Browse > Article
http://dx.doi.org/10.5909/JBE.2019.24.5.703

Deep Learning-based SISR (Single Image Super Resolution) Method using RDB (Residual Dense Block) and Wavelet Prediction Network  

NGUYEN, HUU DUNG (Department of Electronics Engineering, Korea Polytechnic University)
Kim, Eung-Tae (Department of Electronics Engineering, Korea Polytechnic University)
Publication Information
Journal of Broadcast Engineering / v.24, no.5, 2019 , pp. 703-712 More about this Journal
Abstract
Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.
Keywords
Super Resolution; Deep Learning; Wavelet Coefficient; Residual Dense Block; WaveletSRNet;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Y. Romano, M. Protter and M. Elad, "Single Image Interpolation Via Adaptive Nonlocal Sparsity-Based Modeling," in IEEE Trans. Image Process., 2014, https://doi.org/10.1109/tip.2014.2325774
2 W. Ye and K. Ma, "Convolutional Edge Diffusion for Fast Contrast-guided Image Interpolation," in IEEE Signal Process. Lett., 2016, https://doi.org/10.1109/lsp.2016.2571738
3 C. Ji, X. He, Y. Fu, Z. Liang, and L. Qing, ''An edge directed interpolation algorithm based on regularization,'' J. Electron. Inf. Technol., vol. 36, no. 2, pp. 293-297, 2014.
4 X. Gao and H. Xiong, "A hybrid wavelet convolution network with sparse-coding for image super-resolution," in ICIP, 2016, https://doi.org/10.1109/icip.2016.7532596
5 K. Zhang, X. Gao, D. Tao and X. Li, "Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression," in IEEE Trans. Image Process., 2012, https://doi.org/10.1109/tip.2012.2208977
6 V. Papyan and M. Elad, "Multi-Scale Patch-Based Image Restoration," in IEEE Trans. Image Process., 2016, https://doi.org/10.1109/tip.2015.2499698
7 C. Ren, X. He and T. Q. Nguyen, "Single Image Super-Resolution via Adaptive High-Dimensional Non-Local Total Variation and Adaptive Geometric Feature," in IEEE Trans. Image Process., 2017, https://doi.org/10.1109/tip.2016.2619265
8 S. Mallat, "Wavelets for a vision," in Proc. IEEE, 1996, https://doi.org/10.1109/5.488702
9 H. Huang, R. He, Z. Sun and T. Tan, "Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution," in ICCV, 2017, https://doi.org/10.1109/iccv.2017.187
10 T. Tong, G. Li, X. Liu and Q. Gao, "Image Super-Resolution Using Dense Skip Connections," in ICCV, 2017, https://doi.org/10.1109/iccv.2017.514
11 J. Bruna, P. Sprechmann, and Y. LeCun, "Super-Resolution with Deep Convolutional Sufficient Statistics," in ICLR, 2016, https://arxiv.org/abs/1511.05666
12 Y. Matsuo and S. Sakaida, "Super-resolution for 2K/8K television using wavelet-based image registration," in IEEE GlobalSIP, 2017, https://doi.org/10.1109/globalsip.2017.8308668
13 Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu, "Residual dense network for image super-resolution," in CVPR, 2018, https://doi.org/10.1109/cvpr.2018.00262
14 C. Dong, C. C. Loy, K. He, and X. Tang, "Learning a Deep Convolutional Network for Image Super-Resolution," in ECCV, 2014, https://doi.org/10.1007/978-3-319-10593-2_13
15 S. Hitawala, Y. Li, X. Wang, D. Yang, "Image Super-Resolution Using VDSR-ResNeXt and SRCGAN," in CVPR, 2018, https://arxiv.org/abs/1810.05731
16 S. G. Mallat, "A theory for multiresolution signal decomposition: the wavelet representation," in TPAMI, 1989, https://doi.org/10.1109/34.192463
17 H. Chang, D.-Y. Yeung and Y. Xiong, "Super-resolution through neighbor embedding," in CVPR, 2004, https://doi.org/10.1109/CVPR.2004.1315043
18 W. Zhang, Y. Liu, C. Dong, Y. Qiao, "RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution," in CVPR, 2019, https://arxiv.org/abs/1908.06382
19 K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," in CVPR, 2015, https://doi.org/10.1109/cvpr.2016.90
20 Z. Liu, P. Luo, X. Wang and X. Tang, "Deep Learning Face Attributes in the Wild," in ICCV, 2015, https://doi.org/10.1109/iccv.2015.425
21 G. Huang, Z. Liu, L. v. d. Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks,"in Computer Vision and Pattern Recognition, 2017, https://arxiv.org/abs/1608.06993
22 X. Zhang and X. Wu, "Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation," in IEEE Trans. Image Process., 2008, https://doi.org/10.1109/tip.2008.924279