Edge-enhanced Generative Adversarial Network for Reconstruction of Compressed Image
Pages 608 - 617
Abstract
The images are often compressed to reduce storage usage or accelerate image transmission. However, the compression process always results in the loss of image details, such as edge details, which degrades the visual experience. Plenty of reconstruction methods have been proposed, but it is yet challenging to enhance edge details more precisely. In this paper, we propose a GAN-based image reconstruction architecture mainly for edge enhancement. Our model improves by cycleGAN; the model's input adds the extracted edge of the compressed image to promote generating more precise edge information. To further optimize the image edge details, we define a new edge loss function to improve the quality of the generated image. Lastly, we train and test the images from the CelebA dataset and the ACDC medical dataset. The experimental results show that the reconstructed images are clear under the high compression ratio and have more precise image edge details.
References
[1]
N. Ahn, B. Kang, and K. A. Sohn. 2018. Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network. (2018).999. A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration. SIAM Journal on Scientific Computing (1999).
[2]
C. Dong, Y. Deng, C. Loy, and X. Tang. 2015. Compression Artifacts Reduction by a Deep Convolutional Network. In 2015 IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society, Los Alamitos, CA, USA, 576--584. https://doi.org/10.1109/ICCV.2015.73
[3]
C. Dong, C. C. Loy, K. He, and X. Tang. 2016. Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans Pattern Anal Mach Intell 38, 2 (2016), 295--307.
[4]
M. A. T Figueiredo and J. M. N Leitao. 1997. Unsupervised image restoration and edge location using compoundGauss-Markov random fields and the MDL principle. IEEE Transactions on Image Processing 6, 8 (1997), P. 1089--1102.
[5]
Yiming Gao and Xiaoping Yang. 2019. A Cartoon-Texture Approach for JPEG/JPEG 2000 Decompression Based on TGV and Shearlet Trans-form. IEEE Transactions on Image Processing 28, 3 (2019), 1356--1365. https://doi.org/10.1109/TIP.2018.2877485
[6]
D. Glasner, S. Bagon, and M. Irani. 2009. Super-resolution from a single image. In IEEE International Conference on Computer Vision.
[7]
Shuhang Gu, Wangmeng Zuo, Qi Xie, Deyu Meng, Xiangchu Feng, and Lei Zhang. 2015. Convolutional Sparse Coding for Image Super-Resolution. In 2015 IEEE International Conference on Computer Vision (ICCV). 1823--1831. https://doi.org/10.1109/ICCV.2015.212
[8]
Y. Guo, J. Chen, J. Wang, Q. Chen, J. Cao, Z. Deng, Y. Xu, and M. Tan. 2020. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
[9]
Z. Kai, W. Zuo, Y. Chen, D Meng, and Z. Lei. 2016. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing 26, 7 (2016), 3142--3155.
[10]
J. Kim, J. K. Lee, and K. M. Lee. 2016. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. In IEEE Conference on Com-puter Vision Pattern Recognition.
[11]
J. Kim, J. K. Lee, and K. M. Lee. 2016. Deeply-Recursive Convolu-tional Network for Image Super-Resolution. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[12]
Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Jo-hannes Totz, Zehan Wang, and Wenzhe Shi. 2017. Photo-Realistic Sin-gle Image Super-Resolution Using a Generative Adversarial Network. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 105--114. https://doi.org/10.1109/CVPR.2017.19
[13]
R. Liu, S. Li, C. Hou, and G. Lei. 2018. Multiple Residual Learning Network for Single Image Super-Resolution. In 2018 IEEE Visual Com-munications and Image Processing (VCIP).
[14]
X. Liu, X. Wu, J. Zhou, and D. Zhao. 2015. Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain. In Computer Vision Pattern Recognition.
[15]
W. Shi, J. Caballero, F Huszár, J. Totz, and Z. Wang. 2016. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[16]
T. Tong, G. Li, X. Liu, and Q. Gao. 2017. Image Super-Resolution Using Dense Skip Connections. In IEEE International Conference on Computer Vision.
[17]
Ci Wang, Jun Zhou, and Shu Liu. 2013. Adaptive non-local means filter for image deblocking. Signal Processing: Image Communication 28, 5 (2013), 522--530. https://doi.org/10.1016/j.image.2013.01.006
[18]
W. R. Wu and A. Kundu. 1992. Image estimation using fast modified reduced update Kalman filter. IEEE Transactions on Signal Processing 40, 4 (1992), 915--926.
[19]
Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiachao Zhang, Jiantao Zhou, and Ce Zhu. 2020. Image Restoration Using Joint Patch-Group-Based Sparse Representation. IEEE Transactions on Image Processing 29 (2020), 7735--7750. https://doi.org/10.1109/TIP.2020.3005515
[20]
K. Zhang, X. Gao, D. Tao, and X. Li. 2012. Multi-scale dictionary for single image super-resolution. In IEEE Conference on Computer Vision Pattern Recognition.
[21]
Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adver-sarial Networks. In 2017 IEEE International Conference on Computer Vision (ICCV). 2242--2251. https://doi.org/10.1109/ICCV.2017.244
Index Terms
- Edge-enhanced Generative Adversarial Network for Reconstruction of Compressed Image
Recommendations
Semantic Map Based Image Compression via Conditional Generative Adversarial Network
Image and GraphicsAbstractRecently, deep learning methods have been applied for image compression and achieved promising results. For lossy image compression at low bit rate, the traditional compression algorithms usually introduce undesired compression artifacts, such as ...
A Method for Face Image Inpainting Based on Autoencoder and Generative Adversarial Network
Image and Video TechnologyEBcGAN: An Edge-Based Conditional Generative Adversarial Network for Image Fusion
Knowledge Management and Acquisition for Intelligent SystemsAbstractInfrared and visible image fusion aims to extract essential information and synthesize a single fused image containing both the salient target and texture details. Recent fusion techniques, including deep learning methods like auto-encoders, ...
Comments
Information & Contributors
Information
Published In
October 2021
1723 pages
ISBN:9781450384322
DOI:10.1145/3501409
Copyright © 2021 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]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 31 December 2021
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
EITCE 2021
EITCE 2021: 2021 5th International Conference on Electronic Information Technology and Computer Engineering
October 22 - 24, 2021
Xiamen, China
Acceptance Rates
EITCE '21 Paper Acceptance Rate 294 of 531 submissions, 55%;
Overall Acceptance Rate 508 of 972 submissions, 52%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 58Total Downloads
- Downloads (Last 12 months)8
- Downloads (Last 6 weeks)0
Reflects downloads up to 03 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in