Fitting 3D morphable models using implicit representations
C. Basso, and A. Verri. Journal of Virtual Reality and Broadcasting, (February 2007)urn:nbn:de:0009-6-12799,, ISSN 1860-2037.
Abstract
We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to IF03 by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.
%0 Journal Article
%1 BV07
%A Basso, Curzio
%A Verri, Alessandro
%D 2007
%E Herder, Jens
%J Journal of Virtual Reality and Broadcasting
%K 2007 3D_Morphable_Models 4(2007)18 4.2007 DiPP Digital_Peer_Publishing JVRB Journal_of_Virtual_Reality_and_Broadcasting Open_Access Peer_Reviewed [BV07] computer_graphics implicit_surface_representations non-rigid_registration
%N 18
%T Fitting 3D morphable models using implicit representations
%V 4
%X We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to IF03 by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.
@article{BV07,
abstract = {We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to [IF03] by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.},
added-at = {2008-02-29T09:05:41.000+0100},
author = {Basso, Curzio and Verri, Alessandro},
biburl = {https://www.bibsonomy.org/bibtex/27570bf7b8da7c86689c5c2c42fe4cacf/jvrb_regulski},
editor = {Herder, Jens},
interhash = {e51883efbcd43d55f7b2cae19d5b80a9},
intrahash = {7570bf7b8da7c86689c5c2c42fe4cacf},
journal = {Journal of Virtual Reality and Broadcasting},
keywords = {2007 3D_Morphable_Models 4(2007)18 4.2007 DiPP Digital_Peer_Publishing JVRB Journal_of_Virtual_Reality_and_Broadcasting Open_Access Peer_Reviewed [BV07] computer_graphics implicit_surface_representations non-rigid_registration},
month = {February},
note = {{\tt urn:nbn:de:0009-6-12799,}, ISSN 1860-2037},
number = 18,
timestamp = {2008-02-29T09:08:06.000+0100},
title = {Fitting 3D morphable models using implicit representations},
volume = 4,
year = 2007
}