In order to assist a surgeon by operating on a beating heart, visual stabilization makes the beating heart appear still to a surgeon by providing the current heart view as stationary and non-moving. In this way, the surgeon is not disturbed during an operation by a motion of the heart and can get an impression of performing conventional surgery. In contrast to existing methods for visual stabilization, the proposed approach involves a model-based transformation of image sequences provided by a camera system. This transformation incorporates the knowledge of physical characteristics of the heart in form of a mathematical model of the heart surface. Its main advantage is that the uncertainties of the model and measurements are considered. This occurs by estimating the parameters of the transformation. Furthermore, the quality of the visual stabilization is additionally improved by adapting the parameters of the underlying physical model. A performance of the proposed approach is evaluated in an experiment with a pressure-regulated artificial heart. In comparison to standard approaches, it provides superior results illustrating the hig ... mehrh quality of the visual stabilization.