A coupled statistical model for face shape recovery

Authors:
Mario Castelán;William A. P. Smith;Edwin R. Hancock
Affiliations:
Department of Computer Science, University of York, York, UK;Department of Computer Science, University of York, York, UK;Department of Computer Science, University of York, York, UK
Venue:
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Year:
2006

Citing 10
Cited 0

A line-integration based method for depth recovery from surface normals

Computer Vision, Graphics, and Image Processing
A Method for Enforcing Integrability in Shape from Shading Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
A morphable model for the synthesis of 3D faces

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Incorporating Illumination Constraints in Deformable Models for Shape from Shading and Light Direction Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Terrain Analysis Using Radar Shape-from-Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Acquiring Height Maps of Faces from a Single Image

3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium
Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We focus on the problem of developing a coupled statistical model that can be used to recover surface height from brightness images of faces. The idea is to couple intensity and height by jointly modeling their combined variations. The models are constructed by performing Principal Component Analysis (PCA) on the shape coefficients for both intensity and height training data. By fitting the model to intensity data, the height information is implicitly recovered from the coupled shape parameters. Experiments show that the methods generate accurate surfaces from out-of training intensity images.