research-article

Blind Motion Deblurring Based on Generative Adversarial Networks

Authors:

Xuewei LiAuthors Info & Claims

VSIP '19: Proceedings of the 2019 International Conference on Video, Signal and Image Processing

Pages 15 - 20

https://doi.org/10.1145/3369318.3369331

Published: 10 January 2020 Publication History

Abstract

In the past two years, GAN (Generative Adversarial Networks) has emerged and been applied to the image deblurring problem, showing good results, especially in restoring high-frequency texture details of the image. However, there are very few papers on GAN-based image deblurring so far, and it is not ideal for the processing of edge features. In this paper, an end-to-end blind image motion deblurring algorithm based on GAN is proposed. In the pixel domain, we use the weighted sum of cross entropy and L1 loss as the loss function. In the feature domain, the weighted sum of the features extracted by VGG and DenseNet is used to calculate the loss. And we add "deconvolution + PixelShuffle" module to the network. Experiments show that our method achieves the excellent performance in terms of PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index), simultaneously eliminates the checkerboards effectively.

References

[1]

O. V. Michailovich and D. Adam, "A novel approach to the 2-D blind deconvolution problem in medical ultrasound," in IEEE Transactions on Medical Imaging, vol. 24, no. 1, pp. 86--104, Jan. 2005.

[2]

L. Ma, L. Moisan, J. Yu and T. Zeng, "A Dictionary Learning Approach for Poisson Image Deblurring," in IEEE Transactions on Medical Imaging, vol. 32, no. 7, pp. 1277--1289, July 2013.

[3]

P. Svoboda, M. Hradiš, L. Maršík and P. Zemcík, "CNN for license plate motion deblurring," 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 2016, pp. 3832--3836.

[4]

S. Zheng, L. Xu and J. Jia, "Forward Motion Deblurring," 2013 IEEE International Conference on Computer Vision, Sydney, NSW, 2013, pp. 1465--1472.

Digital Library

[5]

J. Ma and F. Le Dimet, "Deblurring From Highly Incomplete Measurements for Remote Sensing," in IEEE Transactions on Geoscience and Remote Sensing, vol. 47, no. 3, pp. 792--802, March 2009.

[6]

S. Dai, M. Yang, Y. Wu and A. K. Katsaggelos, "Tracking Motion-Blurred Targets in Video," 2006 International Conference on Image Processing, Atlanta, GA, 2006, pp. 2389--2392.

[7]

C. J. Schuler, H. C. Burger, S. Harmeling and B. Schölkopf, "A Machine Learning Approach for Non-blind Image Deconvolution," 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, 2013, pp. 1067--1074.

Digital Library

[8]

S. Cho, Jue Wang and S. Lee, "Handling outliers in non-blind image deconvolution," 2011 International Conference on Computer Vision, Barcelona, 2011, pp. 495--502.

Digital Library

[9]

F. Palsson, J. R. Sveinsson, M. O. Ulfarsson and J. A. Benediktsson, "MTF-Based Deblurring Using a Wiener Filter for CS and MRA Pansharpening Methods," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, no. 6, pp. 2255--2269, June 2016.

[10]

Fergus, Rob. "Removing Camera Shake from a Single Photograph." Acm Transactions on Graphics 25.3(2006):787--794.

Digital Library

[11]

N. Joshi, C. L. Zitnick, R. Szeliski and D. J. Kriegman, "Image deblurring and denoising using color priors," 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 2009, pp. 1550--1557.

[12]

Hui-Yu Huang and Wei-Chang Tsai, "Motion deblurring from a single photograph based on kernel estimation," 2013 9th International Conference on Information, Communications & Signal Processing, Tainan, 2013, pp. 1--5.

[13]

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, 2015, pp. 769--777.

[14]

Goodfellow, I. J., et al. (2014) Generative Adversarial Networks. ArXiv e-prints.

[15]

C. Ledig et al., "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 105--114.

[16]

H. Zhang et al., "StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 5908--5916.

[17]

Y. Zhang, Y. Xiang and L. Bai, "Generative Adversarial Network for Deblurring of Remote Sensing Image," 2018 26th International Conference on Geoinformatics, Kunming, 2018, pp. 1--4.

[18]

O. Kupyn, V. Budzan, M. Mykhailych, D. Mishkin and J. Matas, "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 8183--8192.

[19]

K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 770--778.

[20]

W. Shi et al., "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 1874--1883.

[21]

J. Lin, Y. Xia, T. Qin, Z. Chen and T. Liu, "Conditional Image-to-Image Translation," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 5524--5532.

[22]

I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville. Improved Training of Wasserstein GANs. Arxiv e-prints, Mar 2017. 1, 3, 4, 5

[23]

M. Arjovsky, S. Chintala, and L. bottou. Wasserstein GAN. Arxiv e-prints, Jan. 2017.

[24]

J. Johnson, A. Alaphi, and L. Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In European Conference on Computer Vision, 2016.

[25]

K. Simonyan and A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. Arxiv e-prints, Sept. 2014.

[26]

G. Huang, Z. Liu, L. v. d. Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 2261--2269.

[27]

J. Deng, W. Dong, R. Socher, L. Li, Kai Li and Li Fei-Fei, "ImageNet: A large-scale hierarchical image database," 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 2009, pp. 248--255.

[28]

S. Nah, T. H. Kim and K. M. Lee, "Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 257--265.

Cited By

Liang ZYang BXiao H(2020)Using Motion Deblurring Algorithm to Improve Vehicle Recognition via DeblurGAN2020 International Conference on Virtual Reality and Intelligent Systems (ICVRIS)10.1109/ICVRIS51417.2020.00122(486-489)Online publication date: Jul-2020
https://doi.org/10.1109/ICVRIS51417.2020.00122

Index Terms

Blind Motion Deblurring Based on Generative Adversarial Networks
1. Computing methodologies
  1. Computer graphics
    1. Image manipulation
      1. Image processing

Recommendations

BIDGAN: Blind Image Deblurring with Improved CycleGAN and Frequency Filtering
Intelligent Computing Theories and Application
Abstract
The details of images can be severely impaired when they are captured in motion . To overcome such a blind image deblurring problem, we propose a deblurring method based on improved CycleGAN. This method can remarkably improve the definition of ...
Blind motion deblurring using multiple images

Recovery of degraded images due to motion blurring is a challenging problem in digital imaging. Most existing techniques on blind deblurring are not capable of removing complex motion blurring from the blurred images of complex structures. One promising ...
Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks
ICDSP '21: Proceedings of the 2021 5th International Conference on Digital Signal Processing

Low-quality face image restoration is a popular research direction in today's computer vision field. It can be used as a pre-work for tasks such as face detection and face recognition. At present, there is a lot of work to solve the problem of low-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

VSIP '19: Proceedings of the 2019 International Conference on Video, Signal and Image Processing

October 2019

135 pages

ISBN:9781450371483

DOI:10.1145/3369318

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

UNAM: Universidad Nacional Autonoma de Mexico
Wuhan Univ.: Wuhan University, China
NWPU: Northwestern Polytechnical University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 January 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

VSIP 2019

VSIP 2019: 2019 International Conference on Video, Signal and Image Processing

October 29 - 31, 2019

Wuhan, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
119
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Liang ZYang BXiao H(2020)Using Motion Deblurring Algorithm to Improve Vehicle Recognition via DeblurGAN2020 International Conference on Virtual Reality and Intelligent Systems (ICVRIS)10.1109/ICVRIS51417.2020.00122(486-489)Online publication date: Jul-2020
https://doi.org/10.1109/ICVRIS51417.2020.00122

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents