SpringerLink
Log in

A comprehensive review of image denoising in deep learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Deep learning has gained significant interest in image denoising, but there are notable distinctions in the types of deep learning methods used. Discriminative learning is suitable for handling Gaussian noise, while optimization models are effective in estimating real noise. However, there is limited research that summarizes the different deep learning techniques for image denoising. This paper conducts a comprehensive review of techniques and methods used for image denoising and identifying challenges associated with existing approaches. In this paper, a comparative study of deep techniques is offered in image denoising. The study conducted a comprehensive review of 68 papers on image denoising published between 2018 and 2023, providing a detailed analysis of the field’s progress and methodologies over a period of 5 years. Through its literature review, the paper provides a comprehensive summary of image denoising in deep learning, including machine learning methods for image denoising, CNNs for image denoising, additive white noisy-image denoising, real noisy image denoising, blind denoising, hybrid noisy images, state- of-the-art methods for image denoising with deep learning, salt and pepper noise, non-linear filters for digital color images. The main objective of this paper is to provide a comprehensive overview of various approaches used for image denoising, each of which has been explored and developed based on individual research studies. The paper aims to discuss these approaches in a systematic and organized manner, comparing their strengths and weaknesses to provide insights for future research in the field.

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

Access this article

Log in via an institution

Price includes VAT (Germany)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

All the data is collected from the simulation reports of the software and tools used by the authors. Authors are working on implementing the same using real world data with appropriate permissions.

References

  1. Gupta A, Bhateja V, Srivastava A, Gupta A, Satapathy SC (2019) Speckle noise suppression in ultrasound images by using an improved non-local mean filter. In: Soft Computing and Signal Processing: Proceedings of ICSCSP 2018, Volume 2 (pp. 13–19). Springer Singapore

  2. Awad A (2019) Denoising images corrupted with impulse, Gaussian, or a mixture of impulse and gaussian noise. Eng Sci Technol Int J 22(3):746–753

    Google Scholar 

  3. Randhawa SK, Sunkaria RK, Puthooran E (2019) Despeckling of ultrasound images using novel adaptive wavelet thresholding function. Multidimens Syst Signal Process 30:1545–1561

    Google Scholar 

  4. Shin YH, Park MJ, Lee OY, Kim JO (2020) Deep orthogonal transform feature for image denoising. IEEE Access 8:66898–66909

    Google Scholar 

  5. El Helou M, Süsstrunk S (2020) Blind universal bayesian image denoising with gaussian noise level learning. IEEE Trans Image Process 29:4885–4897

    Google Scholar 

  6. Sun H, Peng L, Zhang H, He Y, Cao S, Lu L (2021) Dynamic PET image denoising using deep image prior combined with regularization by denoising. IEEE Access 9:52378–52392

    Google Scholar 

  7. Zin T, Seta S, Nakahara Y, Yamaguchi T, Ikehara M (2022) Local image denoising using RAISR. IEEE Access 10:22420–22428

    Google Scholar 

  8. Li Z, Liu H, Cheng L, Jia X (2023) Image denoising algorithm based on gradient domain guided filtering and NSST. IEEE Access 11:11923–11933

    Google Scholar 

  9. Zhang D, Zhou F (2023) Self-supervised image denoising for real-world images with context-aware transformer. IEEE Access 11:14340–14349

    Google Scholar 

  10. Park HS, Baek J, You SK, Choi JK, Seo JK (2019) Unpaired image denoising using a generative adversarial network in X-ray CT. IEEE Access 7:110414–110425

    Google Scholar 

  11. Cui J, Gong K, Guo N, Wu C, Meng X, Kim K, Zheng K, Wu Z, Fu L, Xu B, Zhu Z (2019) PET image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging 46:2780–2789

    Google Scholar 

  12. Wang X, Li Z, Shan H, Tian Z, Ren Y, Zhou W (2020) Fastderainnet: a deep learning algorithm for single image deraining. IEEE Access 8:127622–127630

    Google Scholar 

  13. Tian M, Song K (2021) Boosting magnetic resonance image denoising with generative adversarial networks. IEEE Access 9:62266–62275

