Abstract
Single image super-resolution (SISR) consists of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community, due to the wide variety of problems ranging from real-world surveillance to aerial and satellite imaging. Most of the improvements in SISR come from convolutional networks, in which approaches often focus on the deeper and wider architectural paradigm. In this work, we decided to step up from the traditional convolutions and adopt the concept of capsules. Since their overwhelming results in image classification and segmentation problems, we question how suitable they are for SISR. We also verify that different solutions share similar configurations, and argue that this trend leads to fewer explorations of network designs. Throughout our experiments, we check various strategies to improve results, ranging from new and different loss functions to changes in the capsule layers. Our network achieved positive and promising results with fewer convolutional-based layers, showing that capsules might be a concept worth applying to the image super-resolution problem. In particular, we observe that the proposed method recreates the connection between the different characters more precisely, thus demonstrating the potential of capsules in super-resolution problems.
Artur Jordáo: This work was done when Artur Jordao was a post-doctoral researcher at the University of Campinas.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). Software available from tensorflow.org
Agustsson, E., Timofte, R.: NTIRE 2017 challenge on single image super-resolution: dataset and study. In: CVPR Workshops, pp. 1–8 (2017)
Andersson, P., Nilsson, J., Akenine-Möller, T., Oskarsson, M., Åström, K., Fairchild, M.D.: FLIP: a difference evaluator for alternating images. In: ACM on Computer Graphics and Interactive Techniques (2020)
Anwar, S., Khan, S.H., Barnes, N.: A deep journey into super-resolution: a survey. ACM Comput. Surv. 53(3), 60:1–60:34 (2020). https://doi.org/10.1145/3390462
Barron, J.T.: A More General Robust Loss Function. arXiv preprint arXiv:1701.03077 (2017)
Behjati, P., Rodriguez, P., Mehri, A., Hupont, I., Tena, C.F., Gonzalez, J.: OverNet: lightweight multi-scale super-resolution with overscaling network. In: WACV, pp. 1–11 (2021)
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: BMVC (2012)
Cai, J., Gu, S., Timofte, R., Zhang, L.: NTIRE 2019 challenge on real image super-resolution: methods and results. In: CVPR Workshops, pp. 1–8 (2019)
Canny, J.: A computational approach to edge detection. Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
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
Gu, J., Tresp, V.: Improving the robustness of capsule networks to image affine transformations. In: CVPR, pp. 1–15 (2020)
Gu, J., Wu, B., Tresp, V.: Effective and efficient vote atack on capsule networks. In: ICLR (2021)
Hinton, G., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: ICLR, pp. 1–10 (2018)
Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Artificial Neural Networks and Machine Learning, pp. 44–51 (2011)
Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: ICPR, pp. 2366–2369 (2010)
Hsu, J., Kuo, C., Chen, D.: Image super-resolution using capsule neural networks. IEEE Access (2020)
Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: CVPR, pp. 1–9 (2015)
Huang, W., Zhou, F.: DA-CapsNet: dual attention mechanism capsule network. Sci. Rep. (2020)
Irani, M., Peleg, S.: Improving resolution by image registration. In: CVGIP: Graph. Model. Image Process. 53(3), 231–239 (1991)
Ji, X., Cao, Y., Tai, Y., Wang, C., Li, J., Huang, F.: Real-world super-resolution via Kernel estimation and noise injection. In: CVPR Workshops, pp. 1–8 (2020)
Kastryulin, S., Zakirov, D., Prokopenko, D.: PyTorch image quality: metrics and measure for image quality assessment (2019). https://github.com/photosynthesis-team/piq
Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: CVPR, pp. 1–8 (2016)
Kim, J., Kwon Lee, J., Mu Lee, K.: Deeply-recursive convolutional network for image super-resolution. In: CVPR, pp. 1–13 (2016)
Kim, J.H., Lee, J.S.: Deep residual network with enhanced upscaling module for super-resolution. In: CVPR Workshops, pp. 1–15 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015)
LaLonde, R., Bagci, U.: Capsules for Object Segmentation. arXiv preprint arXiv:1804.04241 (2018)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 1–8 (2017)
