Unsupervised Single-Image Super-Resolution with Multi-Gram Loss
Abstract
:1. Introduction
- We design a new neural network architecture: UMGSR, which leverages the internal information of the LR image in the training stage. To stably train the network and convey more information about the input, the UMGSR combines the residual learning blocks with a two-step global residual learning.
- The multi-gram loss is introduced to the SR task, cooperating with the perceptual loss. In detail, we combine the multi-gram loss with the pixel-level MSE loss and the perceptual loss as the final loss function. Compared with other unsupervised methods, our design can obtain satisfying results in texture details and struggle for SR image generation similar to the supervised methods.
2. Related Work
3. Methodology
3.1. The Generation of Training Dataset
3.2. Unsupervised Multi-Gram SR Network
3.3. Pixel, Perceptual, and Gram Losses
4. Experiments
4.1. Setting Details
4.2. Ablation Experiments
4.3. Discussion
5. Conclusions and Future Work
Author Contributions
Funding
Conflicts of Interest
References
- Lim, B.; Son, S.; Kim, H.; Nah, S.; Mu Lee, K. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July 2017; pp. 136–144. [Google Scholar]
- Haris, M.; Shakhnarovich, G.; Ukita, N. Deep Back-Projection Networks For Super-Resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 1664–1673. [Google Scholar]
- Ledig, C.; Theis, L.; Huszár, F.; Caballero, J.; Cunningham, A.; Acosta, A.; Aitken, A.; Tejani, A.; Totz, J.; Wang, Z.; et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4681–4690. [Google Scholar]
- Dong, C.; Loy, C.C.; He, K.; Tang, X. Learning a Deep Convolutional Network for Image Super-Resolution. In European Conference on Computer Vision; Springer: Cham, Switzerland, 2014; pp. 184–199. [Google Scholar]
- Kim, J.; Kwon Lee, J.; Mu Lee, K. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 1646–1654. [Google Scholar]
- Tai, Y.; Yang, J.; Liu, X. Image Super-Resolution via Deep Recursive Residual Network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 3147–3155. [Google Scholar]
- Caballero, J.; Ledig, C.; Aitken, A.; Acosta, A.; Totz, J.; Wang, Z.; Shi, W. Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4778–4787. [Google Scholar]
- Sajjadi, M.S.M.; Scholkopf, B.; Hirsch, M. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4501–4510. [Google Scholar]
- Shi, W.; Caballero, J.; Ledig, C.; Zhuang, X.; Bai, W.; Bhatia, K.; de Marvao, A.M.S.M.; Dawes, T.; O’Regan, D.; Rueckert, D. Cardiac image super-resolution with global correspondence using multi-atlas patchmatch. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan, 22–26 September 2013; pp. 9–16. [Google Scholar]
- Zou, W.W.W.; Yuen, P.C. Very Low Resolution Face Recognition Problem. IEEE Trans. Image Process. 2011, 21, 327–340. [Google Scholar] [CrossRef] [PubMed]
- Shocher, A.; Cohen, N.; Irani, M. “Zero-Shot” Super-Resolution using Deep Internal Learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 3118–3126. [Google Scholar]
- Mechrez, R.; Talmi, I.; Zelnik-Manor, L. Image super-resolution based on local self-similarity. In Proceedings of the European Conference on Computer Vision, Munich, Germany, 8–14 September 2018; pp. 768–783. [Google Scholar]
- Gatys, L.A.; Ecker, A.S.; Bethge, M. A Neural Algorithm of Artistic Style. arXiv 2015, arXiv:1508.06576. [Google Scholar] [CrossRef]
- Gatys, L.; Ecker, A.S.; Bethge, M. Texture Synthesis Using Convolutional Neural Networks. In Advances in Neural Information Processing Systems; NIPS: Grenada, Spain, 2015; pp. 262–270. [Google Scholar]
- Blau, Y.; Mechrez, R.; Timofte, R.; Michaeli, T.; Zelnik-Manor, L. 2018 PIRM Challenge on Perceptual Image Super-resolution. In Proceedings of the European Conference on Computer Vision, Munich, Germany, 8–14 September 2018. [Google Scholar]
- Zhang, Y.; Li, K.; Li, K.; Wang, L.; Zhong, B.; Fu, Y. Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In Proceedings of the European Conference on Computer Vision, Munich, Germany, 8–14 September 2018; pp. 286–301. [Google Scholar]
- Zhang, Y.; Tian, Y.; Kong, Y.; Zhong, B.; Fu, Y. Residual Dense Network for Image Super-Resolution. In Proceedings of the IEEE International Conference on Computer Vision, istanbul, Turkey, 30–31 January 2018; pp. 2472–2481. [Google Scholar]
- Zhao, H.; Gallo, O.; Frosio, I.; Kautz, J. Loss Functions for Image Restoration With Neural Networks. IEEE Trans. Comput. Imaging 2016, 3, 47–57. [Google Scholar] [CrossRef]
- Bulat, A.; Tzimiropoulos, G. Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 109–117. [Google Scholar]
- Irani, D.G.S.B.M. Super-resolution from a single image. In Proceedings of the IEEE International Conference on Computer Vision, Kyoto, Japan, 29 September–2 October 2009; pp. 349–356. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 770–778. [Google Scholar]
- Snelgrove, X. High-resolution multi-scale neural texture synthesis. In SIGGRAPH Asia Technical Briefs; ACM SIGGRAPH: Los Angeles, CA, USA, 2017; pp. 1–13. [Google Scholar]
- Chang, H.; Yeung, D.-Y.; Xiong, Y. Very Low Resolution Face Recognition Problem. In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, 27 June–2 July 2004. [Google Scholar]
- Duchon, C.E. Lanczos Filtering in One and Two Dimensions. J. Appl. Meteorol. 1979, 18, 1016–1022. [Google Scholar] [CrossRef]
- Thornton, M.W.; Atkinson, P.M.; Holland, D.A. Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping. Int. J. Remote. Sens. 2006, 27, 473–491. [Google Scholar] [CrossRef]
- Ulyanov, D.; Vedaldi, A.; Lempitsky, V. Deep Image Prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 9446–9454. [Google Scholar]
- Protter, M.; Elad, M. Super Resolution With Probabilistic Motion Estimation. IEEE Trans. Image Process. 2009, 18, 1899–1904. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Suetake, N.; Sakano, M.; Uchino, E. Image super-resolution based on local self-similarity. Opt. Rev. 2008, 15, 26–30. [Google Scholar] [CrossRef]
- Lin, Z.; Shum, H.-Y. Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation. IEEE Trans. Pattern Anal. Mach. Intell. 2004, 26, 83–97. [Google Scholar] [PubMed]
- Redmon, J.; Farhadi, A. YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 7263–7271. [Google Scholar]
- Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 2018, 40, 834–848. [Google Scholar] [CrossRef] [PubMed]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 4510–4520. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems; NIPS: Grenada, Spain, 2012; pp. 1097–1105. [Google Scholar]
- Dong, C.; Loy, C.C.; He, K.; Tang, X. Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 38, 295–307. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Kim, J.; Kwon Lee, J.; Mu Lee, K. Deeply-Recursive Convolutional Network for Image Super-Resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 1637–1645. [Google Scholar]
- Tong, T.; Li, G.; Liu, X.; Gao, Q. Image Super-Resolution Using Dense Skip Connections. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 4799–4807. [Google Scholar]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, 17–22 June 2007; pp. 4700–4708. [Google Scholar]
- Capel, D.L. Image mosaicing. In Image Mosaicing and Super-Resolution; University of Oxford: Oxford, UK, 2004; pp. 47–79. [Google Scholar]
- Farsiu, S.; Robinson, M.D.; Elad, M.; Milanfar, P. Fast and Robust Multiframe Super Resolution. IEEE Trans. Image Process. 2004, 13, 1327–1344. [Google Scholar] [CrossRef] [PubMed]
- Baker, S.; Kanade, T. Limits on super-resolution and how to break them. IEEE Trans. Pattern Anal. Mach. Intell. 2002, 9, 1167–1183. [Google Scholar] [CrossRef]
- Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative Adversarial Nets. In Advances in Neural Information Processing Systems; NIPS: Grenada, Spain, 2014; pp. 2672–2680. [Google Scholar]
- Karras, T.; Aila, T.; Laine, S.; Lehtinen, J. Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv 2017, arXiv:1710.10196. [Google Scholar]
- Johnson, J.; Alahi, A.; Fei-Fei, L. Perceptual losses for real-time style transfer and super-resolution. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 694–711. [Google Scholar]
- Freedman, G.; Fattal, R. Image and video upscaling from local self-examples. ACM Trans. Graph. (TOG) 2011, 30, 12. [Google Scholar] [CrossRef]
- Huang, J.-B.; Singh, A.; Ahuja, N. Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 5197–5206. [Google Scholar]
- Zontak, M.; Irani, M. Internal statistics of a single natural image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 20–25 June 2011; pp. 977–984. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Zeyde, R.; Elad, M.; Protter, M. Texture Synthesis Using Convolutional Neural Networks. In Proceedings of the International Conference on Curves and Surfaces, Avignon, France, 24–30 June 2010; pp. 711–730. [Google Scholar]
- Timofte, R.; Agustsson, E.; Van Gool, L.; Yang, M.-H.; Zhang, L. NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshopsh, Honolulu, HI, USA, 21–26 July 2017; pp. 114–125. [Google Scholar]
- Blau, Y.; Michaeli, T. The Perception-Distortion Tradeoff. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 6228–6237. [Google Scholar]
- Wang, Z.; Bovik, A.C.; Sheikh, H.R.; Simoncelli, E.P. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 2004, 13, 600–612. [Google Scholar] [CrossRef] [PubMed]
- Van der Schaaf, V.A.; van Hateren, J.H.V. Modelling the power spectra of natural images: Statistics and information. Vis. Res. 1996, 36, 2759–2770. [Google Scholar] [CrossRef]
PSNR | EDSR | ZSSR | SRGAN | UMGSR (MSE) | UMGSR (MSE + Percp) | UMGSR (Total Loss) |
---|---|---|---|---|---|---|
Image1 | 27.74 | 24.72 | 24.05 | 25.05 | 25.02 | 24.89 |
Image2 | 25.03 | 23.81 | 22.83 | 23.96 | 24.03 | 23.87 |
Image3 | 27.45 | 26.74 | 24.46 | 24.78 | 24.93 | 24.87 |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Shi, Y.; Li, B.; Wang, B.; Qi, Z.; Liu, J. Unsupervised Single-Image Super-Resolution with Multi-Gram Loss. Electronics 2019, 8, 833. https://doi.org/10.3390/electronics8080833
Shi Y, Li B, Wang B, Qi Z, Liu J. Unsupervised Single-Image Super-Resolution with Multi-Gram Loss. Electronics. 2019; 8(8):833. https://doi.org/10.3390/electronics8080833
Chicago/Turabian StyleShi, Yong, Biao Li, Bo Wang, Zhiquan Qi, and Jiabin Liu. 2019. "Unsupervised Single-Image Super-Resolution with Multi-Gram Loss" Electronics 8, no. 8: 833. https://doi.org/10.3390/electronics8080833