RI | Publications | Limits on Super-Resolution and How to Break Them

Text only version of this site

Limits on Super-Resolution and How to Break Them
S. Baker and T. Kanade
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, September, 2002, pp. 1167 - 1183.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Download [Help]

Adobe portable document format (pdf) [998 KB]
Compressed postscript (ps.gz) [1892 KB]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the 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.) In the first part of this paper, 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 (however many low resolution input images are used.) In the second part of this paper, 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 recogstruction algorithm. We tried our hallucination algorithm on two different datasets, 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.

Notes

Sponsor: US DOD
Grant ID: MDA-904-98-C-A915

Associated center: VASC
Associated lab/group: Face Group
Associated projects: Photometric Limits on Computer Vision, Image Enhancement for Faces, and Hallucinating Faces

Number of pages: 17

Note: (To Appear)

Text Reference

S. Baker and T. Kanade, "Limits on Super-Resolution and How to Break Them," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, September, 2002, pp. 1167 - 1183.

BibTeX Reference

@article{Baker_2002_3909,
   author = "Simon Baker and Takeo Kanade",
   title = "Limits on Super-Resolution and How to Break Them",
   journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
   month = "September",
   year = "2002",
   volume = "24",
   number = "9",
   pages = "1167 - 1183",
   note = "(To Appear)"
}