Transferring a Labeled Generic Rig to Animate Face Models Ver´onica Costa Teixeira Orvalho†, Ernesto Zacur‡, Antonio Susin† veronica.costa@upc.edu, ernesto.zacur@upf.edu, toni.susin@upc.edu †Laboratorio de Simulaci´on Din´amica (Univ. Polit` ecnica de Catalunya), ‡Universitat Pompeu Fabra Abstract We present a facial deformation system that adapts a generic fa- cial rig into different face models. The deformation is based on labels and allows transferring specific facial features between the generic rig and face models. High quality physics-based animation is achieved by combining different deformation methods with our labeling system, which adapts muscles and skeletons from a generic rig to individual face models. We describe how to find the correspondence of the main attributes of the generic rig, transfer them to different 3D face models and generate a sophisticated facial rig based on human anatomy. We show how to apply the same deformation parameters to different face models and obtain unique expressions. Our goal is to ease the char- acter setup process and provide digital artists with a tool that allows manipulating models as if they were using a puppet. We end with different examples that show the strength of our proposal. 1 Introduction Facial animation is related to the interaction of muscles and skeletons be- neath the skin. It is the key element to transmit individuality and per- sonality to a character in films and video games. Therefore, to obtain physically-based animations, it is crucial to develop systems that simulate the anatomical structure of the face. Recent advances in facial synthesis show an increased interest in physics-based approaches [23] [15] [22]. Today, to animate a character, an experienced CG artist has to model each facial rig by hand, making it impossible to re-use the same rig in different facial models. The task is further complicated when a minor artistic change on the facial topology leads to the restarting of the rigging process from scratch. This creates a bottleneck in any CG production and leads to the research of automated methods to accelerate the process [14]. Modeling and animation of deformable objects have been applied to dif- ferent fields [1] [3]. Noh et al. [17] proposed several methods for transferring animations between different face models. The surface correspondence is obtained by specifying the corresponding point pairs on the models. Pighin et al. [7] presented a method to interactively mark corresponding facial fea- tures in several photographs of an individual, to deform a generic face model using radial basis function. Sederberg and Parry [20] first introduced Free- Form Deformation (FFD) in 1986; the method does not require setting the 1