Super-Resolution

Super-Resolution is a Matlab program with graphical user interface that implements several image registration and reconstruction algorithms for super-resolution imaging.

This program is distributed under the General Public Licence GPL, which is included in the GPL file with the code.

Download

If you use this code in your research and publications, please also put a reference to this paper. Thank you!
Matlab code: superresolution_v_2.0.zip (128 Kb)
Example data: image set 1 (176 Kb), image set 2 (2.4 Mb), image set 3 (67.2 Mb)

Tested Configurations

Matlab 7.2 on Windows XP
Matlab 7.4 on Mac

News

January 14, 2006: First version of our Super-Resolution application is available online!
February 2, 2006: Corrected a minor bug in the implementation of the registration algorithm by Keren et al.
June 30, 2006: Corrected a problem with the superresolution.fig file under Windows.
May 9, 2007: Version 2.0 of our Super-Resolution application is available! It contains more algorithms, and faster rotation estimation.

Comments and Remarks

superresolution@epfl.ch

Implemented Algorithms

Image Registration

• P. Vandewalle, S. Süsstrunk and M. Vetterli, A Frequency Domain Approach to Registration of Aliased Images with Application to Super-Resolution, EURASIP Journal on Applied Signal Processing (special issue on Super-resolution), Vol. 2006, pp. Article ID 71459, 14 pages, 2006.
  [detailed record] [bibtex]

  [reproducible paper]
• D. Keren, S. Peleg, and R. Brada, Image sequence enhancement using sub-pixel displacement, in Proceedings IEEE Conference on Computer Vision and Pattern Recognition, June 1988, pp. 742-746.
• L. Lucchese and G. M. Cortelazzo, A noise-robust frequency domain technique for estimating planar roto-translations, IEEE Transactions on Signal Processing, vol. 48, no. 6, pp. 1769-1786, June 2000.
• B. Marcel, M. Briot, and R. Murrieta, Calcul de Translation et Rotation par la Transformation de Fourier, Traitement du Signal, vol. 14, no. 2, pp. 135-149, 1997.

Image Reconstruction

• bicubic interpolation using Matlab's built-in griddata function.
• Papoulis and Gerchberg's POCS algorithm projecting successively onto space of known pixels and space of bandlimited images.
• Iterated back-projection. M. Irani and S. Peleg, Improving resolution by image registration, Graphical Models and Image Processing, 53:231-239, 1991.
• Robust super-resolution. A. Zomet, A. Rav-Acha, and S. Peleg, Robust Super-Resolution, Proceedings international conference on computer vision and pattern recognition (CVPR), 2001.
• POCS (Projection Onto Convex Sets).
• Normalized convolution. Tuan Q. Pham, Lucas J. van Vliet and Klamer Schutte, Robust Fusion of Irregularly Sampled Data Using Adaptive Normalized Convolution, EURASIP Journal on Applied Signal Processing, Vol. 2006, Article ID 83268, 12 pages, 2006.