SpringerLink
Log in

KinD-LCE: curve estimation and Retinex Fusion on low-light image

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Low-light images often suffer from noise and color distortion. Object detection, semantic segmentation, instance segmentation, and other tasks are challenging when working with low-light images because of image noise and chromatic aberration. We also found that the conventional Retinex theory loses information in adjusting the image for low-light tasks. In response to the aforementioned problem, this paper proposes an algorithm for low illumination enhancement. The proposed method, KinD-LCE, uses a light curve estimation module to enhance the illumination map in the Retinex decomposed image, improving the overall image brightness. An illumination map and reflection map fusion module were also proposed to restore the image details and reduce detail loss. Additionally, a TV(total variation) loss function was applied to eliminate noise. Our method was trained on the GladNet dataset, known for its diverse collection of low-light images, tested against the Low-Light dataset, and evaluated using the ExDark dataset for downstream tasks, demonstrating competitive performance with a PSNR of 19.7216 and SSIM of 0.8213.

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
EUR 32.99 /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 includes VAT (France)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Availability of data and materials

The data that support the findings of this study are available on request from thecorresponding author, Jiang, upon reasonable request.

References

  1. Pizer, S.M. et al.: Adaptive histogram equalization and its variations. Comput. Vision, Gr., Image Process 39.3 (1987).

  2. Land, E.H. and McCann, J.J.: Lightness and retinex theory. Josa 61.1, (1971).

  3. Zhou, J., Zhang, D., Zhang, W.: Multiscale fusion method for the enhancement of low-light underwater images. Math. Probl. Eng. 2020, 1–15 (2020)

    CAS  Google Scholar 

  4. Jobson, D.J., Rahman, Z.-u, Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997)

    Article  CAS  PubMed  ADS  Google Scholar 

  5. Liu, R. et al. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2021).

  6. Yan, M., Lou, X., Chan, C.A., Wang, Y., Jiang, W.: A semantic and emotion-basedlatent variable generation model for a dialogue system. CAAI Trans. Intell. Technol. 2023, 1–12 (2023). https://doi.org/10.1049/cit2.12153

    Article  Google Scholar 

  7. Guo, C., et al.: Zero-reference deep curve estimation for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2020).

  8. Rahman, Z., et al.: Efficient image enhancement model for correcting uneven illumination images. IEEE Access 8, 109038–109053 (2020)

    Article  Google Scholar 

  9. Li, C. et al.: Learning to enhance low-light image via zero-reference deep curve estimation" IEEE Transactions on Pattern Analysis and Machine Intelligence. (2021)

  10. Zhang, Y., Zhang, J. and Guo, X.: Kindling the darkness: a practical low-light image enhancer." Proceedings of the 27th ACM International Conference on Multimedia. (2019).

  11. Zhang, Y. et al.: Beyond brightening low-light images. Int. J. Comput. Vision 129.4 (2021).

  12. Jiang, Y., et al.: EnlightenGAN: deep light enhancement without paired supervision. IEEE Transact. Image Process. 30, 2340–2349 (2021)

    Article  ADS  Google Scholar 

  13. **e, J., et al.: Semantically-guided low-light image enhancement. Pattern Recognit. Lett. 138, 308–314 (2020)

    Article  ADS  Google Scholar 

  14. Guan, Y., et al.: A dual-tree complex wavelet transform-based model for low-illumination image enhancement. Wuhan Univ. J. Nat. Sci. 26.05, 405–414 (2021)

    Google Scholar 

  15. Rahman, Z., et al.: "Structure revealing of low-light images using wavelet transform based on fractional-order denoising and multiscale decomposition. Vis. Comput. 375, 865–880 (2021)

    Article  Google Scholar 

  16. Liu, Y. et al.: Image fusion with convolutional sparse representation. IEEE Signal Process. Lett. 23.12 (2016).

  17. Yan, M., Chan, C.A., Li, W., Chih-Lin, L., Bian, S., Gygax, A.F., Leckie, C., Hinton, K., Wong, E., Nirmalathas, A.: Network energy consumption assessment of conventional mobile services and over-the-top instant messaging applications. IEEE J. Sel. Areas Commun. 34(12), 3168–3180 (2016)

    Article  Google Scholar 

  18. Yan, M., Li, W., Chan, C.A., Bian, S., Chih-Lin, I., Gygax, A.F.: "PECS: towards personalized edge caching for future service-centric networks. China Commun. 16(8), 93–106 (2019)

    Article  CAS  Google Scholar 

  19. Ying, Z. Li, G. and Gao, W.: A bio-inspired multi-exposure fusion framework for low-light image enhancement. ar**v preprint ar**v:1711.00591 (2017).