    Google Scholar 

  14. Bayhaqi YA, Hamidi A, Canbaz F, Navarini AA, Cattin PC, Zam A (2022) Deep-learning-based fast Optical Coherence Tomography (OCT) image denoising for smart laser osteotomy. IEEE Trans Med Imaging 41(10):2615–2628

    Google Scholar 

  15. Sereethavekul W, Ekpanyapong M (2023) Adaptive lightweight license plate image recovery using deep learning based on generative adversarial network. IEEE Access 11:26667–26685

    Google Scholar 

  16. Hashimoto F, Ohba H, Ote K, Teramoto A, Tsukada H (2019) Dynamic PET image denoising using deep convolutional neural networks without prior training datasets. IEEE Access 7:96594–96603

    Google Scholar 

  17. Wang F, Huang H, Liu J (2019) Variational-based mixed noise removal with CNN deep learning regularization. IEEE Trans Image Process 29:1246–1258

    MathSciNet  Google Scholar 

  18. Zhang X, Gao P, Zhao K, Liu S, Li G, Yin L (2020) Image restoration via deep memory-based latent attention network. IEEE Access 8:104728–104739

    Google Scholar 

  19. Lan R, Zou H, Pang C, Zhong Y, Liu Z, Luo X (2021) Image denoising via deep residual convolutional neural networks. SIViP 15:1–8

    Google Scholar 

  20. Rawat S, Rana KPS, Kumar V (2021) A novel complex-valued convolutional neural network for medical image denoising. Biomed Signal Process Control 69:102859

    Google Scholar 

  21. Gurrola-Ramos J, Dalmau O, Alarcón TE (2021) A residual dense u-net neural network for image denoising. IEEE Access 9:31742–31754

    Google Scholar 

  22. Meng Y, Zhang J (2022) A novel gray image denoising method using convolutional neural network. IEEE Access 10:49657–49676

    Google Scholar 

  23. Zhang Q, **ao J, Tian C, Chun‐Wei Lin J, Zhang S (2023) A robust deformed convolutional neural network (CNN) for image denoising. CAAI Transactions on Intelligence Technology 8(2):331–342

  24. Lee SE, Woo SM, Kim JH, Ryu JH, Kim JO (2022) Deep region adaptive denoising for texture enhancement. IEEE Access 10:122286–122301

    Google Scholar 

  25. Holla S, Park N, Lee B (2023) EFID: edge-focused image denoising using a convolutional neural network. IEEE Access 11:9613–9626

    Google Scholar 

  26. Shi P, **a H, Han D, Fu R, Yuan D (2018) Stochastic resonance in a time polo-delayed asymmetry bistable system driven by multiplicative white noise and additive color noise. Chaos Solitons Fractals 108:8–14

    MathSciNet  Google Scholar 

  27. Khmag A, Ramli AR, Al-Haddad SAR, Kamarudin N (2018) Natural image noise level estimation based on local statistics for blind noise reduction. Visual Comput 34:575–587

    Google Scholar 

  28. Chen J, Rui Z (2018) Dimension-reduced FPK equation for additive white-noise excited nonlinear structures. Probab Eng Mech 53:1–13

    Google Scholar 

  29. Dytso A, Cardone M, Poor HV (2019) On estimating the norm of a gaussian vector under additive white gaussian noise. IEEE Signal Process Lett 26(9):1325–1329

    Google Scholar 

  30. Soverini U, Söderström T (2020) Frequency domain identification of FIR models in the presence of additive input–output noise. Automatica 115:108879

    MathSciNet  Google Scholar 

  31. Akinlar MA, Inc M, Gómez-Aguilar JF, Boutarfa B (2020) Solutions of a disease model with fractional white noise. Chaos Solitons Fractals 137:109840

    MathSciNet  Google Scholar 

  32. Zhu Q, Wu N, Qiao Y, Zhou M (2016) Optimal scheduling of complex multi-cluster tools based on timed resource-oriented Petri nets. IEEE Access 4:2096–2109

    Google Scholar 

  33. Xu J, Zhang L, Zhang D (2018) External prior guided internal prior learning for real-world noisy image denoising. IEEE Trans Image Process 27(6):2996–3010

    MathSciNet  Google Scholar 

  34. Zhang K, Zuo W, Zhang L (2018) FFDNet: toward a fast and flexible solution for CNN-based image denoising. IEEE Trans Image Process 27(9):4608–4622

