2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
Jian Sun , Xi'an Jiaotong University, China
Wenfei Cao , Xi'an Jiaotong University, China
Zongben Xu , Xi'an Jiaotong University, China
Jean Ponce , École Normale Supérieure / PSL Research University, France
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.
J. Sun, Wenfei Cao, Zongben Xu and J. Ponce, "Learning a convolutional neural network for non-uniform motion blur removal," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 769-777.