Learning Dense 3D Correspondence
Abstract
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.
Cite
Text
Steinke et al. "Learning Dense 3D Correspondence." Neural Information Processing Systems, 2006.Markdown
[Steinke et al. "Learning Dense 3D Correspondence." Neural Information Processing Systems, 2006.](https://mlanthology.org/neurips/2006/steinke2006neurips-learning/)BibTeX
@inproceedings{steinke2006neurips-learning,
title = {{Learning Dense 3D Correspondence}},
author = {Steinke, Florian and Blanz, Volker and Schölkopf, Bernhard},
booktitle = {Neural Information Processing Systems},
year = {2006},
pages = {1313-1320},
url = {https://mlanthology.org/neurips/2006/steinke2006neurips-learning/}
}