Fast Image Deblurring Based On the Lightweight Progressive Residual Network

YANG Aiping; LI Leilei; ZHANG Bing; HE Yuqing

doi:10.11999/JEIT210298

Volume 44 Issue 5

May 2022

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2022 > 44(5): 1674-1682

YANG Aiping, LI Leilei, ZHANG Bing, HE Yuqing. Fast Image Deblurring Based On the Lightweight Progressive Residual Network[J]. Journal of Electronics & Information Technology, 2022, 44(5): 1674-1682. doi: 10.11999/JEIT210298

Citation:

YANG Aiping, LI Leilei, ZHANG Bing, HE Yuqing. Fast Image Deblurring Based On the Lightweight Progressive Residual Network[J]. Journal of Electronics & Information Technology, 2022, 44(5): 1674-1682. doi: 10.11999/JEIT210298

Citation:

PDF( 12424 KB)

Fast Image Deblurring Based On the Lightweight Progressive Residual Network

doi: 10.11999/JEIT210298

School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

Funds: The National Natural Science Foundation of China (62071323, 61632018, 61771329)

Received Date: 2021-04-13
Accepted Date: 2021-11-14
Rev Recd Date: 2021-11-14

Available Online: 2021-12-22

Publish Date: 2022-05-25

Abstract

Abstract

Although deep learning-based methods show their superiority in the field of single image deblurring, it is difficult to be applied to practice for requiring more computing resources and memory consumption as network deepens. In this work, a lightweight and fast progressive residual network for image deburring is proposed. The network takes shallow residual network as basic model to make full use of the local feature information and strengthen the information flow during back propagation. By reusing the residual network recursively in subsequent several stages and sharing parameters, the network model can be greatly simplified and the parameters can be reduced. To improve the reconstruction performance of the network, the feature recalibration module is applied to feature fusion. The channel attention mechanism is applied to integrate input image and output feature map of each residual network, and then the spatial information of feature map is selected adaptively to achieve better feature reconstruction. Experimental results show that the proposed model has fast running speed with a small number of parameters, which is much better than the existing algorithms, and can produce quite promising results for the removal of spatial-invariant blurring.
- Fast image deblurring,
- Lightweight residual network,
- Progressive,
- Feature recalibration

FullText(HTML)

References(23)

References

[1]	LIANG Wang, HANG Yaping, LUO Siwei, et al. Deblurring Gaussian-blur images: A preprocessing for rail head surface defect detection[C]. 2011 IEEE International Conference on Service Operations, Logistics and Informatics, Beijing, China, 2011: 451–456.
[2]	MCCARTHY D M J, CHANDLER J H, and PALMERI A. Monitoring dynamic structural tests using image deblurring techniques[J]. Key Engineering Materials, 2013, 569/570: 932–939. doi: 10.4028/www.scientific.net/KEM.569-570.932
[3]	WANG Ge, SNYDER D L, O’SULLIVAN J A, et al. Iterative deblurring for CT metal artifact reduction[J]. IEEE Transactions on Medical Imaging, 1996, 15(5): 657–664. doi: 10.1109/42.538943
[4]	KUPYN O, BUDZAN V, MYKHAILYCH M, et al. DeblurGAN: Blind motion deblurring using conditional adversarial networks[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8183–8192.
[5]	PAN Jinshan, SUN Deqing, PFISTER H, et al. Blind image deblurring using dark channel prior[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1628–1636.
[6]	LI Xu, ZHENG Shicheng, and JIA Jiaya. Unnatural L0 sparse representation for natural image deblurring[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 1107–1114.
[7]	PAN Jinshan, HU Zhe, SU Zhixun, et al. Deblurring text images via L0-regularized intensity and gradient prior[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2901–2908.
[8]	ZHANG Hong, WU Yujie, ZHANG Lei, et al. Image deblurring using tri-segment intensity prior[J]. Neurocomputing, 2020, 398: 265–279. doi: 10.1016/j.neucom.2020.02.082
[9]	ZHANG Kai, ZUO Wangmeng, and ZHANG Lei. Learning a single convolutional super-resolution network for multiple degradations[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3262–3271.
[10]	VASU S, MALIGIREDDY V R, and RAJAGOPALAN A N. Non-blind deblurring: Handling kernel uncertainty with CNNs[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3272–3281.
[11]	SUN Jian, CAO Wenfei, XU Zongben, et al. Learning a convolutional neural network for non-uniform motion blur removal[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 769–777.
[12]	NAH S, KIM T H, and LEE K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 257–265.
[13]	JAIN V and SEUNG H S. Natural image denoising with convolutional networks[C]. The 21st International Conference on Neural Information Processing Systems, Vancouver, Canada, 2008: 769–776.
[14]	TAO Xin, GAO Hongyun, SHEN Xiaoyong, et al. Scale-recurrent network for deep image deblurring[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8174–8182.
[15]	ZHANG Jiawei, PAN Jinshan, REN J, et al. Dynamic scene deblurring using spatially variant recurrent neural networks[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 2521–2529.
[16]	GAO Hongyun, TAO Xin, SHEN Xiaoyong, et al. Dynamic scene deblurring with parameter selective sharing and nested skip connections[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 3843–3851.
[17]	KUPYN O, MARTYNIUK T, WU Junru, et al. DeblurGAN-v2: Deblurring (orders-of-magnitude) faster and better[C]. 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), 2019: 8877–8886.
[18]	SUIN M, PUROHIT K, and RAJAGOPALAN A N. Spatially-attentive patch-hierarchical network for adaptive motion deblurring[C]. 2020 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 3603–3612.
[19]	LIU Qiaohong, SUN Liping, LING Chen, et al. Nonblind image deblurring based on Bi-composition decomposition by local smoothness and nonlocal self-similarity priors[J]. IEEE Access, 2019, 7: 63954–63971. doi: 10.1109/ACCESS.2019.2915314
[20]	LIU R W, YIN Wei, XIONG Shengwu, et al. L0-regularized hybrid gradient sparsity priors for robust single-image blind deblurring[C]. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, 2018: 1348–1352.
[21]	LI Duo, HU Jie, WANG Changhu, et al. Involution: Inverting the inherence of convolution for visual recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition, online, 2021: 12321–12330.
[22]	BORJI A, CHENG Mingming, HOU Qibin, et al. Salient object detection: A survey[J]. Computational Visual Media, 2019, 5(2): 117–150. doi: 10.1007/s41095-019-0149-9
[23]	PANG Youwei, ZHAO Xiaoqi, ZHANG Lihe, et al. Multi-scale interactive network for salient object detection[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 9410–9419.