Carnegie Mellon University
Limits on Super-Resolution and How to Break Them

Simon Baker and Takeo Kanade
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, pp. 1167 - 1183, September, 2002.

  • Adobe portable document format (pdf) (998KB)
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.

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.

Super-resolution, analysis of reconstructionconstraints, learning, faces, text, hallucination, recogstruction.

Sponsor: US DOD
Grant ID: MDA-904-98-C-A915
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Associated Lab(s) / Group(s): Face Group
Associated Project(s): Photometric Limits on Computer Vision, Image Enhancement for Faces, Hallucinating Faces
Number of pages: 17
Note: (To Appear)

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

BibTeX Reference
   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",
   pages = "1167 - 1183",
   month = "September",
   year = "2002",
   volume = "24",
   number = "9",
   Notes = "(To Appear)"