Abstract
A common approach to recover structure of 3D deformable scene and camera motion from uncalibrated 2D video sequences is to assume that shapes can be accurately represented in linear subspaces. These methods are simple and have been proven effective for reconstructions of objects with relatively small deformations, but have considerable limitations when the deformations are large or complex. This paper describes a novel approach to reconstruction of deformable objects utilising a manifold decision forest technique. The key contribution of this work is the use of random decision forests for the shape manifold learning. The learned manifold defines constraints imposed on the reconstructed shapes. Due to nonlinear structure of the learned manifold, this approach is more suitable to deal with large and complex object deformations when compared to the linear constraints.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Akhter, I., Sheikh, Y., Khan, S., Kanade, T.: Trajectory space: A dual representation for nonrigid structure from motion. IEEE PAMI 33, 1442–1456 (2011)
Arias, P., Randall, G., Sapiro, G.: Connecting the out-of sample and pre-image problems in kernel methods. In: ICPR, pp. 1–8 (2007)
Coifman, R., Lafon, S.: Diffusion maps. Appl. Comp. Harm. Anal. 21, 5–30 (2006)
Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Computer Vision 7, 81–227 (2012)
Gotardo, P., Martinez, A.M.: Computing smooth time-trajectories for camera and deformable shape in structure from motion with occlusion. IEEE PAMI 33, 2051–2065 (2011)
Gotardo, P., Martinez, A.M.: Kernel non-rigid structure from motion. In: ICCV, pp. 802–809 (2011)
Hamsici, O.C., Gotardo, P.F.U., Martinez, A.M.: Learning spatially-smooth mappings in non-rigid structure from motion. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 260–273. Springer, Heidelberg (2012)
Matuszewski, B., Quan, W., Shark, L.-K., McLoughlin, A., Lightbody, C., Emsley, H., Watkins, C.: Hi4d–adsip 3d dynamic facial articulation database. Image and Vision Computing 10, 713–727 (2012)
Paladini, M., Bue, A., Xavier, J., Stosic, M., Dodig, M., Agapito, L.: Factorization for non-rigid and articulated structure using metric projections. In: CVPR, pp. 2898–2905 (2009)
Rabaud, V., Belongie, S.: Linear embeddings in non-rigid structure from motion. In: CVPR, pp. 2427–2434 (2009)
Tao, L., Matuszewski, B.J.: Non-rigid strucutre from motion with diffusion maps prior. In: CVPR (2013)
Tao, L., Matuszewski, B.J., Mein, S.J.: Non-rigid structure from motion with incremental shape prior. In: ICIP, pp. 1753–1756 (2012)
Varol, A., Salzmann, M., Fua, P., Urtasun, R.: A constrained latent variable model. In: CVPR, pp. 2248–2255 (2012)
Yin, L., Wei, X., Sun, Y., Wang, J., Rosato, M.: A 3d face expression database for facial behavior research. In: AFGR, pp. 211–216 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tao, L., Matuszewski, B.J. (2013). Deformable Shape Reconstruction from Monocular Video with Manifold Forests. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds) Computer Analysis of Images and Patterns. CAIP 2013. Lecture Notes in Computer Science, vol 8047. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40261-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-40261-6_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40260-9
Online ISBN: 978-3-642-40261-6
eBook Packages: Computer ScienceComputer Science (R0)