Top > JACIII > Neural Network Implementation of Image Rendering via Self-Cali ...

single-jc.php

JACIII Vol.14 No.4 pp. 344-352
doi: 10.20965/jaciii.2010.p0344
(2010)

Paper:

Views over last 60 days: 656

Neural Network Implementation of Image Rendering via Self-Calibration

Yi Ding*1, Yuji Iwahori*2, Tsuyoshi Nakamura*1, Lifeng He*3,
Robert J. Woodham*4, and Hidenori Itoh*1

*1Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya 466-8555, Japan

*2Dept. of Computer Science, Chubu University, 1200 Matsumoto-cho, Kasugai 487-8501, Japan

*3Faculty of Information Science and Technology, Aichi Prefectural University, 1522-3 Kumabari-Ibaragabasama, Nagakute, Aichi-gun, Aichi 480-1198, Japan

*4University of British Columbia, Vancouver, B.C. V6T 1Z4, Canada

Received:
August 26, 2009
Accepted:
January 7, 2010
Published:
May 20, 2010
Creative Commons License
Keywords:
neural network based rendering, photometric stereo, self-calibration, albedo, shape recovery
Abstract
This paper proposes a new approach for selfcalibration and color image rendering using Radial Basis Function (RBF) neural network. Most empirical approaches make use of a calibration object. Here, we require no calibration object to both shape recovery and color image rendering. The neural network learning data are obtained through the rotations of a target object. The approach can generate realistic virtual images without any calibration object which has the same reflectance properties as the target object. The proposed approach uses a neural network to obtain both surface orientation and albedo, and applies another neural network to generate virtual images for any viewpoint and any direction of light source. Experiments with real data are demonstrated.
Cite this article as:
Y. Ding, Y. Iwahori, T. Nakamura, L. He, R. Woodham, and H. Itoh, “Neural Network Implementation of Image Rendering via Self-Calibration,” J. Adv. Comput. Intell. Intell. Inform., Vol.14 No.4, pp. 344-352, 2010.
Data files:
References
  1. [1] R. J. Woodham, “Photometric Method for Determining Surface Orientation from Multiple Images,” Opt. Engineering, pp. 139-144, 1980.
  2. [2] R. J. Woodham, “Gradient and Curvature from the Photometric-Stereo Method, Including Local Confidence Estimation,” J. Opt. Soc. Am., A, pp. 3050-3068, 1994.
  3. [3] Y. Iwahori, R. J. Woodham, and A. Bagheri, “Principal Components Analysis and Neural Network Implementation of Photometric Stereo,” Proc. IEEE Workshop on Physics-Based Modeling in Computer Vision, pp. 117-125, 1995.
  4. [4] S. Chen, Y. Wu, and B. L. Luk, “Combined Genetic Algorithm Optimization and Regularized Orthogonal Least Squares Learning for Radial Basis Function Networks,” IEEE Trans. on Neural Networks, Vol.10, No,5, pp. 1239-1243, 1999.
    ISSN 1045-9227.
  5. [5] Y. Iwahori, R. J. Woodham, S. Bhuiyan, and N. Ishii, “Neural Network Based Photometric Stereo for Object with Non-Uniform Reflectance Factor,” Proc. of 6th Int. Conf. on Neural Information Processing (ICONIP’99), Vol.III, pp. 1213-1218, 1999.
  6. [6] H. Kawanaka, Y. Iwahori, R. J. Woodham, and K. Funahashi, “Color Photometric Stereo and Virtual Image Rendering Using Neural Network,” Trans. of IEICE, Vol.J89-D-II, No.2, pp. 381-392, 2006. (in Japanese)
  7. [7] K. Ikeuchi, Y. Sato, K. Nishino, and I. Sato, “Modeling from Reality: Photometric Aspect,” Trans. of Virtual Reality Society in Japan, Vol.4, No.4, pp. 623-630, 1999. (in Japanese)
  8. [8] A. Laurentini, “How Far 3D Shapes Can Be Understood from 2D Silhouettes,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.17, No.2, pp. 188-195, 1995.
  9. [9] S. Hiura, K. Sato, and S. Inokuchi, “Simultaneous Measurement of Shape and Reflectance by Rotating Object,” Trans. of Information Processing Society of Japan, Vol.36, No.10, pp. 2295-2302, 1995.
  10. [10] Y. Iwahori, Y. Watanabe, K. Funahashi, and R. J. Woodham, “Self-Calibrated Neural Network Based Photometric Stereo,” Int. J. of Computer and Information Science, Vol.3, No.1, 40359, 2002.
  11. [11] G. Meister, R. Wiemker, R. Monno, H. Spitzer, and A. Strahler, “Investigation on the Torrance-Sparrow Specular BRDF Model,” IGARSS’98, Vol.4, pp. 2095-2097, 1998.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 19, 2024