Abstract
A variety of super-resolution algorithms have been described in this book. Most of them are based on the same source of information however; that the super-resolution image should generate the lower resolution input images when appropriately warped and down-sampled to model image formation. (This information is usually incorporated into super-resolution algorithms in the form of reconstruction constraints which are frequently combined with a smoothness prior to regularize their solution.) In this final chapter, we first investigate how much extra information is actually added by having more than one image for super-resolution. In particular, we derive a sequence of analytical results which show that the reconstruction constraints provide far less useful information as the decimation ratio increases. We validate these results empirically and show that for large enough decimation ratios any smoothness prior leads to overly smooth results with very little high-frequency content however many (noiseless) low resolution input images are used. In the second half of this chapter, we propose a super-resolution algorithm which uses a completely different source of information, in addition to the reconstruction constraints. The algorithm recognizes local “features” in the low resolution images and then enhances their resolution in an appropriate manner, based on a collection of high and low-resolution training samples. We call such an algorithm a hallucination algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baker, S. and Kanade, T. (1999). Hallucinating faces. Technical Report CMU-RI-TR-99-32, The Robotics Institute, Carnegie Mellon University.
Baker, S. and Kanade, T. (2000.a). Hallucinating faces. In Proceedings of the Fourth International Conference on Automatic Face and Gesture Recognition, Grenoble, France.
Baker, S. and Kanade, T. (2000b). Limits on super-resolution and how to break them. In Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, South Carolina.
Baker, S., Nayar, S., and Murase, H. (1998). Parametric feature detection. International Journal of Computer Vision, 27(1):27–50.
Barbe, D. (1980). Charge-Coupled Devices. Springer-Verlag.
Bascle, B., Blake, A., and Zisserman, A. (1996). Motion deblurring and super-resolution from an image sequence. In Proceedings of the Fourth European Conference on Computer Vision, pages 573–581, Cambridge, England.
Bergen, J. R., Anandan, P., Hanna, K.J., and Hingorani, R. (1992). Hierarchical model-based motion estimation. In Proceedings of the Second European Conference on Computer Vision, pages 237–252, Santa Margherita Liguere, Italy.
Born, M. and Wolf, E. (1965). Principles of Optics. Permagon Press.
Burt, P. (1980). Fast filter transforms for image processing. Computer Graphics and Image Processing, 16: 20–51.
Burt, P. and Adelson, E. (1983). The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, 31(4):532–540.
Cheeseman, P., Kanefsky, B., Kraft, R., Stutz, J., and Hanson, R. (1994). Super-resolved surface reconstruction from multiple images. Technical Report FIA-94-12, NASA Ames Research Center, Moffet Field, CA.
Chiang, M.-C. and Boult, T. (1997). Local blur estimation and super-resolution. In Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition, pages 821–826, San Juan, Puerto Rico.
De Bonet, J. (1997). Multiresolution sampling procedure for analysis and synthesis of texture images. In Computer Graphics Proceedings, Annual Conference Series, (SIGGRAPH’ 97), pages 361–368.
Dellaert, F., Thrun, S., and Thorpe, C. (1998). Jacobian images of super-resolved texture maps for model-based motion estimation and tracking. In Proceedings of the Fourth Workshop on Applications of Computer Vision, pages 2–7, Princeton, NJ.
Edwards, G., Taylor, C., and Cootes, T. (1998). Learning to identify and track faces in image sequences. In Proceedings of the Third International Conference on Automatic Face and Gesture Recognition, pages 260–265, Nara, Japan.
Elad, M. and Feuer, A. (1997). Restoration of single super-resolution image from several blurred, noisy and down-sampled measured images. IEEE Transactions on Image Processing, 6(12):1646–58.
Elad, M. and Feuer, A. (1999). Super-resolution reconstruction of image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(9):817–834.
Freeman, W. and Pasztor, E. (1999). Learning low-level vision. In Proceedings of the Seventh International Conference on Computer Vision, Corfu, Greece.
Hardie, R., Barnard, K., and Armstrong, E. (1997). Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE Transactions on Image Processing, 6(12): 1621–1633.
Horn, B. (1996). Robot Vision. McGraw Hill.
Irani, M. and Peleg, S. (1991). Improving resolution by image restoration. Computer Vision, Graphics, and Image Processing, 53:231–239.
Peleg, S., Keren, D., and Schweitzer, L. (1987). Improving image resolution using subpixel motion. Pattern Recognition Letters, pages 223–226.
Philips, P., Moon, H., Rauss, P., and Rizvi, S. (1997). The FERET evaluation methodology for face-recognition algorithms. In CVPR’ 97.
Press, W., Teukolsky, S., Vetterling, W., and Flannery, B. (1992). Numerical Recipes in C. Cambridge University Press, second edition.
Qi, H. and Snyder, Q. (2000). Conditioning analysis of missing data estimation for large sensor arrays. In Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, South Carolina.
Riklin-Raviv, T. and Shashua, A. (1999). The Quotient image: Class based recognition and synthesis under varying illumination. In Proceedings of the 1999 Conference on Computer Vision and Pattern Recognition, pages 566–571, Fort Collins, CO.
Schultz, R. and Stevenson, R. (1994). A Bayseian approach to image expansion for improved definition. IEEE Transactions on Image Processing, 3(3):233–242.
Schultz, R. and Stevenson, R. (1996). Extraction of high resolution frames from video sequences. IEEE Transactions on Image Processing, 5(6): 996–1011.
Shekarforoush, H. (1999). Conditioning bounds for multi-frame super-resolution algorithms. Technical Report CAR-TR-912, Computer Vision Laboratory, Center for Automation Research, University of Maryland.
Shekarforoush, H., Berthod, M., Zerubia, J., and Werman, M. (1996). Sub-pixel bayesian estimation of albedo and height. International Journal of Computer Vision, 19(3):289–300.
Smelyanskiy V., Cheeseman P., Maluf D. and Morris, R. (2000). Bayesian super-resolved surface reconstruction from images. In Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, South Carolina.
Szeliski, R. and Golland, P. (1998). Stereo matching with transparency and matting. In Sixth International Conference on Computer Vision (ICCV’98), pages 517–524, Bombay.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Kluwer Academic Publishers
About this chapter
Cite this chapter
Baker, S., Kanade, T. (2002). Super-Resolution: Limits and Beyond. In: Chaudhuri, S. (eds) Super-Resolution Imaging. The International Series in Engineering and Computer Science, vol 632. Springer, Boston, MA. https://doi.org/10.1007/0-306-47004-7_10
Download citation
DOI: https://doi.org/10.1007/0-306-47004-7_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-7471-8
Online ISBN: 978-0-306-47004-2
eBook Packages: Springer Book Archive