Anais do X SIBGRAPI (1997) #AND06
Rosana M. da Silva,
Wu, Shin-Ting, UNICAMP
Abstract. The reconstruction of a 3-D model from images can be conveniently split into two stages. The first stage consists basically on the extraction of geometrical information such as the depth and the orientation of image points and the second stage concentrates on the transformation of these data to a 3-D model. In this comunication we will focus on the second stage. Our approach is based on a deformable model, which offers more flexibility to mold a 3-D model according to several geometrical constraints. Moreover, instead of looking for a global functional that carries out the transformation, we opt for establishing discrete local correspondences between 3-D surface point data extracted from images and 3-D model points.
[ full version | contact authors ]