    MathSciNet  Google Scholar 

  35. Zhao Y, Jiang Z, Men A, Ju G (2019) Pyramid real image denoising network. In: 2019 IEEE Visual Communications and Image Processing (VCIP). IEEE, pp 1–4

  36. Chen C, **ong Z, Tian X, Zha ZJ, Wu F (2019) Real-world image denoising with deep boosting. IEEE Trans Pattern Anal Mach Intell 42(12):3071–3087

    Google Scholar 

  37. Song Y, Zhu Y, Du X (2020) Grouped multi-scale network for real-world image denoising. IEEE Signal Process Lett 27:2124–2128

    Google Scholar 

  38. Chen J, Zhang G, Xu S, Yu H (2019) A blind CNN denoising model for random-valued impulse noise. IEEE Access 7:124647–124661

    Google Scholar 

  39. ** Y, Zhang J, Ai B, Zhang X (2019) Channel estimation for mmWave massive MIMO with convolutional blind denoising network. IEEE Commun Lett 24(1):95–98

    Google Scholar 

  40. Zhu S, Xu G, Cheng Y, Han X, Wang Z (2019) BDGAN: Image blind denoising using generative adversarial networks. In: Pattern Recognition and Computer Vision: Second Chinese Conference, PRCV 2019, **’an, China, November 8–11, 2019, Proceedings, Part II 2 (pp. 241–252). Springer International Publishing

  41. Goncharova AS, Honigmann A, Jug F, Krull A (2020) Improving blind spot denoising for microscopy. In: Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16 (pp. 380–393). Springer International Publishing

  42. Vo DM, Nguyen DM, Le TP, Lee SW (2021) HI-GAN: a hierarchical generative adversarial network for blind denoising of real photographs. Inf Sci 570:225–240

    MathSciNet  Google Scholar 

  43. Yuan Y, Ma H, Liu G (2021) Partial-DNet: a novel blind denoising model with noise intensity estimation for HSI. IEEE Trans Geosci Remote Sens 60:1–13

    Google Scholar 

  44. Routray S, Ray AK, Mishra C, Palai G (2018) Efficient hybrid image denoising scheme based on SVM classification. Optik 157:503–511

    Google Scholar 

  45. Nourani V, Partoviyan A (2018) Hybrid denoising-jittering data pre-processing approach to enhance multi-step-ahead rainfall–runoff modeling. Stochastic Environ Res Risk Assess 32(2):545–562

    Google Scholar 

  46. Das K, Maitra M, Sharma P, Banerjee M (2019) Early started hybrid denoising technique for medical images. Recent trends in Signal and Image Processing: ISSIP 2017. Springer Singapore, pp 131–140

  47. Abubakar A, Zhao X, Takruri M, Bastaki E, Bermak A (2020) A hybrid denoising algorithm of BM3D and KSVD for gaussian noise in DoFP polarization images. IEEE Access 8:57451–57459

    Google Scholar 

  48. Kazemi Golbaghi F, Rezghi M, Eslahchi MR (2020) A hybrid image denoising method based on integer and fractional-order total variation. Iran J Sci Technol Trans A: Sci 44:1803–1814

    MathSciNet  Google Scholar 

  49. Kaur C, Bisht A, Singh P, Joshi G (2021) EEG Signal denoising using hybrid approach of Variational Mode Decomposition and wavelets for depression. Biomed Signal Process Control 65:102337

    Google Scholar 

  50. Manjón JV, Coupe P (2018) MRI denoising using deep learning. In: Patch-Based Techniques in Medical Imaging: 4th International Workshop, Patch-MI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4 (pp. 12–19). Springer International Publishing

  51. Gondara L, Wang K (2018) Mida: Multiple imputation using denoising autoencoders. In: Advances in Knowledge Discovery and Data Mining: 22nd Pacific-Asia Conference, PAKDD 2018, Melbourne, VIC, Australia, June 3–6, 2018, Proceedings, Part III 22 (pp. 260–272). Springer International Publishing

  52. Tassano M, Delon J, Veit T (2019) Dvdnet: A fast network for deep video denoising. In: 2019 IEEE International Conference on Image Processing (ICIP) (pp. 1805–1809). IEEE

