Skip to main content

2020 | OriginalPaper | Buchkapitel

Effective Utilization of Hybrid Residual Modules in Deep Neural Networks for Super Resolution

verfasst von : Abdul Muqeet, Sung-Ho Bae

Erschienen in: MultiMedia Modeling

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Recently, Single-Image Super-Resolution (SISR) has attracted a lot of researchers due to its numerous real-life applications in multiple domains. This paper focuses on efficient solutions of SISR with Hybrid Residual Modules (HRM). The proposed HRM allows the deep neural network to reconstruct very high quality super-resolved images with much lower computation compared to the conventional SISR methods. In this paper, we first describe the technical details of our HRM in SISR and introduce interesting applications of the proposed SISR method, such as surveillance camera system, medical imaging, astronomical imaging.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)CrossRef Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)CrossRef
2.
Zurück zum Zitat 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, pp. 770–778 (2016) 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, pp. 770–778 (2016)
3.
Zurück zum Zitat Li, J., Fang, F., Mei, K., Zhang, G.: Multi-scale residual network for image super-resolution. In: The European Conference on Computer Vision (ECCV), September 2018CrossRef Li, J., Fang, F., Mei, K., Zhang, G.: Multi-scale residual network for image super-resolution. In: The European Conference on Computer Vision (ECCV), September 2018CrossRef
4.
Zurück zum Zitat Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017 Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017
5.
Zurück zum Zitat Muqeet, A., Iqbal, M.T., Bae, S.H.: Hybrid Residual Attention Network for Single Image Super Resolution. arXiv preprint arXiv:1907.05514 2019 Muqeet, A., Iqbal, M.T., Bae, S.H.: Hybrid Residual Attention Network for Single Image Super Resolution. arXiv preprint arXiv:​1907.​05514 2019
6.
Zurück zum Zitat 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. 27(3), 473–491 (2006)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. 27(3), 473–491 (2006)CrossRef
7.
Zurück zum Zitat Greenspan, H.: Super-resolution in medical imaging. Comput. J. 52(1), 43–63 (2008)CrossRef Greenspan, H.: Super-resolution in medical imaging. Comput. J. 52(1), 43–63 (2008)CrossRef
8.
Zurück zum Zitat Pham, C.H., Ducournau, A., Fablet, R., Rousseau, F.: Brain MRI super-resolution using deep 3D convolutional networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 197–200 (2017) Pham, C.H., Ducournau, A., Fablet, R., Rousseau, F.: Brain MRI super-resolution using deep 3D convolutional networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 197–200 (2017)
9.
Zurück zum Zitat Chen, Y., Xie, Y., Zhou, Z., Shi, F., Christodoulou, A.G., Li, D.: Brain MRI super resolution using 3D deep densely connected neural networks. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 739–742 (2018) Chen, Y., Xie, Y., Zhou, Z., Shi, F., Christodoulou, A.G., Li, D.: Brain MRI super resolution using 3D deep densely connected neural networks. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 739–742 (2018)
10.
Zurück zum Zitat Mahapatra, D., Bozorgtabar, B., Hewavitharanage, S., Garnavi, R.: Image super resolution using generative adversarial networks and local saliency maps for retinal image analysis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 382–390 (2017)CrossRef Mahapatra, D., Bozorgtabar, B., Hewavitharanage, S., Garnavi, R.: Image super resolution using generative adversarial networks and local saliency maps for retinal image analysis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 382–390 (2017)CrossRef
11.
Zurück zum Zitat Tatem, A.J., Lewis, H.G., Atkinson, P.M., Nixon, M.S.: Super-resolution target identification from remotely sensed images using a Hopfield neural network. IEEE Trans. Geosci. Remote Sens. 39(4), 781–796 (2001)CrossRef Tatem, A.J., Lewis, H.G., Atkinson, P.M., Nixon, M.S.: Super-resolution target identification from remotely sensed images using a Hopfield neural network. IEEE Trans. Geosci. Remote Sens. 39(4), 781–796 (2001)CrossRef
12.
Zurück zum Zitat Dao, M., Kwan, C., Koperski, K., Marchisio, G.: A joint sparsity approach to tunnel activity monitoring using high resolution satellite images. In: 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), pp. 322–328 (2017) Dao, M., Kwan, C., Koperski, K., Marchisio, G.: A joint sparsity approach to tunnel activity monitoring using high resolution satellite images. In: 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), pp. 322–328 (2017)
