A machine learning approach for non-blind image deconvolution
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.
Update The performance of EPLL in the final CVPR paper (Fig. 5) is not the best possible with EPLL: We were able to improve its performance by tuning its hyper-parameter beta (Thanks to Libin Sun for pointing this out!). With tuning this parameter, EPLL is the third-best method in our experiments (see updated Fig. 5).
Square blur: Image from the best 5% results
Square blur: Image from the worst 5% results