Bernhard Schölkopf
ABSTRACT
We propose machine learning methods for the estimation of deformation fields that transform two given objects into each other, thereby establishing a dense point to point correspondence. The fields are computed using a modified support vector machine containing a penalty enforcing that points of one object will be mapped to "similar" points on the other one. Our system, which contains little engineering or domain knowledge, delivers state of the art performance. We present application results including close to photorealistic morphs of 3D head models.
- Allen, B., Curless, B., & Popovic, Z. (2003). The space of human body shapes: reconstruction and parameterization from range scans. SIGGRAPH'03. Google Scholar
Digital Library
- Audette, M. A., Ferrie, F. P., & Peters, T. M. (2000). An algorithmic overview of surface registration techniques for medical imaging. Medical Image Analysis, 4, 201--217.Google ScholarCross Ref
- Bakir, G. H., Gretton, A., Franz, M., & Schöölkopf, B. (2004). Sequential multivariate regression via stiefel manifold constraints. Proc. DAGM.Google Scholar
- Bartlett, P., & Schöölkopf, B. (2001). Some kernels for structured data (Technical Report). Biowulf Technologies.Google Scholar
- Besl, P. J., & McKay, N. D. (1992). A method for registration of 3-D shapes. IEEE Trans. PAMI, 14, 239--256. Google ScholarDigital Library
- Beymer, D., & Poggio, T. (1994). Learning and networks: Applications to graphics and very-low bandwidth video-conferencing. GOMAC. California.Google Scholar
- Blanz, V., & Vetter, T. (1999). A morphable model for the synthesis of 3D faces. SIGGRAPH'99. Google ScholarDigital Library
- Bregler, C., & Omohundro, S. M. (1995). Nonlinear image interpolation using manifold learning. Advances in Neural Information Processing Systems 7.Google Scholar
- Carr, J., Beatson, R., Cherrie, J., Mitchell, T., Fright, W., McCallum, B., & Evans, T. (2001). Reconstruction and representation of 3D objects with radial basis functions. SIGGRAPH'01 (pp. 67--76). Google ScholarDigital Library
- Cohen-Or, D., Solomovic, A., & Levin, D. (1998). Three-dimensional distance field metamorphosis. ACM Trans. Graph., 17, 116--141. Google ScholarDigital Library
- Cootes, T. F., Edwards, G. J., & Taylor, C. J. (1998). Active appearance models. ECCV '98: Proceedings of the 5th European Conference on Computer Vision-Volume II (pp. 484--498). Springer-Verlag. Google ScholarDigital Library
- Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines. Cambridge, UK: Cambridge University Press. Google ScholarDigital Library
- Freeman, W. T., Jones, T. R., & Pasztor, E. C. (2002). Example-based super-resolution. IEEE Computer Graphics and Applications. Google ScholarDigital Library
- Grochow, K., Martin, S. L., Hertzmann, A., & Popovic, Z. (2004). Style-based inverse kinematics. SIGGRAPH'04. ACM Press. Google ScholarDigital Library
- Haralick, R., & Shapiro, L. (1992). Computer and robot vision, vol. 2. Reading, MA: Addison-Wesley. Google ScholarDigital Library
- Micchelli, C., & Pontil, M. (2005). On learning vector-valued functions. Neural Computation, 17, 177--204. Google ScholarDigital Library
- Müller, M., Keiser, R., Nealen, A., Pauly, M., Gross, M., & Alexa, M. (2004). Point based animation of elastic, plastic and melting objects. SIGGRAPH/EUROGRAPHICS Symposium on Computer Animation. Google ScholarDigital Library
- Rueckert, D., & Frangi, A. F. (2003). Automatic construction of 3-d statistical deformation models of the brain using nonrigid registration. IEEE Trans. on Medical Imaging, 22, 1014--1025.Google ScholarCross Ref
- Rusinkiewicz, S., & Levoy, M. (2001). Efficient variants of the ICP algorithm. Proc. Conf. on 3D Digital Imaging and Modeling (pp. 145--152).Google ScholarCross Ref
- Saul, L., & Jordan, M. (1997). A variational principle for model-based morphing. Advances in Neural Information Processing Systems 9.Google Scholar
- Schaback, R. (1995). Creating surfaces from scattered data using radial basis functions. In at M. D. al. (Ed.), Mathematical methods for curves and surfaces. Nashville: Vanderbilt University Press.Google Scholar
- Schölkopf, B., Giesen, J., & Spalinger, S. (2005). Kernel methods for implicit surface modeling. Advances in Neural Information Processing Systems 17. Cambridge, MA: MIT Press.Google Scholar
- Schölkopf, B., & Smola, A. J. (2002). Learning with kernels. Cambridge, MA: MIT Press.Google Scholar
- Shelton, C. (2000). Morphable surface models. Int. J. of Computer Vision, 38, 75--91. Google ScholarDigital Library
- Steinke, F., Schölkopf, B., & Blanz, V. (2005). Support vector machines for 3D shape processing. Computer Graphics Forum (Proc. EUROGRAPHICS), 24.Google Scholar
- Vapnik, V. N. (1998). Statistical learning theory. New York: Wiley.Google Scholar
- Vetter, T., & Poggio, T. (1997). Linear object classes and image synthesis from a single example image. IEEE Trans. PAMI, 19, 733--742. Google ScholarDigital Library
- Wahba, G. (1990). Spline models for observational data, vol. 59 of CBMS-NSF Regional Conference Series in Applied Mathematics. Philadelphia, Pennsylvania: Society for Industrial and Applied Mathematics.Google Scholar
- Walder, C. J., & Lovell, B. C. (2003). Kernel based algebraic curve fitting. Proc. ICAPR'2003.Google Scholar
- Weston, J., Chapelle, O., Elisseeff, A., Schölkopf, B., & Vapnik, V. (2003). Kernel dependency estimation. Advances in Neural Information Processing Systems 15.Google Scholar
- Zien, A., Rätsch, G., Mika, S., Schölkopf, B., Lengauer, T., & Müüller, K.-R. (2000). Engineering SVM kernels that recognize translation initiation sites. Bioinformatics, 16, 799--807.Google ScholarCross Ref
- Object correspondence as a machine learning problem
Recommendations
A nonparallel support vector machine for a classification problem with universum learning
Universum samples, defined as samples not belonging to any class for a classification problem of interest, have been useful in supervised learning. Here we design a new nonparallel support vector machine ( U -NSVM) that ...
Learning Correspondence View with Support Vector Machine
GCIS '09: Proceedings of the 2009 WRI Global Congress on Intelligent Systems - Volume 04Correspondence view (CV) is recently introduced for rejecting outliers in computer vision. The fundamental idea of CV is that, for given two images of a scene, the corresponding points constitute a manifold in joint-image space , and outliers can be ...
Comments