13.
Zurück zum Zitat Luo, Y., Zhou, L., Wang, S., Wang, Z.: A joint sparsity approach to tunnel activity monitoring using high resolution satellite images video satellite imagery super resolution via convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 14(12), 2398–2402 (2017)CrossRef Luo, Y., Zhou, L., Wang, S., Wang, Z.: A joint sparsity approach to tunnel activity monitoring using high resolution satellite images video satellite imagery super resolution via convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 14(12), 2398–2402 (2017)CrossRef
14.
Zurück zum Zitat Huang, B., Wang, W., Bates, M., Zhuang, X.: Three-dimensional super-resolution imaging by stochastic optical reconstruction microscopy. Science 319(5864), 810–813 (2008)CrossRef Huang, B., Wang, W., Bates, M., Zhuang, X.: Three-dimensional super-resolution imaging by stochastic optical reconstruction microscopy. Science 319(5864), 810–813 (2008)CrossRef
15.
Zurück zum Zitat Errico, C., et al.: Ultrafast ultrasound localization microscopy for deep super-resolution vascular imaging. Nature 527(7579), 499 (2015)CrossRef Errico, C., et al.: Ultrafast ultrasound localization microscopy for deep super-resolution vascular imaging. Nature 527(7579), 499 (2015)CrossRef
16.
Zurück zum Zitat Hell, S.W., et al.: The 2015 super-resolution microscopy roadmap. J. Phys. D: Appl. Phys. 48(44), 443001 (2015)CrossRef Hell, S.W., et al.: The 2015 super-resolution microscopy roadmap. J. Phys. D: Appl. Phys. 48(44), 443001 (2015)CrossRef
17.
Zurück zum Zitat Li, Z., Peng, Q., Bhanu, B., Zhang, Q., He, H.: Super resolution for astronomical observations. Astrophys. Space Sci. 363(5), 92 (2018)CrossRef Li, Z., Peng, Q., Bhanu, B., Zhang, Q., He, H.: Super resolution for astronomical observations. Astrophys. Space Sci. 363(5), 92 (2018)CrossRef
18.
Zurück zum Zitat Goto, T., Fukuoka, T., Nagashima, F., Hirano, S., Sakurai, M. Super-resolution System for 4K-HDTV. In: 22nd IEEE International Conference on Pattern Recognition, pp. 4453–4458 (2014) Goto, T., Fukuoka, T., Nagashima, F., Hirano, S., Sakurai, M. Super-resolution System for 4K-HDTV. In: 22nd IEEE International Conference on Pattern Recognition, pp. 4453–4458 (2014)
19.
Zurück zum Zitat Kim, S.Y., Oh, J., Kim, M.: Deep SR-ITM: Joint Learning of Super-resolution and Inverse Tone-Mapping for 4K UHD HDR Applications. arXiv preprint arXiv:1904.11176 (2019) Kim, S.Y., Oh, J., Kim, M.: Deep SR-ITM: Joint Learning of Super-resolution and Inverse Tone-Mapping for 4K UHD HDR Applications. arXiv preprint arXiv:​1904.​11176 (2019)
20.
Zurück zum Zitat Kim, S.Y., Oh, J., Kim, M.: JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video. arXiv preprint arXiv:1909.04391 (2019) Kim, S.Y., Oh, J., Kim, M.: JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video. arXiv preprint arXiv:​1909.​04391 (2019)
21.
Zurück zum Zitat Guo, R., Shi, X., Wang, Z.: Super-resolution from unregistered aliased astronomical images. J. Electron. Imaging 28(2), 023032 (2019)CrossRef Guo, R., Shi, X., Wang, Z.: Super-resolution from unregistered aliased astronomical images. J. Electron. Imaging 28(2), 023032 (2019)CrossRef
22.
Zurück zum Zitat Zhang, S., Ling, J., Huang, C.: Super-resolution geometry processing technology for Ill-sampled astronomical images. J. Phys.: Conf. Ser. 1229(1) 012017 (2019) Zhang, S., Ling, J., Huang, C.: Super-resolution geometry processing technology for Ill-sampled astronomical images. J. Phys.: Conf. Ser. 1229(1) 012017 (2019)
23.
Zurück zum Zitat Hu, C., Dai, L., Mir, T., Gao, Z., Fang, J.: Super-resolution channel estimation for mmWave massive MIMO with hybrid precoding. IEEE Trans. Veh. Technol. 67(9), 8954–8958 (2018)CrossRef Hu, C., Dai, L., Mir, T., Gao, Z., Fang, J.: Super-resolution channel estimation for mmWave massive MIMO with hybrid precoding. IEEE Trans. Veh. Technol. 67(9), 8954–8958 (2018)CrossRef
24.
Zurück zum Zitat Liu, H.C., Li, S.T., Yin, H.T.: Infrared surveillance image super resolution via group sparse representation. Opt. Commun. 289, 45–52 (2013)CrossRef Liu, H.C., Li, S.T., Yin, H.T.: Infrared surveillance image super resolution via group sparse representation. Opt. Commun. 289, 45–52 (2013)CrossRef
Metadaten
Titel
Effective Utilization of Hybrid Residual Modules in Deep Neural Networks for Super Resolution
verfasst von
Abdul Muqeet
Sung-Ho Bae
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-37734-2_64

Neuer Inhalt