Limits on super-resolution and how to break them
Baker, S.
Kanade, T.
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Sep 2002
Volume: 24,
Issue: 9
On page(s): 1167- 1183
ISSN: 0162-8828
References Cited: 53
CODEN: ITPIDJ
INSPEC Accession Number: 7377238
Digital Object Identifier: 10.1109/TPAMI.2002.1033210
Current Version Published: 2002-11-07
Abstract
Nearly all super-resolution algorithms are based on the
fundamental constraints that the super-resolution image should generate
low resolution input images when appropriately warped and down-sampled
to model the image formation process. (These reconstruction constraints
are normally combined with some form of smoothness prior to regularize
their solution.) We derive a sequence of analytical results which show
that the reconstruction constraints provide less and less useful
information as the magnification factor increases. We also validate
these results empirically and show that, for large enough magnification
factors, any smoothness prior leads to overly smooth results with very
little high-frequency content. Next, we propose a super-resolution
algorithm that uses a different kind of constraint in addition to the
reconstruction constraints. The algorithm attempts to recognize local
features in the low-resolution images and then enhances their resolution
in an appropriate manner. We call such a super-resolution algorithm a
hallucination or reconstruction algorithm. We tried our hallucination
algorithm on two different data sets, frontal images of faces and
printed Roman text. We obtained significantly better results than
existing reconstruction-based algorithms, both qualitatively and in
terms of RMS pixel error
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
