Abstract
Recurrence of small image patches across different scales of a natural image has been previously used for solving ill-posed problems (e.g., super- resolution from a single image). In this paper we show how this multi-scale prop- erty can also be used for “blind-deblurring”, namely, removal of an unknown blur from a blurry image. While patches repeat ‘as is’ across scales in a sharp natural image, this cross-scale recurrence signi ficantly diminishes in blurry images. We exploit these deviations from ideal patch recurrence as a cue for recovering the un- derlying (unknown) blur kernel. More speci fically, we look for the blur kernel k , such that if its effect is “undone” (if the blurry image is deconvolved with k), the patch similarity across scales of the image will be maximized. We report extensive experimental evaluations, which indicate that our approach compares favorably to state-of-the-art blind deblurring methods, and in particular, is more robust than them.