BRDF Estimation for Faces from a Sparse Dataset Using a Neural Network

We present a novel five source near-infrared photometric stereo 3D face capture device. The accuracy of the system is demonstrated by a comparison with ground truth from a commercial 3D scanner. We also use the data from the five captured images to model the Bi-directional Reflectance Distribution Function BRDF in order to synthesise images from novel lighting directions. A comparison of these synthetic images created from modelling the BRDF using a three layer neural network, a linear interpolation method and the Lambertian model is given, which shows that the neural network proves to be the most photo-realistic.

[1]  J. Lambert.  Photometria sive de mensvra et gradibvs lvminis, colorvm et vmbrae , 1970 .

[2]  Pieter Peers,et al.  Practical modeling and acquisition of layered facial reflectance , 2008, SIGGRAPH Asia '08.

[3]  K. Torrance,et al.  Theory for off-specular reflection from roughened surfaces , 1967 .

[4]  Paul E. Debevec,et al.  Acquiring the reflectance field of a human face , 2000, SIGGRAPH.

[5]  Baba C. Vemuri,et al.  Non-Lambertian Reflectance Modeling and Shape Recovery of Faces Using Tensor Splines , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Bobby Bodenheimer,et al.  Synthesis and evaluation of linear motion transitions , 2008, TOGS.

[7]  Steve Marschner,et al.  Image-Based BRDF Measurement Including Human Skin , 1999, Rendering Techniques.

[8]  Bui Tuong Phong.  Illumination for computer generated pictures , 1975, Commun. ACM.

[9]  Francis Neelamkavil,et al.  Approximating Reflectance Functions using Neural Networks , 1998, Rendering Techniques.

[10]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[11]  Melvyn L. Smith,et al.  3D face reconstructions from photometric stereo using near infrared and visible light , 2010, Comput. Vis. Image Underst..

[12]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[13]  Shree K. Nayar,et al.  Generalization of the Lambertian model and implications for machine vision , 1995, International Journal of Computer Vision.