Linear embeddings in Non-Rigid structure from motion
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Linear embeddings in Non-Rigid structure from motion. / Rabaud, Vincent; Belongie, Serge.
In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, 2009, p. 2427-2434.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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