Limits of Learning-Based Superresolution Algorithms
Zhouchen Lin
Primary Author
Junfeng He
Additional Author
Xiaoou Tang
Additional Author
Chi-Keung Tang
Additional Author
mixed material
bibliography
Netherlands
Springer Netherlands
2008
monographic
Volume 80, Number 3
en
English
15p
International Journal of Computer Vision
Learning-based superresolution (SR) is a popular
SR technique that uses application dependent priors to infer
the missing details in low resolution images (LRIs). However,
their performance still deteriorates quickly when the
magnification factor is only moderately large. This leads us
to an important problem: “Do limits of learning-based SR algorithms
exist?” This paper is the first attempt to shed some
light on this problem when the SR algorithms are designed
for general natural images. We first define an expected risk
for the SR algorithms that is based on the root mean squared
error between the superresolved images and the ground truth
images. Then utilizing the statistics of general natural images,
we derive a closed form estimate of the lower bound
of the expected risk. The lower bound only involves the covariance
matrix and the mean vector of the high resolution
images (HRIs) and hence can be computed by sampling real
images.We also investigate the sufficient number of samples to guarantee an accurate estimate of the lower bound. By
computing the curve of the lower bound w.r.t. the magnification
factor, we could estimate the limits of learning-based
SR algorithms, at which the lower bound of the expected
risk exceeds a relatively large threshold.We perform experiments
to validate our theory. And based on our observations
we conjecture that the limits may be independent of the size
of either the LRIs or the HRIs.
09205691
Portal Perguruan Tinggi
EJ00033
My Library
44
2010-05-21 14:29:45
2010-05-21 14:30:19
machine generated