Research PaperNo Access

A single image super resolution method based on cross residual network and wavelet transform

Kwang-Chol Ri

https://orcid.org/0000-0002-1423-6474

Faculty of Information Science, Kim Il Sung University, Ryongnam-Dong, Taesong District, Pyongyang, DPR Korea

E-mail Address: kc.ri0521@ryongnamsan.edu.kp

Search for more papers by this author

and

Chol-Jin Kim

Faculty of Information Science, Kim Il Sung University, Ryongnam-Dong, Taesong District, Pyongyang, DPR Korea

Search for more papers by this author

https://doi.org/10.1142/S0219691323500169Cited by:0 (Source: Crossref)

Abstract

In this paper, we propose a method to realize single image super resolution using a network composed of residual blocks with a cross architecture and wavelet transform. For the high quality of the reconstructed high resolution image, the brightness change must be sharp at the edge and gentle at the flat region. In single image super resolution, it is important to accurately predict the high-frequency components of the image. Hence, we propose a method to realize single image super resolution by estimating the high-frequency component in the wavelet domain using neural network composed of residual blocks with two crossing skip connections.

Keywords:

AMSC: 42C40, 65T60, 68M10, 92B20, 94A08

References

1. S. Baker and T. Kanade , Limits on super-resolution and how to break them, Pattern Anal. Mach. Intell. IEEE Trans. 24(9) (2002) 1167–1183, https://doi.org/10.1109/TPAMI.2002.1033210. Crossref, Web of Science, Google Scholar
2. M. Bevilacqua, A. Roumy, C. Guillemot and M. L. Alberi-Morel , Low-complexity single-image super-resolution based on nonnegative neighbor embedding, in Proc. 23rd British Machine Vision Conf. (BMVC) (2012), p. 135-1. Crossref, Google Scholar
3. T. Blu, P. Thévenaz and M. Unser , Linear interpolation revitalized, IEEE Trans. Image Process. 13(5) (2004) 710–719. Crossref, Web of Science, Google Scholar
4. Y. Chen, Y. Tai, X. L. Chunhua and S. J. Yang , FSRNet: End-to-end learning face super-resolution with facial priors, in 2018 IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2018), https://doi.org/10.1109/CVPR.2018.00264. Crossref, Google Scholar
5. C. Dong, C. C. Loy, K. He and X. Tang , Image super-resolution using deep convolutional networks, IEEE Trans. Pattern Anal. Mach. Intell. 38 (2016) 295–307. Crossref, Web of Science, Google Scholar
6. H. Huang, R. He, Z. Sun and T. Tan , Wavelet-SRNet: A wavelet-based CNN for multi-scale face super resolution, in 2017 IEEE Int. Conf. Computer Vision (ICCV) (IEEE, 2017), pp. 1689–1697. Crossref, Google Scholar
7. J.-B. Huang, A. Singh and N. Ahuja , Single image super-resolution from transformed self-exemplars, in 2015 IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (IEEE, 2015), https://doi.org/10.1109/CVPR.2015.7299156. Crossref, Google Scholar
8. N. Kumar, R. Verma and A. Sethi , Convolutional neural networks for wavelet domain super resolution, Pattern Recognit. Lett. 90 (2017) 65–71. Crossref, Web of Science, Google Scholar
9. W.-S. Lai, J.-B. Huang, N. Ahuja and M.-H. Yang , Deep Laplacian pyramid networks for fast and accurate super-resolution, in 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (IEEE, 2017), https://doi.org/10.1109/CVPR.2017.618. Crossref, Google Scholar
10. C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang and W. S. Twitter , Photo-realistic single image super-resolution using a generative adversarial network, in Proc. Computer Vision and Pattern Recognition, Venice, Italy, 30 October–1 November 2017, pp. 105–114. Google Scholar
11. B. Lim, S. Son, H. Kim, S. Nah and K. M. Lee , Enhanced deep residual networks for single image super-resolution, in Proc. Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July 2017, pp. 132–1140. Google Scholar
12. H. Liu, Z. Fu, J. Han, L. Shao, S. Hou and Y. Chu , Single image super-resolution using multi-scale deep encoder-decoder with phase congruency edge map guidance, Information Sciences 473 (2019) 44–58. Crossref, Web of Science, Google Scholar
13. P. Liu, Y. Hong and Y. Liu , Multi-branch deep residual network for single image super-resolution, Algorithms 11 (2018) 144, https://doi.org/10.3390/a11100144. Crossref, Web of Science, Google Scholar
