Wavelet model-based stereo for fast, robust face reconstruction

  1. (PDF, 1 MB)
DOIResolve DOI: http://doi.org/10.1109/CRV.2011.53
AuthorSearch for: ; Search for: ; Search for: ; Search for:
Proceedings title2011 Canadian Conference on Computer and Robot Vision (CRV)
Conference8th Canadian Conference on Computer and Robot Vision (CRV 2011), 25-27 May 2011, St. John's, Newfoundland
Pages347354; # of pages: 8
Subjectmodel-based stereo; wavelet prior; Bayesian framework; graphics processing unit (GPU)
AbstractWhen reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstruct is the human face. In this paper we learn a statistical wavelet prior of the shape of the human face and use it to constrain stereo reconstruction within a Bayesian framework. We initialize our algorithm with a, typically noisy, point cloud from a standard stereo algorithm, and search our parameter space for the shape that best fits the point cloud. Due to the wavelet basis, our shape parameters can be optimized independently, thus simplifying and accelerating the search. We follow this by optimizing for a secondary prior and observation: smoothing and photoconsistency. Our method is fast, and is robust to noise and outliers. Additionally, we obtain a shape in an parameterized and corresponded shape space, making it ready for further processing such as tracking, recognition or statistical analysis.
Publication date
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NPARC number18548398
Export citationExport as RIS
Report a correctionReport a correction
Record identifier5ed5d946-a3a0-461e-8024-ed266fd4533b
Record created2011-09-08
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)
Date modified: