(a) Input Image (c) Exaggerated x2 (b) CorrectedFigure 1: An example of using our Non-Local Variations algorithm to automatically detect and visualize small deformations between repeating structures in a single image (a). Our method can be used to identify and correct these variations, thus producing an 'idealized' version of the image (b). Alternatively, our method can be used to exaggerate these variations (c). In the corrected output, the variability in the shape of the corn's kernels is reduced, and the misalignment of rows is corrected. In the exaggerated output, the subtle differences between the kernels and the row misalignment are highlighted. Photo courtesy of Giandomenico Pozz.
AbstractWe present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.