14. J. Lu et al., A deep learning method for image super-resolution based on geometric similarity, Signal Proc.: Image Commun. (2018), https://doi.org/10.1016/j.image.2018.10.003. Google Scholar
15. C. G. Marco Bevilacqua, A. Roumy and M.-L. A. Morel , Low-complexity single-image super-resolution based on nonnegative neighbor embedding, in British Machine Vision Conf. (2012), p. 135-1. Crossref, Google Scholar
16. D. Martin, C. Fowlkes, D. Tal and J. Malik , A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, in IEEE Int. Conf. Computer Vision (IEEE, 2001), pp. 416–423. Crossref, Google Scholar
17. T. Peleg and M. Elad , A statistical prediction model based on sparse representations for single image super-resolution, IEEE Trans. Image Process. 23(6) (2014) 2569–2582. Crossref, Web of Science, Google Scholar
18. H. Ren, M. Elkhamy and J. Lee , Image super resolution based on fusing multiple convolution neural networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2017), pp. 54–61. Crossref, Google Scholar
19. S. Schulter, C. Leistner and H. Bischof , Fast and accurate image upscaling with super-resolution forests, in 2015 IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (IEEE, 2015), https://doi.org/10.1109/CVPR.2015.7299003. Crossref, Google Scholar
20. J. Sun, Z. Xu and H.-Y. Shum , Image super-resolution using gradient profile prior, in IEEE Conf. Computer Vision and Pattern Recognition, 2008, CVPR 2008 (IEEE, 2008), pp. 1–8, https://doi.org/10.1109/CVPR.2008.4587659. Google Scholar
21. R. Timofte, V. De and L. V. Gool , Anchored neighborhood regression for fast example-based super-resolution, in 2013 IEEE Int. Conf. Computer Vision (IEEE, 2013), https://doi.org/10.1109/ICCV.2013.241. Crossref, Google Scholar
22. R. Timofte, V. De Smet and L. Van Gool , A+: Adjusted anchored neighborhood regression for fast super-resolution, in Computer Vision–ACCV 2014: 12th Asian Conference on Computer Vision, Singapore, November 1–5, 2014, Revised Selected Papers, Part IV 12. Springer International Publishing, 2014), pp. 111–126. Google Scholar
23. T. Tong, G. Li, X. Liu and Q. Gao , Image super-resolution using dense skip connections, in IEEE Int. Conf. Computer Vision (ICCV) (IEEE, 2017), https://doi.org/10.1109/ICCV.2017.514. Crossref, Google Scholar
24. Z. Wang et al., Deep networks for image super-resolution with sparse prior, in IEEE Int. Conf. Computer Vision (IEEE, 2015), pp. 370–378. Crossref, Google Scholar
25. Y. Xiao, X. Cao, Y. Zheng and X. Zhu , Joint residual pyramid for depth map super resolution, in PRICAI 2018: Trends in Artificial Intelligence, eds. X. Geng and B.-H. Kang (Springer International Publishing, Cham, 2018), pp. 797–810. Crossref, Google Scholar
26. R. Zeyde, M. Elad and M. Protter , On single image scale up using sparse representations, Curves Surf. 6920 (2012) 711–730. Crossref, Google Scholar
27. F. Zhang, N. Cai, G. Cen, F. Li, H. Wang and X. Chen , Image super-resolution via a novel cascaded convolutional neural network framework, Signal Process.: Image Commun. (2018), https://doi.org/10.1016/j.image.2018.01.009. Crossref, Web of Science, Google Scholar
28. K. Zhang, X. Gao, D. Tao and X. Li , Single image super-resolution with non-local means and steering kernel regression, IEEE Trans. Image Process. 21(11) (2012) 4544–4556. Crossref, Web of Science, Google Scholar
29. K. Zhang, J. Li, Z. Xiong, X. Liu and X. Gao , Optimized multiple linear mappings for single image super-resolution, Opt. Commun. 404 (2017) 169–176. Crossref, Web of Science, Google Scholar
30. Y. Zhang, Y. Tian, Y. Kong, B. Zhong and Y. Fu , Residual dense network for image super-resolution, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 2472–2481. Crossref, Google Scholar
31. L. Zhang and X. Wu , An edge-guided image interpolation algorithm via directional filtering and data fusion, IEEE Trans. Image Process. 15(8) (2006) 2226–2238. Crossref, Web of Science, Google Scholar
32. K. Zhang, W. Zuo and L. Zhang , Learning a single convolutional super-resolution network for multiple degradations, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 3262–3271. Crossref, Google Scholar