Brandon M. Smith,
Charles R. Dyer
University of Wisconsin – Madison
 
Abstract
An algorithm is presented that estimates 3D facial landmark coordinates and occlusion
state from a single 2D image. Unlike previous approaches, we divide the 3D
cascaded shape regression problem into a set of viewpoint domains, which helps avoid
problems in the optimization, such as local minima at test time, and averaging conflicting
gradient directions in the domain maps during training. These problems are especially
important to address in the 3D case, where a wider range of head poses is expected. Parametric
shape models are used and are shown to have several desirable qualities compared
to the recent trend of modeling shape nonparametrically. Results show quantitatively that
our approach is significantly more accurate than recent work.
 
Publication
Brandon M. Smith, Charles R. Dyer. Pose-Robust 3D Facial Landmark Estimation
from a Single 2D Image, British Machine Vision Conference (BMVC), York, September 2016.
[PDF 1.6 MB]
BibTeX: @inproceedings{ SmithBMVC2016, author = {Brandon M. Smith and Charles R. Dyer}, title = "{P}ose-{R}obust {3D} {F}acial {L}andmark {E}stimation from a {S}ingle {2D} {I}mage", booktitle = {Proceedings of the 27th British Machine Vision Conference (BMVC)}, month = {September}, year = {2016}, publisher = {BMVA Press}, editor = {Richard C. Wilson and Edwin R. Hancock and William A. P. Smith}, }
 
Poster
Download [PDF 7.3 MB]
 
Extended Abstract
Download [PDF 0.5 MB]
 
Acknowledgement
This work was supported in part by the U.S. Department of Transportation Federal Highway
Administration DTFH61-14-C-00011.