Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

High-Fidelity Image-Based Modeling Yasutaka Furukawa

Summary: High-Fidelity Image-Based Modeling
Yasutaka Furukawa
Department of Computer Science, University of Illinois at Urbana-Champaign, USA
Jean Ponce
Department of Computer Science, University of Illinois at Urbana-Champaign, USA,
D´epartement d'Informatique Ecole Normale Sup´erieure, Paris, France
Figure 1: Shaded and texture-mapped images of the reconstructions of a Polynesian statue, a Homo Heidelbergensis skull, resting on a circular
cork stand, and an action figure depicting a Roman soldier.
This article presents a novel method for acquiring high-fidelity
solid models of complex 3D shapes from multiple calibrated pho-
tographs. The proposed approach enforces both the photometric
and geometric constraints associated with available image data us-
ing a simple iterative deformation process. Concretely, a wide-
baseline stereo matching technique based on Mikolajczyk's and
Schmid's affine regions is first used to reconstruct a dense set of
patches on the surface of the object of interest. Next, the boundary
of the object's visual hull is deformed to pass through the centers
of the reconstructed patches and recover the surface's main struc-
tural features and concavities. Fine surface details are finally recon-


Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle


Collections: Computer Technologies and Information Sciences