  53. Davy A, Ehret T, Morel JM, Arias P, Facciolo G (2019) A non-local CNN for video denoising. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE, pp 2409–2413

  54. Liu P, Basha E, Li MD, **ao Y, Sanelli Y, Fang R (2019) Deep evolutionary networks with expedited genetic algorithms for medical image denoising. Med Image Anal 54:306–315

    Google Scholar 

  55. Thanh DN, Prasath VS, Erkan U (2019). An improved BPDF filter for high density salt and pepper denoising. In: 2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF) (pp. 1–5). IEEE

  56. Fu B, Zhao X, Song C, Li X, Wang X (2019) A salt and pepper noise image denoising method based on the generative classification. Multimed Tools Appl 78:12043–12053

    Google Scholar 

  57. Thanh DN, Hai NH, Prasath VS, Hieu LM, Tavares JMR (2020) A two-stage filter for high density salt and pepper denoising. Multimed Tools Appl 79(29–30):21013–21035

    Google Scholar 

  58. Thanh DNH, Hien NN, Prasath S (2020) Adaptive total variation L1 regularization for salt and pepper image denoising. Optik 208:163677

    Google Scholar 

  59. Liang L, Deng S, Gueguen L, Wei M, Wu X, Qin J (2021) Convolutional neural network with median layers for denoising salt-and-pepper contaminations. Neurocomputing 442:26–35

    Google Scholar 

  60. Wang G, Liu Y, **ong W, Li Y (2018) An improved non-local means filter for color image denoising. Optik 173:157–173

    Google Scholar 

  61. Tsoutsanis P (2018) Extended bounds limiter for high-order finite-volume schemes on unstructured meshes. J Comput Phys 362:69–94

    MathSciNet  Google Scholar 

  62. Punarselvam E, Suresh P (2019) Non-linear filtering technique used for testing the human lumbar spine FEA model. J Med Syst 43:1–13

    Google Scholar 

  63. Manju BR, Sneha MR (2020) ECG denoising using Wiener filter and kalman filter. Procedia Comput Sci 171:273–281

    Google Scholar 

  64. Kaur M, Sarkar RK, Dutta MK (2021) Investigation on quality enhancement of old and fragile artworks using non-linear filter and histogram equalization techniques. Optik 244:167564

    Google Scholar 

  65. Fu B, Dong Y, Fu S, Wu Y, Ren Y, Thanh DN (2023) Multistage supervised contrastive learning for hybrid-degraded image restoration. SIViP 17(2):573–581

    Google Scholar 

  66. Fu B, Zhang X, Wang L, Ren Y, Thanh DN (2022) Double enhanced residual network for biological image denoising. Gene Expr Patterns 45:119270

    Google Scholar 

  67. Fu B, Zhang X, Wang L, Ren Y, Thanh DN (2022) A blind medical image denoising method with noise generation network. J X-Ray Sci Technol 30(3):531–547

    Google Scholar 

  68. Fu B, Dong Y, Fu S, Mao Y, Thanh DN (2022) Learning domain transfer for unsupervised magnetic resonance imaging restoration and edge enhancement. Int J Imaging Syst Technol 32(1):144–154

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Information and Communication Technology, UniTeN, Kuala Lumpur, Malaysia

    Rusul Sabah Jebur

  2. Department of Computing College of Computing and Informatics, Universiti Tenaga National UniTeN, Kuala Lumpur, Malaysia

    Mohd Hazli Bin Mohamed Zabil & Lim Kok Cheng

  3. Electrical Engineering Technical College, Middle Technical University (MTU), 10022, Baghdad, Iraq

    Dalal Adulmohsin Hammood

Authors
  1. Rusul Sabah Jebur
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohd Hazli Bin Mohamed Zabil
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dalal Adulmohsin Hammood
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lim Kok Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rusul Sabah Jebur.

Ethics declarations

Data sharing

Not applicable.

Conflict of interest

The authors declare that we have no conflict of interest.

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

Jebur, R.S., Zabil, M.H.B.M., Hammood, D.A. et al. A comprehensive review of image denoising in deep learning. Multimed Tools Appl 83, 58181–58199 (2024). https://doi.org/10.1007/s11042-023-17468-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-17468-2

Keywords

Search

Navigation