In some estimation tasks the precision can be increased by applying different models. E.g. it is known that airplanes can be tracked more precisely when different models for different maneuvers as flying straight or curves are used. Usually, something like the interacting multiple model filter (IMM) is used.

In the case of a single model the "online" algorithm is the Extended Kalman Filter. If the data can be processed offline a bundle adjuster/batch estimator/least square optimizer as ceres can be used which yields better results since it adjusts the complete dataset at once. It can handle the nonlinearities better.

Is there any algorithm which does the same for multiple model problems ? Something like a gold standard which should almost always yield the best results ?