Skip to main content

Advertisement

Springer Nature Link
Log in

CEPDNet: a fast CNN-based image denoising network using edge computing platform

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Edge-preserving denoising is important in image analysis such as image segmentation, object detection and biometric recognition. However, most of the existing image denoising methods suffer from the smoothness of high-frequency edge details and high computational complexity in the inference stage. Aiming at this issue, we propose a CNN and tensorRT-based edge-preserving denoising network and complete the deployment and inference acceleration on the edge computing platform through model optimization. Specifically, first, a parallel edge extraction module including wavelet transform and threshold unit is designed to generate the de-redundant edge information from the noisy image. Then, the edge is used as a prior to generate affine transform parameters to improve the weight distribution between the noise features and the edge features, allowing the network to focus more on learning the noise features other than the high-frequency information at the edges. In the deep feature extraction stage, the spatial neighborhood information of feature points is obtained via a newly constructed multi-scale attention module, which is employed to activate the deep features and further improve the ability of the network to extract noise features. Finally, the computational efficiency of the model in the inference stage is further improved through the optimization of the training model with lightweight network design and TensorRT. Extensive experimental results show that the proposed method can effectively preserve image edge details while maintaining a higher inference speed, i.e., a denoising frame rate of about 40fps at the image resolution of 256 × 256.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Data availability

The public datasets are used in this study. No new data were created or analyzed. Data sharing is not applicable to this article. The SIDD datasets can be found here (http://www.cs.yorku.ca/~kamel/sidd/dataset.php, accessed on 1 August 2024).

References

  1. Zhang SS, Lam E (2021) Learning to restore light fields under low-light imaging. Neurocomputing 456:76–87

    Article  Google Scholar 

  2. Goyal B, Dogra A, Agrawal S, Sohi BS, Sharma A (2020) Image denoising review: from classical to state-of-the-art approaches. Inform fusion 55:220–244

    Article  Google Scholar 

  3. Xu X, Wang QD, Guo LL, Zhang J, Ding SF (2023) FEMRNet: feature-enhanced multi-scale residual network for image denoising. Appl Intell 53:26027–26049

    Article  Google Scholar 

  4. Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans Image Process 16:2080–2095

    Article  MathSciNet  Google Scholar 

  5. Gu SH, Zhang L, Zuo WM, Feng XC (2014) Weighted nuclear norm minimization with application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp 2862–2869

  6. Chiang YW, Sullivan BJ (1989) Multi-frame image restoration using a neural network. In: Proceedings of the 32nd Midwest Symposium on Circuits and Systems, Champaign, IL, USA, 14–16 August 1989, pp 744–747

  7. Zhang K, Zuo WM, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE T Image Process 26:3142–3155

    Article  MathSciNet  Google Scholar 

  8. Zhang K, Zuo WM, Zhang L (2018) FFDNet: toward a fast and flexible solution for CNN-based image denoising. IEEE T Image Process 27:4608–4622

    Article  MathSciNet  Google Scholar 

  9. Guo S, Yan ZF, Zhang K, Zuo WM, Zhang L (2019) Toward convolutional blind denoising of real photographs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019, pp 1712–1722

  10. Wu CZ, Chen X, Zhan S (2020) Remote sensing image denoising using residual encoder-decoder networks with edge enhancement. Natl Remote Sens Bull 24:27–36

    Article  Google Scholar 

  11. Chen JW, Chen JW, Chao HY, Yang M (2018) Image blind denoising with generative adversarial network based noise modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018, pp 3155–3164

  12. Tian CW, Xu Y, Li ZY, Zuo WM, Fei LK, Liu H (2020) Attention-guided CNN for image denoising. Neural netw 124:117–129

    Article  Google Scholar 

  13. Tian C, Xu Y, Zuo W (2020) Image denoising using deep CNN with batch renormalization. Neural Netw 121:461–473

    Article  Google Scholar 

  14. Zhang S, Liu CY, Zhang YX, Liu S, Wang X (2023) Multi-scale feature learning convolutional neural network for image denoising. Sensors 23(18):7713

    Article  Google Scholar 

  15. Gou Y, Hu P, Lv J, Zhou JT, Peng X (2022) Multi-scale adaptive network for single image denoising. arXiv 2022, arXiv:eess.IV/2203.04313

