Title :
A Machine Learning Approach for Non-blind Image Deconvolution
Author :
Schuler, Christian J. ; Burger, Harold Christopher ; Harmeling, Stefan ; Scholkopf, Bernhard
Author_Institution :
Max Planck Inst. for Intell. Syst., Tubingen, Germany
Abstract :
Image deconvolution is the ill-posed problem of recovering a sharp image, given a blurry one generated by a convolution. In this work, we deal with space-invariant non-blind deconvolution. Currently, the most successful methods involve a regularized inversion of the blur in Fourier domain as a first step. This step amplifies and colors the noise, and corrupts the image information. In a second (and arguably more difficult) step, one then needs to remove the colored noise, typically using a cleverly engineered algorithm. However, the methods based on this two-step approach do not properly address the fact that the image information has been corrupted. In this work, we also rely on a two-step procedure, but learn the second step on a large dataset of natural images, using a neural network. We will show that this approach outperforms the current state-of-the-art on a large dataset of artificially blurred images. We demonstrate the practical applicability of our method in a real-world example with photographic out-of-focus blur.
Keywords :
Fourier transforms; convolution; deconvolution; image denoising; image restoration; learning (artificial intelligence); neural nets; Fourier domain; blurry image; colored noise removal; ill-posed problem; image convolution; image information; machine learning approach; natural image dataset; neural network; photographic out-of-focus blur; regularized blur inversion; sharp image recovery; space-invariant nonblind image deconvolution; two-step procedure; Colored noise; Deconvolution; Kernel; Neural networks; Noise reduction; Training; deblurring; deconvolution; learning; neural networks;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.142