Skip to Main content Skip to Navigation
Conference papers

Learning a convolutional neural network for non-uniform motion blur removal

Jian Sun 1 Wenfei Cao 1 Zongben Xu 1 Jean Ponce 2, 3
3 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
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 de-blurring 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01250478
Contributor : Minsu Cho <>
Submitted on : Monday, January 4, 2016 - 7:15:45 PM
Last modification on : Tuesday, September 22, 2020 - 3:51:55 AM
Long-term archiving on: : Friday, April 15, 2016 - 4:21:28 PM

File

sun2015.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce. Learning a convolutional neural network for non-uniform motion blur removal. CVPR 2015 - IEEE Conference on Computer Vision and Pattern Recognition 2015, Jun 2015, Boston, United States. ⟨10.1109/CVPR.2015.7298677⟩. ⟨hal-01250478⟩

Share

Metrics

Record views

346

Files downloads

1639