Strong Edge Extraction Network for Non-uniform Blind Motion Image Deblurring

被引：0
作者：
Huang Y.-N. [1 ,2 ]
Li W.-H. [1 ,2 ]
Cui J.-K. [1 ,2 ]
Gong W.-G. [1 ,2 ]
机构：
[1] Key Laboratory of Optoelectronic Technology & Systems Ministry of Education, Chongqing
[2] College of Optoelectronic Engineering S, Chongqing University, Chongqing
来源：
Li, Wei-Hong (weihongli@cqu.edu.cn); Li, Wei-Hong (weihongli@cqu.edu.cn) | 1600年 / Science Press卷 / 47期
关键词：
Blind image deblurring; Convolutional neural network; Gradient feature; Non-uniform motion blurry image; Strong edge extraction;
D O I：
10.16383/j.aas.c190654
中图分类号：
学科分类号：
摘要：
Although non-uniform motion image deblurring based on the deep learning has achieved better recovery effect, the most of the existing methods cannot recover the image edge well. In this paper, a strong edge extraction network (SEEN) is proposed for extracting the strong edges of the non-uniform motion blurry image to improve the quality of image deblurring. The designed SEEN is composed of two sub-networks, that is, SEEN-1 and SEEN-2. SEEN-1 is designed as a bilateral filter for extracting the edges of the image after filtering the image details. SEEN-2 is designed as an L0 smoothing filter for extracting strong edges of the blurry image. Meanwhile, we also combine the strong edge features map and the blurry features map for further using the strong edge features. Finally, some experiments are executed on GoPro dataset and the results demonstrate that the proposed network can better extract the strong edge of the non-uniform motion blurry image, and obtain good results in both quality of visual perception and quantitative measurement. Copyright © 2021 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：2637 / 2653
页数：16
相关论文
共 23 条
[1]  
Xu L, Jia J Y., Two-phase kernel estimation for robust motion deblurring, Proceedings of the 2010 European Conference on Computer Vision, pp. 157-170, (2010)
[2]  
Mesarovic V Z, Galatsanos N P., MAP and regularized constrained total least-squares image restoration, Proceedings of the 1st International Conference on Image Processing, pp. 177-181, (1994)
[3]  
Michael K N, Robert J P, Felipe P., A New Approach to Constrained Total Least Squares Image Restoration, Linear Algebra and its Applications, 316, 1-3, pp. 237-258, (2000)
[4]  
Li W H, Chen Y Q, Chen R, Gong W G, Zhao B X., Hybrid order l0-regularized blur kernel estimation model for image blind deblurring, Proceedings of the 2017 International Symposium on Neural Networks, pp. 239-247, (2017)
[5]  
Li W H, Chen R, Xu S W, Gong W G., Blind motion image deblurring using nonconvex higher-order total variation model, Journal of Electronic Imaging, 25, 5, (2016)
[6]  
Shen Z Y, Xu T F, Pan J S., Non-uniform Motion Deblurring with Kernel Grid Regularization, Signal Processing Image Communication, 62, pp. 1-15, (2018)
[7]  
Chakrabarti A., A neural approach to blind motion deblurring, Proceedings of the 2016 European Conference on Computer Vision, pp. 221-235, (2016)
[8]  
Xu X Y, Pan J S, Zhang Y J, Yang M H., Motion Blur Kernel Estimation via Deep Learning, IEEE Transactions on Image Processing, 27, 1, pp. 194-205, (2018)
[9]  
Xu L, Ren J S, Liu C, Jia J Y., Deep convolutional neural network for image deconvolution, Proceedings of the 2014 International Conference on Neural Information Processing Systems, pp. 1790-1798, (2014)
[10]  
Tao X, Gao H Y, Shen X Y, Wang J, Jia J Y., Scale-Recurrent network for deep image deblurring, Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8174-8182, (2018)
123