Abstract
Realistic representation of objects requires models which can synthesize the image of an object under all possible viewing conditions. We propose to learn these models from examples. Methods for learning surface geometry and albedo from one or more images under fixed posed and varying lighting conditions are described. Singular value decomposition (SVD) is used to determine shape, albedo, and lighting conditions up to an unknown 3×3 matrix, which is sufficient for recognition. The use of class-specific knowledge and the integrability constraint to determine this matrix is explored. We show that when the integrability constraint is applied to objects with varying albedo it leads to an ambiguity in depth estimation similar to the bas relief ambiguity. The integrability constraint, however, is useful for resolving ambiguities which arise in current photometric theories.
Preview
Unable to display preview. Download preview PDF.
References
J.J. Atick, P.A. Griffin and A. N. Redlich. Statistical Approach to Shape from Shading. Preprint. Computational Neuroscience Laboratory. The Rockefeller University. New York. NY. 1995.
P. Belhumeur and D. Kriegman. “What is the set of images of an object under all lighting conditions?”. In Proceedings of Conference on Computer Vision and Pattern Recognition. San Francisco. CA. 1996.
P.N. Belhumeur, J.P. Hespanha, and D.J. Kriegman. “Eignefaces vs. Fisherfaces: Recognition using Class Specific Linear Projection”. In Proceedings of ECCV. Cambridge, England. 1996.
A. Lanitis, C.J. Taylor and T.F. Cootes. A Unified approach to Coding and Interpreting Face Images. In Proceedings of ICCV. Boston. MA. 1995.
R. Epstein, P.W. Hallinan and A.L. Yuille. “5 ± Eigenimages Suffice: An Empirical Investigation of Low-Dimensional Lighting Models”. In Proceedings of IEEE WORKSHOP ON PHYSICS-BASED MODELING IN COMPUTER VISION. 1995.
R. Epstein and A.L. Yuille. In preparation. 1996.
R.A. Fisher. The use of multiple measures in taxonomic problems. Ann. Eugenics, 7: pp 179–188. 1936.
U. Grenander, Y. Chow, and D.M. Keenan. Hands: A Pattern Theroetic Study of Biological Shapes. New York: Springer-Verlag. 1991.
W.E.L. Grimson. Object Recognition by Computer. MIT Press. Cambrige, MA. 1990.
G. Hager and P.N. Belhumeur. In Proc ECCV. Cambridge, England. 1996.
P.W. Hallinan. “A low-dimensional lighting representation of human faces for arbitrary lighting conditions”. In. Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pp 995–999. 1994.
P.W. Hallinan. A Deformable Model for Face Recognition under Arbitrary Lighting Conditions. PhD Thesis. Division of Applied Sciences. Harvard University. 1995.
K. Hayakawa. “Photometric Stereo under a light source with arbitrary motion”. Journal of the Optical Society of America A, 11(11). 1994.
B.K.P. Horn. Computer Vision. MIT Press, Cambridge, Mass. 1986.
B.K.P. Horn and M. J. Brooks, Eds. Shape from Shading. Cambridge MA, MIT Press, 1989.
P.J. Huber. Robust Statistics. John Wiley and Sons. New York. 1980.
Y. Iwahori, R.J. Woodham and A Bagheri “Principal Components Analysis and Neural Network Implementation of Photometric Stereo”. In Proceedings of the IEEE Workshop on Physics-Based Modeling in Computer Vision. pp117–125 (1995).
J.J. Koenderink and A.J. van Doorn. “The internal representation of solid shape with respect to vision”. Biological Cybernetics, Vol. 32. pp 211–216. 1979.
J.J. Koenderink, A.J. van Doorn, A.M.L. Kappers ”Surface Perception in Pictures”. Perception and Psychophysics, vol 52, pp487–496. 1992.
Y. Moses, Y. Adini, and S. Ullman. “Face Recognition: The problem of compensating for changes in the illumination direction”. In European Conf. on Comp. Vision., pp 286–296. 1994.
Y. Moses, S. Ullman, and S. Edelman. “Generalization to Novel Images in Upright and Inverted Faces”. Preprint. Dept. of Applied Mathematics and Computer Science. The Weizmann Institute of Science. Israel. 1995.
J.L. Mundy and A. Zisserman (eds.) Geometric Invariance in Computer Vision. MIT Press. Cambridge, MA. 1992.
H. Murase and S. Nayar. “Visual learning and recognition of 3-D objects from appearance”. Int. Journal of Computer Vision. 14. pp 5–24. 1995.
S.K. Nayar, K. Ikeuchi and T. Kanade ”Surface reflections: physical and geometric perspectives” IEEE trans. on Pattern Analysis and Machine Intelligence, vol 13 p611–634. 1991.
A. Shashua. Geometry and Photometry in 3D Visual Recognition. PhD Thesis. MIT. 1992.
W. Silver. Determining Shape and Reflectance Using Multiple Images. PhD Thesis. MIT, Cambridge, MA. 1980.
M. Turk and A. Pentland. “Faces recognition using eigenfaces”. In Proceedings of IEEE Conf. on Comp. Vision and Pattern Recognition. pp 586–591. 1991.
R. Woodham. “Analyszing Images of Curved Surfaces”. Artificial Intelligence, 17, pp 117–140. 1981.
A.L. Yuille, M. Ferraro, and T. Zhang. “Shape from Warping”. Submitted to CVGIP. 1996.
A.L. Yuille. “A Mathematical Analysis of SVD applied to lighting estimation and image warping”. Preprint. Smith-Kettlewell Eye Research Institute. San Francisco. 1996.
Song Chun Zhu and A.L. Yuille. “A Flexible Object Recognition and Modelling System”. In Proceedings of the International Conference on Computer Vision. Boston 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Epstein, R., Yuille, A.L., Belhumeur, P.N. (1996). Learning object representations from lighting variations. In: Ponce, J., Zisserman, A., Hebert, M. (eds) Object Representation in Computer Vision II. ORCV 1996. Lecture Notes in Computer Science, vol 1144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61750-7_29
Download citation
DOI: https://doi.org/10.1007/3-540-61750-7_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61750-1
Online ISBN: 978-3-540-70673-1
eBook Packages: Springer Book Archive