'Linear embeddings in Non-Rigid structure from motion', 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, s. 2427-2434. https://doi.org/10.1109/CVPRW.2009.5206628

APA

Rabaud, V., & Belongie, S. (2009). Linear embeddings in Non-Rigid structure from motion. 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, 2427-2434. https://doi.org/10.1109/CVPRW.2009.5206628

Vancouver

Rabaud V, Belongie S. Linear embeddings in Non-Rigid structure from motion. 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009;2427-2434. https://doi.org/10.1109/CVPRW.2009.5206628

Author

Rabaud, Vincent ; Belongie, Serge. / Linear embeddings in Non-Rigid structure from motion. I: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009 ; s. 2427-2434.

Bibtex

@inproceedings{ab80cb9404f44cee9357cd1ed66ec58b,
title = "Linear embeddings in Non-Rigid structure from motion",
abstract = "This paper proposes a method to recover the embedding of the possible shapes assumed by a deforming nonrigid object by comparing triplets of frames from an orthographic video sequence. We assume that we are given features tracked with no occlusions and no outliers but possible noise, an orthographic camera and that any 3D shape of a deforming object is a linear combination of several canonical shapes. By exploiting any repetition in the object motion and defining an ordering between triplets of frames in a Generalized Non-Metric Multi-Dimensional Scaling framework, our approach recovers the shape coefficients of the linear combination, independently from other structure and motion parameters. From this point, a good estimate of the remaining unknowns is obtained for a final optimization to perform full non-rigid structure from motion. Results are presented on synthetic and real image sequences and our method is found to perform better than current state of the art.",
author = "Vincent Rabaud and Serge Belongie",
year = "2009",
doi = "10.1109/CVPRW.2009.5206628",
language = "English",
pages = "2427--2434",
journal = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009",
note = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 ; Conference date: 20-06-2009 Through 25-06-2009",

}

RIS

TY - GEN

T1 - Linear embeddings in Non-Rigid structure from motion

AU - Rabaud, Vincent

AU - Belongie, Serge

PY - 2009

Y1 - 2009

N2 - This paper proposes a method to recover the embedding of the possible shapes assumed by a deforming nonrigid object by comparing triplets of frames from an orthographic video sequence. We assume that we are given features tracked with no occlusions and no outliers but possible noise, an orthographic camera and that any 3D shape of a deforming object is a linear combination of several canonical shapes. By exploiting any repetition in the object motion and defining an ordering between triplets of frames in a Generalized Non-Metric Multi-Dimensional Scaling framework, our approach recovers the shape coefficients of the linear combination, independently from other structure and motion parameters. From this point, a good estimate of the remaining unknowns is obtained for a final optimization to perform full non-rigid structure from motion. Results are presented on synthetic and real image sequences and our method is found to perform better than current state of the art.

AB - This paper proposes a method to recover the embedding of the possible shapes assumed by a deforming nonrigid object by comparing triplets of frames from an orthographic video sequence. We assume that we are given features tracked with no occlusions and no outliers but possible noise, an orthographic camera and that any 3D shape of a deforming object is a linear combination of several canonical shapes. By exploiting any repetition in the object motion and defining an ordering between triplets of frames in a Generalized Non-Metric Multi-Dimensional Scaling framework, our approach recovers the shape coefficients of the linear combination, independently from other structure and motion parameters. From this point, a good estimate of the remaining unknowns is obtained for a final optimization to perform full non-rigid structure from motion. Results are presented on synthetic and real image sequences and our method is found to perform better than current state of the art.

UR - http://www.scopus.com/inward/record.url?scp=70450186991&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206628

DO - 10.1109/CVPRW.2009.5206628

M3 - Conference article

AN - SCOPUS:70450186991

SP - 2427

EP - 2434

JO - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

JF - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Y2 - 20 June 2009 through 25 June 2009

ER -

ID: 302050218