Skip to main content
SpringerLink
Log in

Transpose convolution based model for super-resolution image reconstruction

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Single image resolution is a noticeably challenging issue that targets to acquire a high-resolution output out of one of its low-resolution variants. Many existing approaches for single-image resolutions are based on the direct solving details by using pre-defined up sampling operators. Therefore, it is challenging for the reconstruction process when the image has a larger upsampling factor. Recently, convolution neural networks (CNNs) made easy progress on super-resolution (SR) image with good results. However, the majority of methods are based on pre-defined up sampling, which uses the bicubic interpolation technique for upscaling the low-resolution (LR) image and employs feature maps to reconstruct the final high-resolution (HR) image. This leads to visual artifacts in reconstructed images and can be difficult to train such a model with a larger network. Therefore, we remove the proposed transposed convolution layer method with a novel architecture and avoid the usage of pre-defined up sampling operators. We purpose an efficient method for the usage of transposed convolution with a new architecture design and use a recurrent residual block for mapping extraction in a step-by-step manner. Finally, we generate the desired super-resolution image with low complexity and fewer parameters. Experiments and state-of-art results show better performance than existing models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Freeman WT, Jones TR, Pasztor EC (2002) To address the lack of resolution independence in most models, we developed a fast and simple one-pass, training-based super-resolution algorithm for creating plausible high-frequency details in zoomed images. Example-Based Super-Resolution, no. April 56–65

  2. Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. Proceedings IEEE computer society conference on computer vision and pattern recognition 07-12-June:3791–3799. https://doi.org/10.1109/CVPR.2015.7299003

    Google Scholar 

  3. Yang CY, Yang MH (2013) Fast direct super-resolution by simple functions. Proc IEEE Int Conf Comput Vis, 561–568. https://doi.org/10.1109/ICCV.2013.75

  4. Timofte R, De Smet V, Van Gool L (2015) A+: Adjusted anchored neighborhood regression for fast super-resolution. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 9006:111–126. https://doi.org/10.1007/978-3-319-16817-3_8

    Google Scholar 

  5. Sahito F, Zhiwen P, Ahmed J, Memon RA (2019) Wavelet-integrated deepnetworks for single image super-resolution. Electronics 8:553

    Article  Google Scholar 

  6. Kumar A, Shaikh AM, Li Y, Bilal H, Yin B (2020) Pruning filters with L1-norm and capped L1-norm for CNN compression. Appl Intell, 1–9

  7. Long J, Shelhamer E, Darrell T (2015) Long_Shelhamer_Fcn. In: 2015 IEEE conference on computer vision and pattern recognition, pp 3431–3440. https://doi.org/10.1109/CVPR.2015.7298965

  8. Dosovitskiy A, et al. (2015) FlowNet: learning optical flow with convolutional networks. In: Proceedings IEEE international conference on computer vision, vol 2015 Inter, pp 2758–2766. https://doi.org/10.1109/ICCV.2015.316

  9. Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307. https://doi.org/10.1109/TPAMI.2015.2439281

    Article  Google Scholar 

  10. Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. Proceedings IEEE computer society conference on computer vision and pattern recognition 2016-Decem:1646–1654. https://doi.org/10.1109/CVPR.2016.182

    Google Scholar 

  11. Kim J, Lee JK, Lee KM (2015) Deeply-recursive convolutional network for image super-resolution, (CVPR), arXiv:1511.04491v2

  12. Lai WS, Bin Huang J, Ahuja N, Yang MH (2017) Deep laplacian pyramid networks for fast and accurate super-resolution. Proceedings - 30th IEEE conference on computer vision and pattern recognition, CVPR 2017 2017-Janua:5835–5843. https://doi.org/10.1109/CVPR.2017.618

    Google Scholar 

  13. Lai WS, Bin Huang J, Ahuja N, Yang MH (2018) Fast and accurate image super-resolution with deep Laplacian pyramid networks. IEEE Trans Pattern Anal Mach Intell 41(11):2599–2613. https://doi.org/10.1109/TPAMI.2018.2865304

    Article  Google Scholar 

  14. Hu Y, Gao X, Li J, Huang Y, Wang H (2018) Single image super-resolution via cascaded multi-scale cross network. arXiv:1802.08808v1

  15. Cao F, Chen B (2019) New architecture of deep recursive convolution networks for super-resolution. Knowl-Based Syst 178:98–110. https://doi.org/10.1016/j.knosys.2019.04.021

    Article  Google Scholar 

  16. Zeng K, Ding S, Jia W (2019) Single image super-resolution using a polymorphic parallel CNN. Appl Intell 49:292–300. https://doi.org/10.1007/s10489-018-1270-7

    Article  Google Scholar 

  17. Tang Y, Gong W, Yi Q, Li W (2018) Combining sparse coding with structured output regression machine for single image super-resolution. Inf Sci 430–431:577–598. https://doi.org/10.1016/j.ins.2017.12.001, ISSN 0020255

    Article  Google Scholar 

  18. Hao F, Zhang T, Zhao L, et al. (2021) Efficient residual attention network for single image super-resolution. Appl Intell. https://doi.org/10.1007/s10489-021-02489-x

  19. Shi W, et al. (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 1874–1883

  20. Han W, Chang S, Liu D, Yu M, Witbrock M (2018) Image super-resolution via dual-state recurrent networks, (CVPR), https://doi.org/10.1109/CVPR.2018.00178

  21. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proc. Int Conf Mach Learn, pp 448–456

  22. Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. In: european conference on computer vision (ECCV), pp 391–407

  23. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 770–778

  24. Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873

    Article  MathSciNet  MATH  Google Scholar 

  25. Bevilacqua M, Roumy A, Guillemot C, Alberi Morel ML (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: BMVC, pp 1–10

  26. Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: CVPR, pp 416–423

  27. Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: Curves and surfaces, pp 711–730

  28. Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: IEEE international conference on computer vision and pattern recognition (CVPR), pp 5197–5206

  29. Timofte R, De Smet V, Van Gool L (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Asian conference on computer vision. Springer, pp 111–126

Download references

Author information

Authors and Affiliations

  1. National Mobile Communication Research Laboratory, Southeast University, Nanjing, China

    Faisal Sahito & Pan Zhiwen

  2. College of Electronic and Communication Engineering, Beijing University of Posts and Telecommunication, Beijing, China

    Fahad Sahito

  3. Department of Electrical Engineering, Sukkur IBA University, Sukkur, 65200, Pakistan

    Junaid Ahmed

Authors
  1. Faisal Sahito
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pan Zhiwen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fahad Sahito
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Junaid Ahmed
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Faisal Sahito.

Ethics declarations

I certify that there is no actual or potential conflict of interest in relation to this article.

Associated data will be made available on reasonable request.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sahito, F., Zhiwen, P., Sahito, F. et al. Transpose convolution based model for super-resolution image reconstruction. Appl Intell 53, 10574–10584 (2023). https://doi.org/10.1007/s10489-022-03745-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03745-4

Keywords

Search

Navigation