Motion Blur Kernel Estimation via Deep Learning

Xiangyu Xu; Jinshan Pan; Yu Jin Zhang; Ming Hsuan Yang

doi:10.1109/TIP.2017.2753658

Motion Blur Kernel Estimation via Deep Learning

Xiangyu Xu, Jinshan Pan, Yu Jin Zhang, Ming Hsuan Yang

College of Computing

Research output: Contribution to journal › Article › peer-review

102 Citations (Scopus)

Abstract

The success of the state-of-the-art deblurring methods mainly depends on the restoration of sharp edges in a coarse-to-fine kernel estimation process. In this paper, we propose to learn a deep convolutional neural network for extracting sharp edges from blurred images. Motivated by the success of the existing filtering-based deblurring methods, the proposed model consists of two stages: suppressing extraneous details and enhancing sharp edges. We show that the two-stage model simplifies the learning process and effectively restores sharp edges. Facilitated by the learned sharp edges, the proposed deblurring algorithm does not require any coarse-to-fine strategy or edge selection, thereby significantly simplifying kernel estimation and reducing computation load. Extensive experimental results on challenging blurry images demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of visual quality and run-time.

Original language	English
Article number	8039224
Pages (from-to)	194-205
Number of pages	12
Journal	IEEE Transactions on Image Processing
Volume	27
Issue number	1
DOIs	https://doi.org/10.1109/TIP.2017.2753658
Publication status	Published - 2018 Jan

Bibliographical note

Funding Information:
This work was supported in part by the NSF CAREER under Grant 1149783, in part by the NSF of China under Grant 61673234, Grant 61732007 and Grant U1636124, in part by the 973 Program of China under Grant 2014CB347600, in part by the NSF of Jiangsu Province under Grant BK20140058, in part by the National Key Research and Development Program of China under Grant 2016YFB1001001, and in part by gifts from Adobe and Nvidia. The work of X. Xu was supported by a scholarship from China Scholarship Council.

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Graphics and Computer-Aided Design

Access to Document

10.1109/TIP.2017.2753658

Cite this

@article{25d2c11797704b95b0273b0cd4ed77e2,

title = "Motion Blur Kernel Estimation via Deep Learning",

abstract = "The success of the state-of-the-art deblurring methods mainly depends on the restoration of sharp edges in a coarse-to-fine kernel estimation process. In this paper, we propose to learn a deep convolutional neural network for extracting sharp edges from blurred images. Motivated by the success of the existing filtering-based deblurring methods, the proposed model consists of two stages: suppressing extraneous details and enhancing sharp edges. We show that the two-stage model simplifies the learning process and effectively restores sharp edges. Facilitated by the learned sharp edges, the proposed deblurring algorithm does not require any coarse-to-fine strategy or edge selection, thereby significantly simplifying kernel estimation and reducing computation load. Extensive experimental results on challenging blurry images demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of visual quality and run-time.",

author = "Xiangyu Xu and Jinshan Pan and Zhang, {Yu Jin} and Yang, {Ming Hsuan}",

note = "Funding Information: This work was supported in part by the NSF CAREER under Grant 1149783, in part by the NSF of China under Grant 61673234, Grant 61732007 and Grant U1636124, in part by the 973 Program of China under Grant 2014CB347600, in part by the NSF of Jiangsu Province under Grant BK20140058, in part by the National Key Research and Development Program of China under Grant 2016YFB1001001, and in part by gifts from Adobe and Nvidia. The work of X. Xu was supported by a scholarship from China Scholarship Council. Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2018",

month = jan,

doi = "10.1109/TIP.2017.2753658",

language = "English",

volume = "27",

pages = "194--205",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Motion Blur Kernel Estimation via Deep Learning

AU - Xu, Xiangyu

AU - Pan, Jinshan

AU - Zhang, Yu Jin

AU - Yang, Ming Hsuan

N1 - Funding Information: This work was supported in part by the NSF CAREER under Grant 1149783, in part by the NSF of China under Grant 61673234, Grant 61732007 and Grant U1636124, in part by the 973 Program of China under Grant 2014CB347600, in part by the NSF of Jiangsu Province under Grant BK20140058, in part by the National Key Research and Development Program of China under Grant 2016YFB1001001, and in part by gifts from Adobe and Nvidia. The work of X. Xu was supported by a scholarship from China Scholarship Council. Publisher Copyright: © 2017 IEEE.

PY - 2018/1

Y1 - 2018/1

N2 - The success of the state-of-the-art deblurring methods mainly depends on the restoration of sharp edges in a coarse-to-fine kernel estimation process. In this paper, we propose to learn a deep convolutional neural network for extracting sharp edges from blurred images. Motivated by the success of the existing filtering-based deblurring methods, the proposed model consists of two stages: suppressing extraneous details and enhancing sharp edges. We show that the two-stage model simplifies the learning process and effectively restores sharp edges. Facilitated by the learned sharp edges, the proposed deblurring algorithm does not require any coarse-to-fine strategy or edge selection, thereby significantly simplifying kernel estimation and reducing computation load. Extensive experimental results on challenging blurry images demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of visual quality and run-time.

AB - The success of the state-of-the-art deblurring methods mainly depends on the restoration of sharp edges in a coarse-to-fine kernel estimation process. In this paper, we propose to learn a deep convolutional neural network for extracting sharp edges from blurred images. Motivated by the success of the existing filtering-based deblurring methods, the proposed model consists of two stages: suppressing extraneous details and enhancing sharp edges. We show that the two-stage model simplifies the learning process and effectively restores sharp edges. Facilitated by the learned sharp edges, the proposed deblurring algorithm does not require any coarse-to-fine strategy or edge selection, thereby significantly simplifying kernel estimation and reducing computation load. Extensive experimental results on challenging blurry images demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of visual quality and run-time.

UR - http://www.scopus.com/inward/record.url?scp=85030645947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030645947&partnerID=8YFLogxK

U2 - 10.1109/TIP.2017.2753658

DO - 10.1109/TIP.2017.2753658

M3 - Article

C2 - 28922121

AN - SCOPUS:85030645947

SN - 1057-7149

VL - 27

SP - 194

EP - 205

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

IS - 1

M1 - 8039224

ER -

Motion Blur Kernel Estimation via Deep Learning

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this