Abstract
We present a new method for recovering the 3D shape of a featureless smooth surface from three or more calibrated images. The main contribution of this paper is the ability to handle general images which are taken from unconstrained viewpoints and unconstrained illumination directions. To the best of our knowledge, no other method is currently capable of handling such images, since correspondence between such images is hard to compute. Our method combines geometric and photometric information in order to recover a dense correspondence between the images and successfully computes an accurate 3D shape of the surface. The method is based on a single pass and local computation and does not make use of global optimization over the whole surface. While we assume a Lambertian reflectance function, our method can be easily modified to handle more general reflectance models as long as it is possible to recover local normals from photometric information. Experimental results are presented for simulated and real images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bouguet, J.Y.: Camera calibration toolbox for matlab, http://www.vision.caltech.edu/bouguetj/calib_doc
Dupuis, P., Oliensis, J.: Direct method for reconstructing shape from shading. In: Proc. IEEE Conf. Comp. Vision Patt. Recog., pp. 453–458 (1992)
Hartley, R.I., Sturm, P.: Triangulation. Comp. Vis. Im. Understanding 68(2), 146–157 (1997)
Horn, B.K.P., Brooks, M.: Seeing shape from shading. MIT Press, Cambridge (1999)
Ikeuchi, K., Horn, B.K.P.: Numerical shape from shading and occluding boundaries. Artificial Intelligence 17, 141–184 (1981)
Jin, H., Cremers, D., Yezzi, A., Soatto, S.: Shedding light on stereoscopic segmentation. In: Proc. Int. Conf. Comp. Vision (2004)
Kimmel, R., Bruckstein, A.: Global shape from shading. Comp. Vis. Im. Understanding 62(3), 360–369 (1995)
Maki, A., Watanabe, M., Wiles, C.: Geotensity: Computing motion and lighting for 3D surface reconstruction. Int. J. of Comp. Vision 48(2), 75–90 (2002)
Onn, R., Bruckstein, A.M.: Integrability disambiguates surface recovery in two-image photometric stereo. Int. J. of Comp. Vision 5(1), 105–113 (1990)
Prados, E., Faugeras, O.D.: Perspective shape from shading and viscosity solutions. In: Proc. Int. Conf. Comp. Vision, pp. 826–831 (2003)
Samaras, D., Metaxas, D.: Incorporating illumination constraints in deformable models for shape from shading and light direction estimation. IEEE Trans. Patt. Anal. Mach. Intell. 25(2), 247–264 (2003)
Shimshoni, I., Moses, Y., Lindenbaum, M.: Shape reconstruction of 3d bilaterally symmetric surfaces. Int. J. of Comp. Vision 39(2), 97–110 (2000)
Simakov, D., Frolova, D., Basri, R.: Dense shape reconstruction of a moving object under arbitrary, unknown lighting. In: Proc. Int. Conf. Comp. Vision, pp. 1202–1207 (2003)
Tankus, A., Sochen, N.A., Yeshurun, Y.: A new perspective [on] shape-from-shading. In: Proc. Int. Conf. Comp. Vision, pp. 862–869 (2003)
Weber, M., Blake, A., Cipolla, R.: Towards a complete dense geometric and photometric reconstruction under varying pose and illumination. In: British Mach. Vis. Conf., pp. 83–92 (2002)
Woodham, R.J.: Photometric stereo: A reflectance map technique for determining surface orientation from image intensity. In: Proc. SPIE, vol. 155, pp. 136–143 (1978)
Zhang, L., Curless, B., Hertzmann, A., Seitz, S.M.: Shape and motion under varying illumination: unifying structure from motion, photometric stereo, and multi-view stereo. In: Proc. Int. Conf. Comp. Vision, pp. 618–625 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moses, Y., Shimshoni, I. (2006). 3D Shape Recovery of Smooth Surfaces: Dropping the Fixed Viewpoint Assumption. In: Narayanan, P.J., Nayar, S.K., Shum, HY. (eds) Computer Vision – ACCV 2006. ACCV 2006. Lecture Notes in Computer Science, vol 3851. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11612032_44
Download citation
DOI: https://doi.org/10.1007/11612032_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-31219-2
Online ISBN: 978-3-540-32433-1
eBook Packages: Computer ScienceComputer Science (R0)