Internal Statistics of a Single Natural Image
Maria
Zontak, Michal Irani
This webpage presents the paper "Internal Statistics of
a Single Natural Image" (CVPR 2011).
Paper [PDF]
Abstract
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 parametricly 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 images.
(iii)
Internal statistics often has stronger predictive power than external
statistics, indicating that it may potentially give rise to more
powerful image-specific priors.
This web page contains:
1. More
examples of External vs. Internal super-resolution (Sec. 4).
2. Elaborating
on the parametric approximation of the NN function (Sec. 2).