3-D Geometry reconstruction using a color image
stereo pair and partial differential equations
by
L.Alvarez and J.Sánchez

In this work, we present a new model for a dense disparity estimation and the 3-D geometry reconstruction using a
color image stereo pair. First, we present a brief introduction to the 3-D Geometry of a camera system. Next,  we
propose a new model for the disparity estimation based on an energie functional. We look for the local minima of
the energy using the associated Euler-Lagrange partial differential equation. This model is a generalization to color
image of the model developed by L.Alvarez, R.Deriche, J.Sánchez and J.Weickert in the paper Dense Disparity Map
Estimation Respecting Image Discontinuities with some changes in the strategy to avoid the irrelevant local minima.
We present some numerical experiences of $3-D$ reconstruction, using this method for some real stereo pairs.
 

For more details see the paper 3-D Geometry reconstruction using a color image stereo pair and partial
differential equations

Next we present several experiments to illustrate the method



Figure 1. We present an stereo pair of the face of Javier Sánchez, one of author
of this work, and 4 views of the 3-D reconstruction using the proposed method. If
you click on the image you will see a movie to ilustrate the 3-D reconstruction.



Figure 2. We present an stereo pair of the face of Julio Esclarín, a member of the Comp.
Science Depart. at the University of Las Palmas, and 4 views of the 3-D reconstruction
using the proposed method. If you click on the image you will see a movie to
ilustrate the 3-D reconstruction.


 



Figure 3. We present an stereo pair of an outdoor scene of the laboratory Instituto Universitario de
Ciencias y Tecnologías Cibernéticas de la Universidad de Las Palmas de G.C., and 4 views of
the 3-D reconstruction using the proposed method. If you click on the image you will see a movie to
ilustrate the 3-D reconstruction.




lalvarez@dis.ulpgc.es / updated March 17, 2000