Perceiving Systems Conference Paper 2012

Coregistration: Simultaneous alignment and modeling of articulated 3D shape

Coregteaser

Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.

Author(s): Hirshberg, D. and Loper, M. and Rachlin, E. and Black, M.J.
Book Title: European Conf. on Computer Vision (ECCV)
Pages: 242--255
Year: 2012
Month: October
Series: LNCS 7577, Part IV
Editors: A. Fitzgibbon et al. (Eds.)
Publisher: Springer-Verlag
Project(s):
Bibtex Type: Conference Paper (inproceedings)
DOI: 10.1007/978-3-642-33783-3_18
Electronic Archiving: grant_archive
Links:

BibTex

@inproceedings{Hirshberg:ECCV:2012,
  title = {Coregistration: Simultaneous alignment and modeling of articulated {3D} shape},
  booktitle = {European Conf. on Computer Vision (ECCV)},
  abstract = {Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize
  implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this
  model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing
  a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness
  to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.},
  pages = {242--255},
  series = {LNCS 7577, Part IV},
  editors = {A. Fitzgibbon et al. (Eds.)},
  publisher = {Springer-Verlag},
  month = oct,
  year = {2012},
  slug = {hirshberg-eccv-2012},
  author = {Hirshberg, D. and Loper, M. and Rachlin, E. and Black, M.J.},
  month_numeric = {10}
}