The design of physiological motion compensation systems for robotic-assisted cardiac Minimally Invasive Surgery (MIS) is a challeng- ing research topic. In this domain, vision-based techniques have proven to be a practical way to retrieve the motion of the beating heart. However due to the complexity of the heart motion and its surface characteristics, efficient tracking is still a complicated task. In this paper, we propose an algorithm for tracking the 3D motion of the beating heart, based on a Thin-Plate Splines (TPS) parametric model. The novelty of our approach lies in that no explicit matching between the stereo camera images is re- quired and consequently no intermediate steps such as rectification are needed. Experiments conducted on ex-vivo and in-vivo tissue show the effectiveness of the proposed algorithm for tracking surfaces undergoing complex deformations.