A Hybrid Framework for Surface Registration and Deformable Models

In computer vision, two complementary approaches have been widely used to perform object reconstruction and registration. The deformable model framework locally applies internal and external forces to fit 3D data. The non-rigid registration framework iteratively computes the best global transformation that minimizes the distance between a template and the data. In this paper, first we show that applying a global transformation on a surface model, is equivalent to applying an external force on a deformable model without any regularizing force. Second we propose a hybrid framework that combines the registration framework and the deformable models framework. Our hybrid deformation approach allows us to control the scale at which the model is deformed. This is clearly beneficial for performing both reconstruction and registration tasks. We show examples of this approach on active contours and deformable surfaces. Furthermore, a global transformation based on axial symmetry is introduced.