Coordinate-descent super-resolution and registration for parametric global motion models

We present a method for simultaneously obtaining registration and super-resolution from a sequence of low resolution images, based on a coordinate-descent approach. The novelty of the algorithm resides on the registration step, which can be applied easily to any parametric global motion model. We prove the validity of the model with synthetic and real data experiments, being of special interest the good performance achieved in the difficult case of images registered under a projective transformation.

► A framework for simultaneously registering and obtaining a high resolution image from a sequence is described. ► Its novelty resides in its capability for handling complex parametric motions like homographies. ► The method is theoretically justified and convergence is studied. ► Synthetic and real world experiments are performed, proving the validity of the method.