Single Image Deblurring with Adaptive Dictionary Learning


Zhe Hu1 Jia-Bin Huang1,2 Ming-Hsuan Yang1
1UC Merced                2UIUC

In Proc. of IEEE International Conference on Image Processing (ICIP 2010)

Abstract

We propose a motion deblurring algorithm that exploits sparsity constraints of image patches using one single frame. In our formulation, each image patch is encoded with sparse coefficients using an over-complete dictionary. The sparsity constraints facilitate recovering the latent image without solving an ill-posed deconvolution problem. In addition, the dictionary is learned and updated directly from one single frame without using additional images. The proposed method iteratively utilizes sparsity constraints to recover latent image, estimates the deblur kernel, and updates the dictionary directly from one single image. The final deblurred image is then recovered once the deblur kernel is estimated using our method. Experiments show that the proposed algorithm achieves favorable results against the state-of-the-art methods.

Paper and MATLAB code

The paper and MATLAB code can be found here. [PDF] [Poster] MATLAB code

More results

More comparison results can be found here. Downloads

BibTex

@inproceedings{hu_icip2010,
title = {Single image deblurring with adaptive dictionary learning},
author = {Zhe Hu and Jia-Bin Huang and Ming-Hsuan Yang},
journal = {Proc. IEEE International Conference on Image Processing (ICIP 2010)},
year = {2010},
pages = {1169-1172},
}