Abstract
This paper describes an approach to implicit Non-Rigid Structure-from-Motion based on the low-rank shape model. The main contributions are the use of an implicit model, of matching tensors, a rank estimation procedure, and the theory and implementation of two smoothness priors. Contrarily to most previous methods, the proposed method is fully automatic: it handles a substantial amount of missing data as well as outlier contaminated data, and it automatically estimates the degree of deformation. A major problem in many previous methods is that they generalize badly. Although the estimated model fits the visible training data well, it often predicts the missing data badly. To improve generalization a temporal smoothness prior and a surface shape prior are developed. The temporal smoothness prior constrains the camera trajectory and the configuration weights to behave smoothly. The surface shape prior constrains consistently close image point tracks to have similar implicit structure. We propose an algorithm for achieving a Maximum A Posteriori (map) solution and show experimentally that the map-solution generalizes far better than the prior-free Maximum Likelihood (ml) solution.
Similar content being viewed by others
References
Aanæs, H., Kahl, F.: Estimation of deformable structure and motion. In: The Vision and Modeling of Dynamic Scenes Workshop (2002)
Bartoli, A., Olsen, S.: A batch algorithm for implicit non-rigid shape and motion recovery. In: Workshop on Dynamical Vision at ICCV’05 (2005)
Brand, M.: Morphable 3D models from video. In: Conf. on Computer Vision and Pattern Recognition, pp. 456–463 (2001)
Brand, M.: A direct method for 3D factorization of nonrigid motion observed in 2D. In: Conf. on Computer Vision and Pattern Recognition, pp. 122–128 (2005)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: Conf. on Computer Vision and Pattern Recognition, pp. 690–696 (2000)
Buchanan, A.M., Fitzgibbon, A.W.: Damped Newton algorithms for matrix factorization with missing data. In: Conf. on Computer Vision and Pattern Recognition, pp. 316–322 (2005)
Del Bue, A., Lladó, X., de Agapito, L.: Non-rigid metric shape and motion recovery from uncalibrated images using priors. In: Conf. on Computer Vision and Pattern Recognition, pp. 1191–1198 (2006)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2003)
Jacobs, D.W.: Linear fitting with missing data for structure-from-motion. Comput. Vis. Image Underst. 82(1), 57–81 (2001)
Martinec, D., Pajdla, T.: 3D reconstruction by fitting low-rank matrices with missing data. In: Conf. on Computer Vision and Pattern Recognition, pp. 198–205 (2005)
Olsen, S., Bartoli, A.: Using priors for improving generalization in non-rigid structure-from-motion. In: Proceedings of the British Machine Vision Conference, pp. 1050–1059 (2007)
Roy-Chowdhury, A.K.: A measure of deformability of shapes, with application to human motion analysis. In: Conf. on Computer Vision and Pattern Recognition, pp. 398–404 (2005)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. Int. J. Comput. Vis. 9(2), 137–154 (1992)
Torr, P.H.S.: Bayesian model estimation and selection for epipolar geometry and generic manifold fitting. Int. J. Comput. Vis. 50(1), 27–45 (2002)
Torr, P.H.S., Zisserman, A.: MLESAC: A new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. 78, 138–156 (2000)
Torresani, L., Bregler, C.: Space-time tracking. In: European Conference on Computer Vision, pp. 801–812 (2002)
Torresani, L., Hertzmann, A.: Automatic non-rigid 3D modeling from video. In: European Conference on Computer Vision, pp. 299–312 (2004)
Torresani, L., Hertzmann, A., Bregler, C.: Non-rigid structure-from-motion: Estimating shape and motion with hierarchical priors. In: IEEE PAMI (2007)
Torresani, L., Yang, D.B., Alexander, E.J., Bregler, C.: Tracking and modeling non-rigid objects with rank constraints. In: Conf. on Computer Vision and Pattern Recognition, pp. 493–500 (2001)
Triggs, B.: Linear projective reconstruction from matching tensors. Image Vis. Comput. 15(8), 617–625 (1997)
Vidal, R., Abretske, D.: Nonrigid shape and motion from multiple perspective views. In: European Conference on Computer Vision, pp. 205–218 (2006)
Xiao, J., Chai, J.-X., Kanade, T.: A closed-form solution to non-rigid shape and motion recovery. In: European Conference on Computer Vision, pp. 573–587 (2004)
Xiao, J., Kanade, T.: Non-rigid shape and motion recovery: Degenerate deformations. In: International Conference on Computer Vision and Pattern Recognition, pp. 668–675 (2004)
Yan, J., Pollefeys, M.: Articulated motion segmentation using RANSAC with priors. In: Workshop on Dynamical Vision (2005)
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper combines and extends two conference papers; the first one appeared in the Workshop on Dynamical Vision held at ICCV’05 [2], and the second one appeared at the 2007 British Machine Vision Conference [11]. This paper integrates the two publications into a comprehensive presentation of our approach to Non-Rigid Structure-from-Motion.
Rights and permissions
About this article
Cite this article
Olsen, S.I., Bartoli, A. Implicit Non-Rigid Structure-from-Motion with Priors. J Math Imaging Vis 31, 233–244 (2008). https://doi.org/10.1007/s10851-007-0060-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-007-0060-3