A shrinkage learning approach for single image super-resolution with overcomplete representations

Authors:
Amir Adler;Yacov Hel-Or;Michael Elad
Affiliations:
Computer Science Department, The Technion, Haifa, Israel;Efi Arazi School of Computer Science, The Interdisciplinary Center, Herzelia, Israel;Computer Science Department, The Technion, Haifa, Israel
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Year:
2010

Citing 10
Cited 4

Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Predicting Wavelet Coefficients Over Edges Using Estimates Based on Nonlinear Approximants

DCC '04 Proceedings of the Conference on Data Compression
Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image

The Computer Journal
Resolution enhancement based on learning the sparse association of image patches

Pattern Recognition Letters
Image super-resolution via sparse representation

IEEE Transactions on Image Processing
Why Simple Shrinkage Is Still Relevant for Redundant Representations?

IEEE Transactions on Information Theory
De-noising by soft-thresholding

IEEE Transactions on Information Theory
The contourlet transform: an efficient directional multiresolution image representation

IEEE Transactions on Image Processing
Nonlinear approximation based image recovery using adaptive sparse reconstructions and iterated denoising-part I: theory

IEEE Transactions on Image Processing
A Discriminative Approach for Wavelet Denoising

IEEE Transactions on Image Processing

High resolution segmentation of neuronal tissues from low depth-resolution EM imagery

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Singular value decomposition based fusion for super-resolution image reconstruction

Image Communication
Learned shrinkage approach for low-dose reconstruction in computed tomography

Journal of Biomedical Imaging
Single image super-resolution based on space structure learning

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

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 lowresolution 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.