Abstract
We present a novel approach for online shrinkage functions learning in single image super-resolution. The proposed approach leverages the classical Wavelet Shrinkage denoising technique where a set of scalar shrinkage functions is applied to the wavelet coefficients of a noisy image. In the proposed approach, a unique set of learned shrinkage functions is applied to the overcomplete representation coefficients of the interpolated input image. The super-resolution image is reconstructed from the post-shrinkage coefficients. During the learning stage, the low-resolution input image is treated as a reference high-resolution image and a super-resolution reconstruction process is applied to a scaled-down version of it. The shapes of all shrinkage functions are jointly learned by solving a Least Squares optimization problem that minimizes the sum of squared errors between the reference image and its super-resolution approximation. Computer simulations demonstrate superior performance compared to state-of-the-art results.
Chapter PDF
Similar content being viewed by others
Keywords
- Sparse Representation
- Noisy Image
- Shrinkage Function
- Overcomplete Representation
- Image Degradation Model
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Yang, J., Wright, J., Ma, Y., Huang, T.: Image super-resolution as sparse representation of raw image patches. In: CVPR (2008)
Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation. Submitted to IEEE Trans. on Image Processing (2010)
Wang, J., Zhua, S., Gonga, Y.: Resolution enhancement based on learning the sparse association of image patches. Pattern Recognition Letters 31, 1–10 (2010)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Computer Graphics and Applications 22, 56–65 (2002)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV (2009)
Elad, M., Datsenko, D.: Example-based regularization deployed to super-resolution reconstruction of a single image. The Computer Journal 50, 1–16 (2007)
Guleryuz, O.G.: Predicting wavelet coefficients over edges using estimates based on nonlinear approximants. In: Proceedings of the Data Compression Conference (2004)
Mueller, N., Lu, Y., Do, M.N.: Image interpolation using multiscale geometric representations. In: SPIE Symposium on Electronic Imaging, San Jose (2007)
Hel-Or, Y., Shaked, D.: A discriminative approach for wavelet denoising. IEEE Trans. on Image Processing 17, 443–457 (2008)
Ruderman, D.L., Bialek, W.: Statistics of natural images: Scaling in the woods. Phys. Rev. Lett. 73, 814–817 (1994)
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)
Elad, M.: Why simple shrinkage is still relevant for redundant representations? IEEE Trans. on Information Theory 52, 5559–5569 (2006)
Donoho, D.L., Johnstone, I.M.: Ideal spatial adaptation by wavelet shrinkage. Biometrika 81, 425–455 (1994)
Donoho, D.L.: Denoising by soft thresholding. IEEE Trans. on Information Theory 41, 613–627 (1995)
Coifman, R.R., Donoho, D.L.: Translation invariant de-noising. In: Lecture Notes in Statistics: Wavelets and Statistics, pp. 125–150 (1995)
Ma, J., Plonka, G.: The curvelet transform. IEEE Signal Processing Magazine 27, 118–133 (2010)
Do, M.N., Vetterli, M.: The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans. on Image Processing 14, 2091–2106 (2005)
Guleryuz, O.G.: Nonlinear approximation based image recovery using adaptive sparse reconstructions and iterated denoising-part i: theory. IEEE Trans. on Image Processing 15, 539–554 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Adler, A., Hel-Or, Y., Elad, M. (2010). A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15552-9_45
Download citation
DOI: https://doi.org/10.1007/978-3-642-15552-9_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15551-2
Online ISBN: 978-3-642-15552-9
eBook Packages: Computer ScienceComputer Science (R0)