Robust Parameterization and Computation of the Trifocal Tensor

This paper presents all algorithm for computing a maximum likelihood estimate (MLE) of the trifocal tensor. The input to the algorithm is three images of the same scene, and the output is the estimated tensor and corner and line feature matches across the three images that are consistent with this estimate. Particular novelties of the algorithm are the computation of a trifocal tensor from six point correspondences, and a parameterization of the trifocal tensor which enforces the constraints between the tensor elements. The algorithm uses techniques from robust statistics and is fully automatic. Results are presented for synthetic and real image triplets. The proposed parameterization is compared to other existing methods.