Abstract
We address the problem of 3-D Mesh segmentation for categories of objects with known part structure. Part labels are derived from a semantic interpretation of non-overlapping subsurfaces. Our approach models the label distribution using a Conditional Random Field (CRF) that imposes constraints on the relative spatial arrangement of neighboring labels, thereby ensuring semantic consistency. To this end, each label variable is associated with a rich shape descriptor that is intrinsic to the surface. Randomized decision trees and cross validation are employed for learning the model, which is eventually applied using graph cuts. The method is flexible enough for segmenting even geometrically less structured regions and is robust to local and global shape variations.
Chapter PDF
Similar content being viewed by others
Keywords
- Markov Random Field
- Conditional Random Field
- Relative Spatial Arrangement
- Unary Potential
- Pairwise Potential
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.
References
Golovinskiy, A., Funkhouser, T.: Randomized cuts for 3D mesh analysis. ACM Transactions on Graphics (Proceedings SIGGRAPH Asia) 27 (2008)
Shapira, L., et al.: Consistent mesh partitioning and skeletonisation using the shape diameter function. Visual Computing 24 (2008)
Liu, R., et al.: A part-aware surface metric for shape analysis. Eurographics 28 (2009)
Slabaugh, G., et al.: 3D shape modeling for hearing aid design. IEEE Signal Processing Magazine (2008)
Zouhar, A., et al.: Freeform shape clustering for customized design automation. In: ICCV Workshop on 3-D Digital Imaging and Modeling (2009)
Agathos, A., et al.: 3D mesh segmentation methodologies for CAD applications. Computer-Aided Design and Applications 4 (2007)
Winn, J., Shotton, J.: The layout consistent random field for recognizing and segmenting partially occluded objects. In: CVPR (2006)
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. PAMI 6 (1984)
Lafferty, J., et al.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)
Boykov, Y., et al.: Efficient approximate energy minimization via graph cuts. PAMI (2001)
Surazhsky, V., et al.: Fast exact and approximate geodesics on meshes. SIGGRAPH (2005)
Shi, Y., et al.: Direct mapping of hippocampal surfaces with intrinsic shape context. Neuroimage (2007)
Kolmogorov, V., Zahib, R.: What energy functions can be minimized via graph cuts? PAMI (2002)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI (2004)
Potts, R.: Some generalized order-disorder transformation. In: Proceedings of the Cambridge Philosophical Society (1952)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zouhar, A., Baloch, S., Tsin, Y., Fang, T., Fuchs, S. (2010). Layout Consistent Segmentation of 3-D Meshes via Conditional Random Fields and Spatial Ordering Constraints. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010. MICCAI 2010. Lecture Notes in Computer Science, vol 6363. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15711-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-15711-0_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15710-3
Online ISBN: 978-3-642-15711-0
eBook Packages: Computer ScienceComputer Science (R0)