A surface deformation framework for 3D shape recovery. Sahillioglu, Y. & Yemez, Y. In Gunsel, B, Jain, A., Tekalp, A., & Sankur, B, editors, MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY, volume 4105, of LECTURE NOTES IN COMPUTER SCIENCE, pages 570-577, 2006. Int Assoc Pattern Recognit; Istanbul Tech Univ; TUBITAK. International Workshop on Multimedia Content Representation, Classification and Security (MRCS 2006), Istanbul, TURKEY, SEP 11-13, 2006
abstract   bibtex   
We present a surface deformation framework for the problem of 3D shape recovery. A spatially smooth and topologically plausible surface mesh representation is constructed via a surface evolution based technique, starting from an initial model. The initial mesh, representing the bounding surface, is refined or simplified where necessary during surface evolution using a set of local mesh transform operations so as to adapt local properties of the object surface. The final mesh obtained at convergence can adequately represent the complex surface details such as bifurcations, protrusions and large visible concavities. The performance of the proposed framework which is in fact very general and applicable to any kind of raw surface data, is demonstrated on the problem of shape reconstruction from silhouettes. Moreover, since the approach we take for surface deformation is Lagrangian, that can track changes in connectivity and geometry of the deformable mesh during surface evolution, the proposed framework can be used to build efficient time-varying representations of dynamic scenes.
@inproceedings{ ISI:000241429800073,
Author = {Sahillioglu, Yusuf and Yemez, Yucel},
Editor = {{Gunsel, B and Jain, AK and Tekalp, AM and Sankur, B}},
Title = {{A surface deformation framework for 3D shape recovery}},
Booktitle = {{MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY}},
Series = {{LECTURE NOTES IN COMPUTER SCIENCE}},
Year = {{2006}},
Volume = {{4105}},
Pages = {{570-577}},
Note = {{International Workshop on Multimedia Content Representation,
   Classification and Security (MRCS 2006), Istanbul, TURKEY, SEP 11-13,
   2006}},
Organization = {{Int Assoc Pattern Recognit; Istanbul Tech Univ; TUBITAK}},
Abstract = {{We present a surface deformation framework for the problem of 3D shape
   recovery. A spatially smooth and topologically plausible surface mesh
   representation is constructed via a surface evolution based technique,
   starting from an initial model. The initial mesh, representing the
   bounding surface, is refined or simplified where necessary during
   surface evolution using a set of local mesh transform operations so as
   to adapt local properties of the object surface. The final mesh obtained
   at convergence can adequately represent the complex surface details such
   as bifurcations, protrusions and large visible concavities. The
   performance of the proposed framework which is in fact very general and
   applicable to any kind of raw surface data, is demonstrated on the
   problem of shape reconstruction from silhouettes. Moreover, since the
   approach we take for surface deformation is Lagrangian, that can track
   changes in connectivity and geometry of the deformable mesh during
   surface evolution, the proposed framework can be used to build efficient
   time-varying representations of dynamic scenes.}},
ISSN = {{0302-9743}},
ISBN = {{3-540-39392-7}},
Unique-ID = {{ISI:000241429800073}},
}

Downloads: 0