Monocular Template-based Reconstruction of Smooth and Inextensible Surfaces

In this chapter, we deal with another problem of importance in computer vision: the reconstruction of a deforming surface from a monocular sequence of images. Our contribution is a new algorithm that works under the assumption that the deformable surface is inextensible. This problem may be seen as a natural continuation of the aspects previously treated in this document. Indeed, as we will show, the approach we use for reconstructing deformable surfaces is again formulated as a parameter estimation problem. Besides, given the considered approach, the reconstruction of deformable surfaces requires one to first register the current image with some template image. Our contributions related to this topic from section 5 and section 6 may thus be used here. The work presented in this chapter has been published in (39).


Contributions to Parametric Image Registration and 3D Surface Reconstruction (Ph.D. dissertation, November 2010) - Florent Brunet
Webpage generated on July 2011
PDF version (11 Mo)