Human Face Reconstruction Using Bayesian Deformable Models

This paper presents a Bayesian framework for 3D facial reconstruction. The framework iteratively deforms a generic face mesh to fit a set of range points representing a face. The generic mesh is generated from the extensive FRGC database of face images. The deformation process is conducted within a Bayesian framework and is driven by a Markov Chain Monte Carlo (MCMC) sampler which uses information from the likelihood and prior distributions of the generic face mesh. The paper presents results on the construction of a generic face model, the deformation framework and fitting results to both synthetic and real data. The results verify the effectiveness of the proposed technique, accurately deforming a generic face mesh to captured 3D data points of human faces.

[1]  David Salesin,et al.  Synthesizing realistic facial expressions from photographs , 1998, SIGGRAPH.

[2]  Edwin R. Hancock,et al.  Estimating facial pose using shape-from-shading , 2002, Pattern Recognit. Lett..

[3]  Adrian Hilton,et al.  Video-rate capture of dynamic face shape and appearance , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[4]  Sing Bing Kang.  A Structure from Motion Approach using Constrained Deformable Models and Appearance Prediction , 2002 .

[5]  Patrick J. Flynn,et al.  A survey of approaches to three-dimensional face recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  Dimitris N. Metaxas,et al.  Deformable model-based shape and motion analysis from images using motion residual error , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Takeo Kanade,et al.  Super-Resolution Optical Flow , 1999 .

[8]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  A-Nasser Ansari,et al.  3D face modeling using two views and a generic face model with application to 3D face recognition , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[10]  Gregory W. Wornell,et al.  Quantization Index Modulation Methods for Digital Watermarking and Information Embedding of Multimedia , 2001, J. VLSI Signal Process..

[11]  Qian Chen,et al.  Building 3-D Human Face Models from Two Photographs , 2001, J. VLSI Signal Process..

[12]  Thomas Vetter,et al.  Face Recognition Based on Fitting a 3D Morphable Model , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Ruey-Song Huang,et al.  Facial model estimation from stereo/mono image sequence , 2003, IEEE Trans. Multim..

[14]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[15]  Pascal Fua,et al.  Animated Heads from Ordinary Images: A Least-Squares Approach , 1999, Comput. Vis. Image Underst..

[16]  Pascal Fua,et al.  3D stereo reconstruction of human faces driven by differential constraints , 2000, Image Vis. Comput..