Spectral methods such as the improved Fourier Mellin Invariant (iFMI) transform have proved to be faster, more robust
and accurate than feature based methods on image registration. However, iFMI is restricted to work only when the camera moves in 2D space and has not been applied on omni-cameras images so far. In this work, we extend the iFMI method and apply a motion model to estimate an omnicamera’s pose when it moves in 3D space. In the experiment section, we compare the extended iFMI method against ORB and AKAZE feature based approaches on three datasets, showing different types of environments: office, lawn and urban scenery (MPI-omni dataset). The results show that our method reduces the error of the camera pose estimation two to
three times with respect to the feature registration techniques, while offering lower processing times.