  16. Jia XL, Peng YL, Ge B, Li J, Liu SG, Wang WA (2022) A multi-scale dilated residual convolution network for image denoising. Neural Process Lett 55:1231–1246

    Article  Google Scholar 

  17. Tian CW, Zhang MH, Zuo WM, Zhang SC, Zhang YN, Lin CW (2024) A cross transformer for image denoising. Inf Fusion 102:102043

    Article  Google Scholar 

  18. He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016, pp 770–778

  19. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 21–26 July 2017, pp 1063–6919

  20. Ma KD, Duanmu ZF, Wu QB, Wang Z, Yong HW, Li HL, Zhang L (2016) Waterloo exploration database: new challenges for image quality assessment models. IEEE T Image Process 26:1004–1016

    Article  MathSciNet  Google Scholar 

  21. Roth S, Black MJ (2005) Fields of experts: a framework for learning image priors. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, 20–25 June 2005, pp 860–867

  22. Zoran D, Weiss Y (2011) From learning models of natural image patches to whole image restoration. In: Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain, 6–13 November 2011, pp 479–486

  23. Zhang K, Zuo WM, Gu SH, Zhang L (2017) Learning deep cnn denoiser prior for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017, pp 3929–3938

  24. Chen Y, Pock T (2016) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans Pattern Anal Mach Intell 39:1256–1272

    Article  Google Scholar 

  25. Tian CW, Xu Y, Zuo WM, Du B, Lin CW, Zhang D (2021) Designing and training of a dual CNN for image denoising. Knowl Based Syst 226:106949

    Article  Google Scholar 

  26. Jia XL, Peng YL, Ge B, Li J, Liu SG, Wang WN (2023) A multi-scale dilated residual convolution network for image denoising. Neural Process Lett 55:1231–1246

    Article  Google Scholar 

  27. Xu J, Zhang L, Zhang D (2018) A trilateral weighted sparse coding scheme for real-world image denoising. In: Proceedings of the European Conference on Computer Vision, Munich, Germany, 8–14 September 2018, pp 21–38

  28. Anwar S, Barnes N (2019) Real image denoising with feature attention. In: Proceedings of the International Conference on Computer Vision. Seoul, Korea (South), 27 October–2 November 2019, pp 3155–3164

  29. Kim Y, Soh JW, Park GY, Cho NI (2020) Transfer learning from synthetic to real-noise denoising with adaptive instance normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020, pp 3482–3492

  30. Chang M, Li Q, Feng H, Zhihai X (2020) Spatial-adaptive network for single image denoising. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, proceedings. Springer International Publishing, Cham, pp 171–187

    Chapter  Google Scholar 

  31. Du Y, Han GQ, Tan YJ, Xiao CF, He SF (2021) Blind image denoising via dynamic dual learning. IEEE T Multimedia 23:2139–2152

    Article  Google Scholar 

  32. Quan YH, Chen YX, Shao YZ, Teng H, Xu Y, Ji H (2021) Image denoising using complex-valued deep CNN. Pattern Recognit 111:107639

    Article  Google Scholar 

  33. Zhang YL, Tian YP, Kong Y, Zhong BN, Fu Y (2021) Residual dense network for image restoration. IEEE Trans Pattern Anal Mach Intell 43:2480–2495

    Article  Google Scholar 

  34. Zhou YL, Fu XJ (2021) Image denoising based on dual-tree complex wavelet transform and convolutional neural network. J Phys Conf Ser 1995:012030

    Article  Google Scholar 

  35. Zhu J, Yao C, Tang Y, Gao Y, Zhou L, Hongmei H (2022) MRDA-Net: multiscale residual dense attention network for image denoising. In: Sun X, Zhang X, Xia Z, Bertino E (eds) Advances in artificial intelligence and security: 8th International Conference on Artificial Intelligence and Security. Springer International Publishing, Cham, pp 213–230

    Chapter  Google Scholar 

  36. Xu M, Xie X (2022) NFCNN: toward a noise fusion convolutional neural network for image denoising. Signal Image Video Process 16:175–183

    Article  Google Scholar 

  37. Jiang B, Lu Y, Wang JH, Lu GM, Zhang DF (2022) Deep image denoising with adaptive priors. IEEE Trans Circuits Syst Video Technol 32:5124–5136

