Abstract
Convolutional Neural Networks (CNNs) have shown promising results on Single Image Super-Resolution (SISR) task. A pair of Low-Resolution (LR) and High-Resolution (HR) images are typically used in the CNN models to train them to super-resolve LR images in a fully supervised manner. Owing to non-availability of true LR-HR pairs, the LR images are generally synthesized from HR data by applying synthetic degradation such as bicubic downsampling. Such networks under-perform when used on real-world data where degradation is different from the synthetically generated LR image. As obtaining true LR-HR pair is a tedious and resource (time and effort) consuming task, we propose a new approach and architecture to super-resolve the real-world LR images in an unsupervised manner by using a Generative Adversarial Network (GAN) framework with Variational Auto-Encoder (VAE). Along with a new network architecture, we also introduce a novel loss metric based on no-reference quality scores of SR images to improve the perceptual fidelity of the SR images. Through the experiments on NTIRE-2020 Real-World SR Challenge dataset, we demonstrate the superiority of the proposed approach over the other competing state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agustsson, E., Timofte, R.: NTIRE 2017 challenge on single image super-resolution: dataset and study. In: 2017 IEEE Conference on CVPRW, pp. 1122–1131 (2017)
Cai, J., Zeng, H., Yong, H., Cao, Z., Zhang, L.: Toward real-world single image super-resolution: a new benchmark and a new model. In: ICCV, pp. 3086–3095, October 2019
Cheng, G., Matsune, A., Li, Q., Zhu, L., Zang, H., Zhan, S.: Encoder-decoder residual network for real super-resolution. In: CVPR Workshops, June 2019
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. PAMI 38(2), 295–307 (2016)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Du, C., Zewei, H., Anshun, S., et al.: Orientation-aware deep neural network for real image super-resolution. In: The IEEE Conference on CVPRW, June 2019
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680. Curran Associates, Inc. (2014)
Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734 (2018)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: 2016 IEEE CVPR, pp. 1646–1654 (2016)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Ledig, C., Theis, L., Huszár, F., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings IEEE Conference on CVPR, pp. 4681–4690 (2017)
Li, Y., Agustsson, E., Gu, S., Timofte, R., Van Gool, L.: CARN: convolutional anchored regression network for fast and accurate single image super-resolution. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 166–181. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_11
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: 2017 IEEE Conference on CVPRW, pp. 1132–1140 (2017)
Lin, H., Hosu, V., Saupe, D.: KADID-10K: a large-scale artificially distorted IQA database. In: 2019 10th Conference QoMEX, pp. 1–3. IEEE (2019)
Lugmayr, A., Danelljan, M., Timofte, R.: Unsupervised learning for real-world super-resolution. In: ICCV Workshops (2019)
Lugmayr, A., Danelljan, M., Timofte, R., et al.: Aim 2019 challenge on real-world image super-resolution: methods and results. In: ICCV Workshops (2019)
Lugmayr, A., Danelljan, M., Timofte, R., et al.: NTIRE 2020 challenge on real-world image super-resolution: methods and results. In: CVPRW (2020)
Park, S.-J., Son, H., Cho, S., Hong, K.-S., Lee, S.: SRFeat: single image super-resolution with feature discrimination. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 455–471. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_27
Prajapati, K., Chudasama, V., Patel, H., Upla, K., Ramachandra, R., Raja, K., Busch, C.: Unsupervised single image super-resolution network (USISResNet) for real-world data using generative adversarial network. In: 2020 IEEE CVPR-W, pp. 1904–1913 (2020)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Shi, Y., Zhong, H., Yang, Z., Yang, X., Lin, L.: DDet: dual-path dynamic enhancement network for real-world image super-resolution. IEEE Signal Process. Lett. 27, 481–485 (2020)
Shocher, A., Cohen, N., Irani, M.: Zero-shot super-resolution using deep internal learning. In: 2018 IEEE/CVF Conference on CVPR, pp. 3118–3126 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Spearman, C.: The proof and measurement of association between two things. In: Jenkins, J.J., Paterson, D.G. (eds.) Studies in individual differences: The search for intelligence, Appleton-Century-Crofts, pp. 45–58 (1961)
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 IEEE Conference on CVPRW, pp. 114–125 (2017)
Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: Proceedings of IEEE ICCV, pp. 4799–4807 (2017)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 63–79. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_5
Xu, X., Li, X.: Scan: spatial color attention networks for real single image super-resolution. In: The IEEE Conference on CVPRW, June 2019
Yuan, Y., Liu, S., Zhang, J., Zhang, Y., Dong, C., Lin, L.: Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In: 2018 IEEE/CVF Conference on CVPRW, pp. 814–81409, June 2018
Zhang, K., Zuo, W., Zhang, L.: Learning a single convolutional super-resolution network for multiple degradations. In: Proceedings IEEE Conference on CVPR, pp. 3262–3271 (2018)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of IEEE Conference on CVPR, pp. 586–595 (2018)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_18
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: Proceedings of IEEE Conference on CVPR, pp. 2472–2481 (2018)
Acknowledgment
This work is supported by ERCIM, who kindly enabled the internship of Kishor Upla at NTNU, Gjøvik. Authors are also thankful to Science and Engineering Research Board (SERB), a statutory body of Department of Science and Technology (DST), Government of India for providing support for this research work (ECR/2017/003268).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Prajapati, K. et al. (2021). Unsupervised Real-World Super-resolution Using Variational Auto-encoder and Generative Adversarial Network. In: Del Bimbo, A., et al. Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science(), vol 12662. Springer, Cham. https://doi.org/10.1007/978-3-030-68790-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-68790-8_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68789-2
Online ISBN: 978-3-030-68790-8
eBook Packages: Computer ScienceComputer Science (R0)