  20. Ying, Z. et al.: A new image contrast enhancement algorithm using exposure fusion framework. International Conference on Computer Analysis of Images and Patterns. Springer, Cham, (2017).

  21. Gharbi, M. et al.: Deep bilateral learning for real-time image enhancement. ACM Transact. Gr. (TOG), 36.4, (2017).

  22. Li, C. et al.: Low-light image and video enhancement using deep learning: a survey. IEEE Transactions on Pattern Analysis & Machine Intelligence, 01, (2021).

  23. Guo, X., Li, Y. and Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Transact. Image Process. 26.2 (2016).

  24. Lore, K.G., Akintayo, A. and Sarkar, S. LLNet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recog. 61 (2017).

  25. Rudin, Leonid I., Stanley Osher, and Emad Fatemi. "Nonlinear total variation based noise removal algorithms." Physica D: nonlinear phenomena 60.1–4 (1992).

  26. Wei, C. et al.: Deep retinex decomposition for low-light enhancement. ar**v preprint ar**v:1808.04560 (2018).

  27. Wang, W. et al.: Gladnet: Low-light enhancement network with global awareness. 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE, (2018).

  28. Loh, Y.P., Chan, C.S.: Getting to know low-light images with the exclusively dark dataset. Comput. Vis. Image Underst. 178, 30–42 (2019)

    Article  Google Scholar 

  29. Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image/video quality assessment. Electron. Lett. 44(13), 800–801 (2008)

    Article  ADS  Google Scholar 

  30. Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Transact Image Process. 134, 600–612 (2004)

    Article  ADS  Google Scholar 

  31. Lv, F. et al.: MBLLEN: low-light image/video enhancement using CNNs. BMVC. 220(1) (2018).

  32. Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. European conference on computer vision. Springer, Cham (2020)

    Book  Google Scholar 

  33. Cordts, M. et al.: The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

Download references

Funding

This work was supported by the National Natural Science Foundation of China (61876049, 62172118) and Nature Science key Foundation of Guangxi (2021GXNSFDA196002); in part by the Sichuan Regional Innovation Cooperation Project (2021YFQ0002); in part by the Guangxi Key Laboratory of Image and Graphic Intelligent Processing under Grants (GIIP2004) and Student’s Platform for Innovation and Entrepreneurship Training Program under Grant (202010595053, 202010595168, S202110595168, 202110595025, 202310595036).

Author information

Authors and Affiliations

  1. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin Guangxi, 541004, China

    **aochun Lei, Weiliang Mai, Junlin **e, He Liu, Zetao Jiang, Zhaoting Gong, Chang Lu & Linjun Lu

  2. Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin Guangxi, 541004, China

    **aochun Lei & Zetao Jiang

Authors
  1. **aochun Lei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Weiliang Mai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Junlin **e
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. He Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zetao Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhaoting Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Chang Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Linjun Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

XL. and JX. contributed to Conceptualization; JX  and WM contributed to Data Curation; XL and JX contributed to Formal Analysis; JX and XL contributed to Methodology; ZJ and ZG contributed to Supervision; ZS and LL contributed to Validation; LL and CL, ZG and WM contributed to Visualization; XL and JX contributed to Writing original draft preparation, ; ZJ, ZG and WM contributed to Writing review and editing; All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Zetao Jiang.

Ethics declarations

Conflict of interest

No potential conflict of interest was reported by the authors.

Ethical approval

This declaration is “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

Lei, X., Mai, W., **e, J. et al. KinD-LCE: curve estimation and Retinex Fusion on low-light image. SIViP 18, 1733–1746 (2024). https://doi.org/10.1007/s11760-023-02850-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-023-02850-2

Keywords

Search

Navigation