Fully non-local super-resolution via spectral hashing

Super-resolution is the task of creating an high resolution image from a low resolution input sequence. To overcome the difficul- ties of fine image registration, several methods have been proposed exploiting the non-local intuition, i.e. any datapoint can contribute to the final result if it is relevant. These algorithms however limit in practice the search region for relevant points in order to lower the corresponding computational cost. Furthermore, they define the non-local relations in the high resolution space, where the true im- ages are unknown. In this work, we introduce the use of spectral hashing to effi- ciently compute fully non-local neighbors. We also restate the super- resolution functional using fixed weights in the low resolution space, allowing us to use resolution schemes that avoid many artifacts.