Channeling Mr. Potato head - Face super-resolution using semantic components

We present a novel approach to face super-resolution using information about semantic components. For each facial component, we seek a similar matching aligned component from a dictionary of training face images. During this process, we also consider the appropriate face pose and use information about people wearing glasses. We then blend the gradient and the high-frequency information of the best-matching high-resolution facial components along with glasses to the input image that has been up-scaled by an existing method. In this paper, we compare with several state-of-the-art methods and demonstrate improvements for multiple poses and expressions.