Non-rigid registration of 3D facial surfaces with robust outlier detection. Kaiser, M., Störmer, A., Arsić, D., & Rigoll, G. In 2009 Workshop on Applications of Computer Vision, WACV 2009, 2009.
abstract   bibtex   
Non-rigid registration of 3D facial surfaces is a crucial step in a variety of applications. Outliers, i.e., features in a facial surface that are not present in the reference face, often perturb the registration process. In this paper, we present a novel method which registers facial surfaces reliably also in the presence of huge outlier regions. A cost function incorporating several channels (red, green, blue, etc.) is proposed. The weight of each point of the facial surface in the cost function is controlled by a weight map, which is learned iteratively. Ideally, outliers will get a zero weight so that their disturbing effect is decreased. Results show that with an intelligent initialization the weight map improves the registration results considerably. © 2009 IEEE.
@inproceedings{
 title = {Non-rigid registration of 3D facial surfaces with robust outlier detection},
 type = {inproceedings},
 year = {2009},
 identifiers = {[object Object]},
 id = {da188db7-0134-3705-8d54-c1aeec0d5cec},
 created = {2018-08-01T22:39:56.908Z},
 file_attached = {false},
 profile_id = {86d0a3fe-915f-3d60-83e8-6b5e820c3322},
 last_modified = {2018-08-01T22:39:56.908Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {Non-rigid registration of 3D facial surfaces is a crucial step in a variety of applications. Outliers, i.e., features in a facial surface that are not present in the reference face, often perturb the registration process. In this paper, we present a novel method which registers facial surfaces reliably also in the presence of huge outlier regions. A cost function incorporating several channels (red, green, blue, etc.) is proposed. The weight of each point of the facial surface in the cost function is controlled by a weight map, which is learned iteratively. Ideally, outliers will get a zero weight so that their disturbing effect is decreased. Results show that with an intelligent initialization the weight map improves the registration results considerably. © 2009 IEEE.},
 bibtype = {inproceedings},
 author = {Kaiser, M. and Störmer, A. and Arsić, D. and Rigoll, G.},
 booktitle = {2009 Workshop on Applications of Computer Vision, WACV 2009}
}

Downloads: 0