Real time magnetic resonance imaging (MRI) is rapidly gaining importance in interventional therapies. An accurate motion estimation is required for mobile targets, and can be conveniently addressed using an image registration algorithm. Since the adaptation of the control parameters of the algorithm depends on the application (targeted organ, location of the tumor, slice orientation, ...), typically an individual calibration is required. However, the assessment of the estimated motion accuracy is difficult since the real target motion is unknown. In this paper, existing criteria based only on anatomical image similarity are demonstrated to be inadequate. A new criterion is introduced, which is based on the local magnetic field distribution. The proposed criterion was used to assess, during a preparative calibration step, the optimal configuration of an image registration algorithm derived from the Horn and Schunck method. The accuracy of the proposed method was evaluated in a moving phantom experiment, which allows the comparison with the known motion pattern and to established criteria based on anatomical images. The usefulness of the method for the calibration of optical-flow based algorithms was also demonstrated in-vivo under conditions similar to thermo-ablation for the abdomen of twelve volunteers. In average over all volunteers, a resulting displacement error of 1.5 mm was obtained (largest observed error equal to 4-5 mm) using a criterion based on anatomical image similarity. A better average accuracy of 1 mm was achieved using the proposed criterion (largest observed error equal to 2 mm). In both kidney and liver, the proposed criterion was shown to provide motion field accuracy in the range of the best achievable.< Réduire