Li, C., Bovik, A.C.: Content-weighted video quality assessment using a three-component image model. J. Electron. Imag. 19, 19 (2010)
Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J.E., Stoica, I.: Tune: a research platform for distributed model selection and training. arXiv preprint arXiv:1807.05118 (2018)
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: CVPR Workshops, pp. 1–8 (2017)
Lin, M., Chen, Q., Yan, S.: Network in Network. arXiv preprint arXiv:1312.4400 (2013)
Majdabadi, M.M., Ko, S.B.: Capsule GAN for Robust Face Super-Resolution. Multim. Tools Appl. (2020)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, vol. 2, pp. 416–423 (2001)
Nasrollahi, K., Moeslund, T.B.: Super-resolution: a comprehensive survey. Mach. Vis. Appl. 25(6), 1423–1468 (2014)
Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill (2016). http://distill.pub/2016/deconv-checkerboard
Pandey, R.K., Saha, N., Karmakar, S., Ramakrishnan, A.G.: MSCE: an edge preserving robust loss function for improving super-resolution algorithms. arXiv preprint arXiv:1809.00961 (2018)
Ren, H., Kheradmand, A., El-Khamy, M., Wang, S., Bai, D., Lee, J.: Real-world super-resolution using generative adversarial networks. In: CVPR Workshops, pp. 1–8 (2020)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NeurIPS, pp. 3856–3866 (2017)
Sabour, S., Tagliasacchi, A., Yazdani, S., Hinton, G.E., Fleet, D.J.: Unsupervised part representation by flow capsules. In: Meila, M., Zhang, T. (eds.) ICML, vol. 139, pp. 9213–9223 (2021)
Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: NeurIPS, pp. 901–909. Curran Associates, Inc. (2016)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR, pp. 1–8 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Singh, M., Nagpal, S., Singh, R., Vatsa, M.: Dual directed capsule network for very low resolution image recognition. In: ICCV, pp. 1–8 (2019)
Sobel, I., Feldman, G.: A \(3\times 3\) Isotropic Gradient Operator for Image Processing (1968). Talk at the Stanford Artificial Project
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)
Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1–8 (2015)
Timofte, R., et al.: NTIRE 2017 challenge on single image super-resolution: methods and results. In: CVPR Workshops, pp. 1110–1121 (2017)
Timofte, R., Gu, S., Wu, J., Van Gool, L.: NTIRE 2018 challenge on single image super-resolution: methods and results. In: CVPR Workshops, pp. 1–17 (2018)
Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. In: NeurIPS, pp. 550–558 (2016)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: ECCV, pp. 63–79 (2019)
Wang, Z., Liu, D., Yang, J., Han, W., Huang, T.: Deep networks for image super-resolution with sparse prior. In: ICCV, pp. 370–378 (2015)
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems Computers, vol. 2, pp. 1398–1402 (2003)
Wang, Z., Chen, J., Hoi, S.C.H.: Deep learning for image super-resolution: a survey. Trans. Pattern Anal. Mach. Intell. 43(10), 3365–3387 (2021)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. Trans. Image Process. 13(4), 600–612 (2004)
Xu, J., Zhao, Y., Dong, Y., Bai, H.: Fast and accurate image super-resolution using a combined loss. In: CVPR Workshops, pp. 1093–1099 (2017)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. Trans. Image Process. 19(11), 2861–2873 (2010)
Yu, C., Zhu, X., Zhang, X., Wang, Z., Zhang, Z., Lei, Z.: HP-capsule: unsupervised face part discovery by hierarchical parsing capsule network. In: CVPR, pp. 4022–4031 (2022)
Yu, J., Fan, Y., Yang, J., Xu, N., Wang, X., Huang, T.S.: Wide Activation for Efficient and Accurate Image Super-Resolution. arXiv preprint arXiv:1808.08718 (2018)
Zhang, K., Gu, S., Timofte, R.: NTIRE 2020 challenge on perceptual extreme super-resolution: methods and results. In: CVPR Workshops, pp. 1–10 (2020)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 1–8 (2018)
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: CVPR, pp. 2472–2481 (2018)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47–57 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de Araújo, G.C., Jordão, A., Pedrini, H. (2023). Single Image Super-Resolution Based on Capsule Neural Networks. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14197. Springer, Cham. https://doi.org/10.1007/978-3-031-45392-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-45392-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45391-5
Online ISBN: 978-3-031-45392-2
eBook Packages: Computer ScienceComputer Science (R0)