    Article  Google Scholar 

  38. Geng MF, Meng XX, Yu JY, Zhu L, Jin LJ, Jiang Z, Qiu B, Li H, Kong HJ, Yuan JM, Yang K, Shan HM, Han HB, Yang Z, Ren QS, Lu YY (2022) Content-noise complementary learning for medical image denoising. IEEE T Med Imaging 41:407–419

    Article  Google Scholar 

  39. Xu JZ, Yuan MK, Yan DM, Wu TR (2023) Deep unfolding multi-scale regularizer network for image denoising. Comp Visual Media 9:335–350

    Article  Google Scholar 

  40. Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang MH, Shao L (2023) Learning enriched features for real image restoration and enhancement. IEEE T Pattern Anal 45:1934–1948

    Article  Google Scholar 

  41. Tian CW, Zheng MH, Zuo WM, Zhang B, Zhang YN, Zhang D (2023) Multi-stage image denoising with the wavelet transform. Pattern Recognit 134:109050

    Article  Google Scholar 

  42. Liu K, Guo YP, Su BY (2023) Image denoising network based on subband information sharing using dual-tree complex wavelet. Neural Process Lett 55:10975–10991

    Article  Google Scholar 

  43. Tao H, Guo W, Han R, Yang Q, Zhao J (2023) RDASNet: image denoising via a residual dense attention similarity network. Sensors 23(3):1486. https://doi.org/10.3390/s23031486

    Article  Google Scholar 

  44. Wu J, Wu H, Yuan GW (2024) Detail-aware image denoising via structure preserved network and residual diffusion model. Vis Comput. https://doi.org/10.1007/s00371-024-03353-y

    Article  Google Scholar 

  45. Feng SL, Qi ZS, Zhang GR, Lin C, Huang MX (2024) FCNet: a deep neural network based on multi-channel feature cascading for image denoising. J Supercomput 80:17042–17067

    Article  Google Scholar 

  46. Zhao SB, Lin S, Cheng X, Zhou KX, Zhang M, Wang H (2024) Dual-GAN complementary learning for real-world image denoising. IEEE Sens J 24:355–366

    Article  Google Scholar 

  47. Ding SF, Wang QD, Guo LL, Li X, Ding L, Wu XD (2024) Wavelet and adaptive coordinate attention guided fine-grained residual network for image denoising. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2023.3348804

    Article  Google Scholar 

  48. Meng JY, Wang FQ, Liu J (2024) Learnable nonlocal self-similarity of deep features for image denoising. Siam J Imaging Sci. https://doi.org/10.1137/22m1536996

    Article  MathSciNet  Google Scholar 

  49. Zhou YQ, Jiao JB, Huang HB, Wang Y, Wang J, Shi HS, Huang T (2020) When awgn-based denoiser meets real noises. In: Proceedings of the AAAI Conference on Artificial Intelligence, New York, USA, 7–12 February 2020; pp 13074–13081

  50. Abdelhamed A, Lin S, Brown MS (2018) A high-quality denoising dataset for smartphone cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018, pp 1692–1700

  51. Nam S, Hwang Y, Matsushita Y, Kim SJ (2016) A holistic approach to cross-channel image noise modeling and its application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016, pp 1683–1691

Download references

Acknowledgements

The authors would like to thank the anonymous reviewers for their valuable comments.

Funding

This research was funded by the project program of Science and Technology on Micro-system Laboratory, grant number 6142804231002; the Natural Science Foundation of Hebei Province, grant number F2022210013; the Natural Science Foundation of Hebei Province Department of Education, grant number QN2022044.

Author information

Authors and Affiliations

  1. Hebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment, School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China

    Xuefei Bai

  2. School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China

    Xuefei Bai & Yongsong Wan

  3. Laboratory of Micro-Nano Sensor Technology, Xiong’an Institute of Innovation, Xiong’an, 071800, China

    Weiming Wang

Authors
  1. Xuefei Bai
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yongsong Wan
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Weiming Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Conceptualization, methodology, data curation, writing—original draft preparation and project administration were contributed by X.B.; software, investigation, resources and visualization were involved by Y.W.; validation was performed by Y.W. and W.W.; formal analysis, writing—review and editing and supervision W.W.; funding acquisition was done by X.B. and W.W. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Xuefei Bai.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

Not applicable.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bai, X., Wan, Y. & Wang, W. CEPDNet: a fast CNN-based image denoising network using edge computing platform. J Supercomput 81, 100 (2025). https://doi.org/10.1007/s11227-024-06646-0

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06646-0

Keywords