[1]LIN Zhenxian,ZHANG Mengkai,WU Chengmao.Image restoration with residual dense network[J].CAAI Transactions on Intelligent Systems,2021,16(3):442-448.[doi:10.11992/tis.201912002]
Copy

Image restoration with residual dense network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 16 Number of periods: 2021 3 Page number: 442-448 Column: 学术论文—机器感知与模式识别 Public date: 2021-05-05
Title:
Image restoration with residual dense network
Author(s):
LIN Zhenxian1;  ZHANG Mengkai2;  WU Chengmao3
1. School of Science, Xi’an University of Post and Telecommunications, Xi’an 710121, China;
2. School of Communication and Information Engineering, Xi’an University of Post and Telecommunications, Xi’an 710121, China;
3. School of Electronic Engineering, Xi’an University of Post and Telecommunications, Xi’an 710121, China
Keywords:
image processing; motion pictures; image denoising; image restoration; deep learning; network model; network architecture; convolutional neural network
CLC:
TP183
DOI:
10.11992/tis.201912002
Abstract:
Aiming at the problem of motion blur caused by object motion or camera shake in the image generation process, an image restoration method based on the residual dense network is proposed. An adversarial network structure is used in the method, taking the residual dense network as the generator and fusing different levels of features in a long-short connection to generate restored images. The deep convolution network acts as the discriminator to identify the authenticities of images, training the network performance in adversarial between the generator and discriminator. The proposed method combines the adversarial and content losses to improve the effectiveness of network restoration. This study demonstrates the restoration of an input blur image in an end-to-end way without estimating the blur kernel. Experiments show that the proposed method results in a better restoration effect.
References:
[1] 程俊廷, 左旺孟. 快速非均匀模糊图像的盲复原模型[J]. 黑龙江科技大学学报, 2017, 27(2):196-199
CHENG Junting, ZUO Wangmeng. Fast blind deblurring models for restoration of non-uniform blur images[J]. Journal of Heilongjiang University of Science and Technology, 2017, 27(2):196-199
[2] BANHAM M R, KATSAGGELOS A K. Digital image restoration[J]. IEEE signal processing magazine, 1997, 14(2):24-41.
[3] ZHOU Y T, CHELLAPPA R, VAID A, et al. Image restoration using a neural network[J]. IEEE transactions on acoustics, speech, and signal processing, 1988, 36(7):1141-1151.
[4] JAIN V, SEUNG S. Natural image denoising with convolutional networks[C]//Advances in Neural Information Processing Systems. Vancouver, Canada, 2009:769-776.
[5] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:2261-2269.
[6] ZHANG Kai, ZUO Wangmeng, CHEN Yunjin, et al. Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J]. IEEE transactions on image processing, 2017, 26(7):3142-3155.
[7] LIU Ding, WEN Bihan, FAN Yuchen, et al. Non-local recurrent network for image restoration[C]//32nd Conference on Neural Information Processing Systems. Montréal, Canada, 2018:1673-1682.
[8] GUO Shi, YAN Zifei, ZHANG Kai, et al. Toward convolutional blind denoising of real photographs[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019:1712-1722.
[9] CHA S, MOON T. Fully convolutional pixel adaptive image denoiser[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South), 2019:4159-4168.
[10] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada, 2014:2672-2680.
[11] KUPYN O, BUDZAN V, MYKHAILYCH M, et al. DeblurGAN:blind motion deblurring using conditional adversarial networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:8183-8192.
[12] WANG M, LI H, LI F. Generative adversarial network based on resnet for conditional image restoration[EB/OL].[2021?06?07] https://arxiv.org/abs/1707.04881.
[13] ZHOU H, SUN J, YACOOB Y, et al. Label denoising adversarial network (LDAN) for inverse lighting of faces[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:6238-6247.
[14] ZHANG Yulun, TIAN Yapeng, KONG Yu, et al. Residual dense network for image super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:2472-2481.
[15] SAJJADI M S M, SCH?LKOPF B, HIRSCH M. EnhanceNet:single image super-resolution through automated texture synthesis[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy, 2017:4501-4510.
[16] ADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL].[2021?06?07] https://arxiv.org/abs/1511.06434.
[17] ZHAO Hang, GALLO O, FROSIO I, et al. Loss functions for image restoration with neural networks[J]. IEEE transactions on computational imaging, 2017, 3(1):47-57.
[18] WHYTE O, SIVIC J, ZISSERMAN A, et al. Non-uniform deblurring for shaken images[J]. International journal of computer vision, 2012, 98(2):168-186.
[19] NAH S, KIM T H, LEE K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:257-265.
[20] BENGIO Y, LOURADOUR J, COLLOBERT R, et al. Curriculum learning[C]//Proceedings of the 26th Annual International Conference on Machine Learning. Montreal, Canada, 2009:41-48.
[21] 佟雨兵, 张其善, 祁云平. 基于PSNR与SSIM联合的图像质量评价模型[J]. 中国图象图形学报, 2006, 11(12):1758-1763
TONG Yubing, ZHANG Qishan, QI Yunping. Image quality assessing by combining PSNR with SSIM[J]. Journal of image and graphics, 2006, 11(12):1758-1763
[22] WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE transactions on image processing, 2004, 13(4):600-612.
[23] TAO Xin, GAO Hongyun, SHEN Xiaoyong, et al. Scale-recurrent network for deep image deblurring[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:8174-8182.
Similar References:

Memo

-

Last Update: 2021-06-25

Copyright © CAAI Transactions on Intelligent Systems