Header logo is

Learning Dense 3D Correspondence

2007

Conference Paper

ei


Establishing correspondence between distinct objects is an important and nontrivial task: correctness of the correspondence hinges on properties which are difficult to capture in an a priori criterion. While previous work has used a priori criteria which in some cases led to very good results, the present paper explores whether it is possible to learn a combination of features that, for a given training set of aligned human heads, characterizes the notion of correct correspondence. By optimizing this criterion, we are then able to compute correspondence and morphs for novel heads.

Author(s): Steinke, F. and Schölkopf, B. and Blanz, V.
Book Title: Advances in Neural Information Processing Systems 19
Journal: Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference
Pages: 1313-1320
Year: 2007
Month: September
Day: 0
Editors: B Sch{\"o}lkopf and J Platt and T Hofmann
Publisher: MIT Press

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: 20th Annual Conference on Neural Information Processing Systems (NIPS 2006)
Event Place: Vancouver, BC, Canada

Address: Cambridge, MA, USA
Digital: 0
ISBN: 0-262-19568-2
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{4148,
  title = {Learning Dense 3D Correspondence},
  author = {Steinke, F. and Sch{\"o}lkopf, B. and Blanz, V.},
  journal = {Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference},
  booktitle = {Advances in Neural Information Processing Systems 19},
  pages = {1313-1320},
  editors = {B Sch{\"o}lkopf and J Platt and T Hofmann},
  publisher = {MIT Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, MA, USA},
  month = sep,
  year = {2007},
  month_numeric = {9}
}