Initialization of deformable models from 3D data

The robustness of shape recovery based on deformable models depends in general, on the relative difference of position and topology of the initial model with respect to the data: a close initialization with correct topology guarantees a proper recovery of the object. Furthermore, the closeness of the initial model greatly influences the time of computation needed for the recovery. In this paper, we propose a method for initializing deformable models from range data or volumetric images. The proposed method solves two distinct problems. First, we use the topological segmentation of volumetric images in order to recover the approximate topology of the object. Second, we use an efficient mesh sampling algorithm to control the number of vertices of the initial model. The method takes into account missing data and outliers.