Automatic 3D face reconstruction from single images or video

Pia Breuer, Kwang- In Kim, Wolf Kienzle, Bernhard Schölkopf, Volker Blanz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • 28 Citations

Abstract

This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high resolution 3D surface model.
LanguageEnglish
Title of host publicationProc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Print)9781424421541
DOIs
StatusPublished - 2008
Event8th International Conference on Automatic Face & Gesture Recognition (FG 08), 2008 - Amsterdam, Netherlands
Duration: 17 Sep 200819 Sep 2008

Conference

Conference8th International Conference on Automatic Face & Gesture Recognition (FG 08), 2008
CountryNetherlands
CityAmsterdam
Period17/09/0819/09/08

Fingerprint

Support vector machines
Face recognition

Cite this

Breuer, P., Kim, K. I., Kienzle, W., Schölkopf, B., & Blanz, V. (2008). Automatic 3D face reconstruction from single images or video. In Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008 (pp. 1-8). IEEE. DOI: 10.1109/AFGR.2008.4813339

Automatic 3D face reconstruction from single images or video. / Breuer, Pia; Kim, Kwang- In; Kienzle, Wolf; Schölkopf, Bernhard ; Blanz, Volker.

Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008. IEEE, 2008. p. 1-8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Breuer, P, Kim, KI, Kienzle, W, Schölkopf, B & Blanz, V 2008, Automatic 3D face reconstruction from single images or video. in Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008. IEEE, pp. 1-8, 8th International Conference on Automatic Face & Gesture Recognition (FG 08), 2008, Amsterdam, Netherlands, 17/09/08. DOI: 10.1109/AFGR.2008.4813339
Breuer P, Kim KI, Kienzle W, Schölkopf B, Blanz V. Automatic 3D face reconstruction from single images or video. In Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008. IEEE. 2008. p. 1-8. Available from, DOI: 10.1109/AFGR.2008.4813339
Breuer, Pia ; Kim, Kwang- In ; Kienzle, Wolf ; Schölkopf, Bernhard ; Blanz, Volker. / Automatic 3D face reconstruction from single images or video. Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008. IEEE, 2008. pp. 1-8
@inproceedings{51578b43bae9430eb7b929a89e906170,
title = "Automatic 3D face reconstruction from single images or video",
abstract = "This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high resolution 3D surface model.",
author = "Pia Breuer and Kim, {Kwang- In} and Wolf Kienzle and Bernhard Sch{\"o}lkopf and Volker Blanz",
year = "2008",
doi = "10.1109/AFGR.2008.4813339",
language = "English",
isbn = "9781424421541",
pages = "1--8",
booktitle = "Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008",
publisher = "IEEE",
address = "USA United States",

}

TY - GEN

T1 - Automatic 3D face reconstruction from single images or video

AU - Breuer,Pia

AU - Kim,Kwang- In

AU - Kienzle,Wolf

AU - Schölkopf,Bernhard

AU - Blanz,Volker

PY - 2008

Y1 - 2008

N2 - This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high resolution 3D surface model.

AB - This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high resolution 3D surface model.

UR - http://dx.doi.org/10.1109/AFGR.2008.4813339

U2 - 10.1109/AFGR.2008.4813339

DO - 10.1109/AFGR.2008.4813339

M3 - Conference contribution

SN - 9781424421541

SP - 1

EP - 8

BT - Proc. IEEE International Conference on Automatic Face & Gesture Recognition, 2008

PB - IEEE

ER -