Maria Zontak (CS & Applied Mathematics, Weizmann Institute of Science)
Tuesday, 6.12.2011, 11:30
Statistics of 'natural images' provides useful priors for solving
under-constrained problems in Computer Vision. Such statistics is usually
obtained from large collections of natural images. We claim that the
substantial internal data redundancy within a single natural image (e.g.,
recurrence of small image patches), gives rise to powerful internal
statistics, obtained directly from the image itself. While internal patch
recurrence has been used in various applications, we provide a parametric
quantification of this property. We show that the likelihood of an image
patch to recur at another image location can be expressed parametrically as
a function of the spatial distance from the patch, and its gradient content.
This "internal parametric prior" is used to improve existing algorithms that
rely on patch recurrence.
Moreover, we show that internal image-specific statistics is often more
powerful than general external statistics, giving rise to more powerful
image-specific priors. In particular:
(i) Patches tend to recur much more frequently (densely) inside the same
image, than in any random external collection of natural images.
(ii) To find an equally good external representative patch for all the
patches of an image, requires an external database of hundreds of natural
(iii) Internal statistics often has stronger predictive power than external
statistics, indicating that it may potentially give rise to more powerful
*Joint work with Michal Irani.