||3D multi-view reconstruction technologies have many applications in media production due to their abilities to produce a virtual clone of an actor from a simple video acquisition performed by a set of multi-viewpoint cameras. We perform synchronized video captures from multiple viewpoints in a chroma-key studio and then compute a silhouette-based reconstruction of an actor. The major drawback of this method is that the successive poses of the actor are reconstructed as inconsistent time series of static objects. We propose a new approach to transform these initial results into a dynamic 3D object where the actor is figured as a time-consistent animated character. Our method contains a motion estimation procedure and a template mesh deformation process to finally obtain a single animated mesh that matches the evolving shape of the reconstructed actor.