Color photometric stereo and virtual image rendering using neural networks

SUMMARY In this paper we extend the application of neural network-based photometric stereo founded on the principle of empirical photometric stereo to color images proposing a method for computing both the normal vectors of a target object and its color reflectance coefficients. This method is able to render objects that have non-Lambert reflectance properties without using any parametric reflectance function as a reflectance model. In addition, we propose a novel neural network-based rendering method that allows the generation of realistic virtual images of an object with arbitrary light source direction and from arbitrary viewpoints based on the physical reflectance properties of the actual object and perform a comparative evaluation with approximations by existing models, the Phong model, and the Torrance–Sparrow model. © 2007 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 90(12): 47–60, 2007; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/ecjb.20423

[1]  Hidekazu Tanaka,et al.  Neural Network Based Photometric Stereo with a Nearby Rotational Moving Light Source , 1997 .

[2]  Yuji Iwahori,et al.  Neural network based modeling and color rendering for mixed reality , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[3]  Katsushi Ikeuchi,et al.  Object shape and reflectance modeling from observation , 1997, SIGGRAPH.

[4]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[5]  Robert J. Woodham,et al.  Photometric method for determining surface orientation from multiple images , 1980 .

[6]  Maria Petrou,et al.  Colour photometric stereo: simultaneous reconstruction of local gradient and colour of rough textured surfaces , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  Katsushi Ikeuchi,et al.  Temporal-color space analysis of reflection , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Yuji Iwahori,et al.  Self-calibration and neural network implementation of photometric stereo , 2002, Object recognition supported by user interaction for service robots.

[9]  M. Shoaib Bhuiyan,et al.  Neural network based photometric stereo for object with non-uniform reflectance factor , 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

[10]  R. Woodham.  Gradient and curvature from the photometric-stereo method, including local confidence estimation , 1994 .