Object correspondence as a machine learning problem
2005
Conference Paper
ei
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.
Author(s): | Schölkopf, B. and Steinke, F. and Blanz, V. |
Book Title: | Proceedings of the 22nd International Conference on Machine Learning |
Pages: | 777-784 |
Year: | 2005 |
Day: | 0 |
Editors: | L De Raedt and S Wrobel |
Publisher: | ACM |
Department(s): | Empirische Inferenz |
Bibtex Type: | Conference Paper (inproceedings) |
Event Name: | ICML 2005 |
Event Place: | Bonn, Germany |
Address: | New York, NY, USA |
Organization: | Max-Planck-Gesellschaft |
School: | Biologische Kybernetik |
Links: |
PDF
|
BibTex @inproceedings{3386, title = {Object correspondence as a machine learning problem}, author = {Sch{\"o}lkopf, B. and Steinke, F. and Blanz, V.}, booktitle = {Proceedings of the 22nd International Conference on Machine Learning}, pages = {777-784}, editors = {L De Raedt and S Wrobel}, publisher = {ACM}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, address = {New York, NY, USA}, year = {2005}, doi = {} } |