The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Limits on super-resolution and how to break them
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Principles of Optics: 60th Anniversary Edition
Born, M., & Wolf, E. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108769914 · Cited by 26,251
The Laplacian pyramid as a compact image code
Burt, P., & Adelson, E. (1983) · IEEE Transactions on Communications · doi:10.1109/tcom.1983.1095851 · Cited by 6,077
Neural network-based face detection
Rowley, H. A., Baluja, S., & Kanade, T. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.655647 · Cited by 3,554
The design and use of steerable filters
Freeman, W. T., & Adelson, E. H. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.93808 · Cited by 2,942
Improving resolution by image registration
Irani, M., & Peleg, S. (1991) · CVGIP: Graphical Models and Image Processing · doi:10.1016/1049-9652(91)90045-l · Cited by 1,929
Freeman, W. T., Pasztor, E. C., & Carmichael, O. T. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026501619075 · Cited by 1,459
Limits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854852 · Cited by 1,184
Self-citationHierarchical model-based motion estimation
Bergen, J. R., Anandan, P., Hanna, K. J., & Hingorani, R. (1992) · Lecture Notes in Computer Science · doi:10.1007/3-540-55426-2_27 · Cited by 1,154
Elad, M., & Feuer, A. (1997) · IEEE Transactions on Image Processing · doi:10.1109/83.650118 · Cited by 1,035
Extraction of high-resolution frames from video sequences
Schultz, R. R., & Stevenson, R. L. (1996) · IEEE Transactions on Image Processing · doi:10.1109/83.503915 · Cited by 978
Joint MAP registration and high-resolution image estimation using a sequence of undersampled images
Hardie, R. C., Barnard, K. J., & Armstrong, E. E. (1997) · IEEE Transactions on Image Processing · doi:10.1109/83.650116 · Cited by 826
Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency
Irani, M., & Peleg, S. (1993) · Journal of Visual Communication and Image Representation · doi:10.1006/jvci.1993.1030 · Cited by 805
High-resolution image recovery from image-plane arrays, using convex projections
Stark, H., & Oskoui, P. (1989) · Journal of the Optical Society of America A · doi:10.1364/josaa.6.001715 · Cited by 734
(2000) · doi:10.1109/afgr.2000.840616 · Cited by 634
The FERET evaluation methodology for face-recognition algorithms
Phillips, P. J., Moon, H., Rauss, P., & Rizvi, S. A. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609311 · Cited by 590
Multiresolution sampling procedure for analysis and synthesis of texture images
De Bonet, J. S. (1997) · Proceedings of the 24th annual conference on Computer graphics and interactive techniques - SIGGRAPH '97 · doi:10.1145/258734.258882 · Cited by 570
A Bayesian approach to image expansion for improved definition
Schultz, R. R., & Stevenson, R. L. (1994) · IEEE Transactions on Image Processing · doi:10.1109/83.287017 · Cited by 535
Recursive reconstruction of high resolution image from noisy undersampled multiframes
Kim, S. P., Bose, N. K., & Valenzuela, H. M. (1990) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/29.56062 · Cited by 520
Fast filter transform for image processing
Burt, P. J. (1981) · Computer Graphics and Image Processing · doi:10.1016/0146-664x(81)90092-7 · Cited by 458
Image sequence enhancement using sub-pixel displacements
Keren, D., Peleg, S., & Brada, R. (2003) · Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1988.196317 · Cited by 352
Improved resolution from subpixel shifted pictures
Ur, H., & Gross, D. (1992) · CVGIP: Graphical Models and Image Processing · doi:10.1016/1049-9652(92)90065-6 · Cited by 291
Super-resolution reconstruction of image sequences
Elad, M., & Feuer, A. (1999) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.790425 · Cited by 254
Superresolution restoration of an image sequence: adaptive filtering approach
Elad, M., & Feuer, A. (1999) · IEEE Transactions on Image Processing · doi:10.1109/83.748893 · Cited by 222
Virtual bellows: constructing high quality stills from video
Mann, S., & Picard, R. W. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413336 · Cited by 202
Stereo matching with transparency and matting
Szeliski, R., & Golland, P. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1998.710766 · Cited by 144
Learning to identify and track faces in image sequences
Edwards, G. J., Taylor, C., & Cootes, T. F. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1998.670958 · Cited by 120
Baker, S., Nayar, S. K., & Murase, H. (1998) · International Journal of Computer Vision · doi:10.1023/a:1007901712605 · Cited by 118
Self-citationTexture recognition using a non-parametric multi-scale statistical model
Bonet, J. S. D., & Viola, P. A. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1998.698672 · Cited by 88
The quotient image: Class based recognition and synthesis under varying illumination conditions
Raviv, T. R., & Shashua, A. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1999.784968 · Cited by 78
Bayesian super-resolved surface reconstruction from images
Smelyanskiy, V., Cheeseman, P. C., Maluf, D. A., & Morris, R. D. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855843 · Cited by 33
Cited by
NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study
Agustsson, E., & Timofte, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.150 · Cited by 4,295
Super-resolution from a single image
Glasner, D., Bagon, S., & Irani, M. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459271 · Cited by 1,889
Sparse Representation for Color Image Restoration
Mairal, J., Elad, M., & Sapiro, G. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.911828 · Cited by 1,716
Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior
Kim, K. I., & Kwon, Y. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.25 · Cited by 956
Image super-resolution using gradient profile prior
Sun, J., Xu, Z., & Shum, H.-Y. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587659 · Cited by 916
Metadata
- Authors
- Baker, S., & Kanade, T.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2002-09
- Volume
- 24
- Issue
- 9
- Pages
- 1167-1183
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2140257560
- Cited by
- 1,205
- References
- 30
- FWCI
- 35.20
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.