Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal

TL;DR

This paper introduces a deep learning method that estimates and removes complex non-uniform motion blur from single images by predicting motion distributions, extending kernels with rotations, and applying a Markov random field for smoothness.

Contribution

The paper presents a novel CNN-based approach combined with image rotations and a Markov random field to effectively estimate and remove non-uniform motion blur, outperforming previous methods.

Findings

Effective estimation of complex non-uniform motion blur

Improved removal of motion blur in challenging scenarios

Outperforms previous approaches in experimental evaluations

Abstract

In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image. We propose a deep learning approach to predicting the probabilistic distribution of motion blur at the patch level using a convolutional neural network (CNN). We further extend the candidate set of motion kernels predicted by the CNN using carefully designed image rotations. A Markov random field model is then used to infer a dense non-uniform motion blur field enforcing motion smoothness. Finally, motion blur is removed by a non-uniform deblurring model using patch-level image prior. Experimental evaluations show that our approach can effectively estimate and remove complex non-uniform motion blur that is not handled well by previous approaches.