Multi-view AAM fitting and camera calibration

Koterba, Seth; Baker, Simon; Matthews, Iain; Hu, Chaofang; Xiao, Jing; Cohn, Jeffrey P.; Kanade, Takeo

doi:10.1109/iccv.2005.157

Cited by 37 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this an initial estimate of the similarity transform between the model space and the initial data is computed using linear least-squares. While this is a major limitation of our method in its current instantiation, this step could be replaced by automatic mutli-view face detection and localization in the input images, for example by a method such as that of Koterba et al [14]. Such an automated registration method would likely be equally or more accurate as manually selecting landmarks in noisy point-clouds.…”

Section: A Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Wavelet Model-based Stereo for Fast, Robust Face Reconstruction

Brunton

Lang

Dubois

et al. 2011

2011 Canadian Conference on Computer and Robot Vision

View full text Add to dashboard Cite

Abstract-When 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.

show abstract

Section: A Implementationmentioning

confidence: 99%

“…Zhao et al [13] performed stereo reconstruction by first fitting an approximate global parametric and then refining the model using local correspondence processes. Koterba et al [14] studied the relationship between multi-view Active Appearance Model (AAM) fitting and camera calibration.…”

Section: Introductionmentioning

confidence: 99%

Wavelet Model-based Stereo for Fast, Robust Face Reconstruction

Brunton

Lang

Dubois

et al. 2011

2011 Canadian Conference on Computer and Robot Vision

View full text Add to dashboard Cite

show abstract

“…Three-dimensional active appearance models (AAMs) are often used for facial motion capture [12,14]. In this approach, parametric models encoding both facial shape and appearance are fitted to one or several image sequences.…”

Section: Related Workmentioning

confidence: 99%

Dense 3D motion capture for human faces

Furukawa

Ponce

2009

2009 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Three-dimensional active appearance models (AAMs) are often used for facial motion capture [11,14]. In this approach, parametric models encoding both facial shape and appearance are fitted to one or several image sequences.…”

Section: Related Workmentioning

confidence: 99%