Skip to main content
Springer Nature Link
Log in

Exposure correction by deep curve estimation

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

Abstract

Taking photos with improper exposure settings can produce undesirable over- or under-exposed images. Exposure correction is a technique aiming to restore the appearance of these improperly exposed images. A trend of existing works is to correct both over- and under-exposed images with an unified deep model. However, the black-box nature of deep learning makes these methods lack intuitive explanations and prone to overfitting. Therefore, we propose to alleviate this problem by the combination of deep learning and traditional intensity transformation strategy. Specifically speaking, we firstly propose a curve model composited by gamma transformation and logistic function, which are used to compensate for image brightness and enhance image contrast respectively. Then, we merge the curve model and deep learning into a framework by using a convolution network to estimate the parameters of the curve model. The curve model imposes a constraint on the framework, which brings better interpretability and low risk of overfitting to our method. Experimental results have revealed the effectiveness of our method, and it has achieved satisfactory performance both quantitatively and qualitatively.

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

Similar content being viewed by others

Availability of data and materials

The dataset is public available in the corresponding reference.

Notes

  1. https://en.wikipedia.org/wiki/Logistic_function.

  2. When testing on full-resolution images, Retinex-Net needs two GPUs and other methods only use one.

References

  1. Ramanath, R., Snyder, W.E., Yoo, Y., Drew, M.S.: Color image processing pipeline. IEEE Signal Process. Mag. 22, 34–43 (2005)

    Article  Google Scholar 

  2. Peng, J., Jiang, G., Wang, H.: Adaptive memorization with group labels for unsupervised person re-identification. IEEE Trans. Circuits Syst. Video Technol. 33, 5802–5813 (2023)

    Article  Google Scholar 

  3. Wang, H., Jiang, G., Peng, J., Deng, R., Fu, X.: Towards adaptive consensus graph: multi-view clustering via graph collaboration. IEEE Trans. Multimed. (2022). https://doi.org/10.1109/TMM.2022.3212270

    Article  Google Scholar 

  4. Jiang, G., Peng, J., Wang, H., Mi, Z., Fu, X.: Tensorial multi-view clustering via low-rank constrained high-order graph learning. IEEE Trans. Circuits Syst. Video Technol. 32, 5307–5318 (2022)

    Article  Google Scholar 

  5. Gonzales, R.C., Woods, R.E.: Digital Image Processing, 4th edn. Pearson Education, London (2018)

    Google Scholar 

  6. Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R., Geselowitz, A., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 39, 355–368 (1987)

  7. Kim, J.-Y., Kim, L.-S., Hwang, S.-H.: An advanced contrast enhancement using partially overlapped sub-block histogram equalization. IEEE TCSVT 11, 475–484 (2001)

    Google Scholar 

  8. Bassiou, N., Kotropoulos, C.: Color image histogram equalization by absolute discounting back-off. Comput. Vis. Image Underst. 107, 108–122 (2007)

    Article  Google Scholar 

  9. Yadav, G., Maheshwari, S., Agarwal, A.: Contrast limited adaptive histogram equalization based enhancement for real time video system. In: International Conference on Advances in Computing, Communications and Informatics, pp. 2392–2397 (2014)

  10. Russ, J.C.: The Image Processing Handbook, 5th edn. CRC Press, Boca Raton (2006)

    Book  Google Scholar 

  11. Land, E.H.: The retinex theory of color vision. Sci. Am. 237, 108–129 (1977)

    Article  Google Scholar 

  12. Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE TIP 26, 1–12 (2017)

    MathSciNet  Google Scholar 

  13. Zhang, Q., Yuan, G., Xiao, C., Zhu, L., Zheng, W.-S.: High-quality exposure correction of underexposed photos. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 582–590 (2018)

  14. Zhang, Q., Nie, Y., Zheng, W.S.: Dual illumination estimation for robust exposure correction. Comput. Graph. Forum 38, 243–252 (2019)

    Article  Google Scholar 

  15. Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: BMVC (2018)

  16. Ren, W., Liu, S., Ma, L., Xu, Q., Xu, X., Cao, X., Du, J., Yang, M.H.: Low-light image enhancement via a deep hybrid network. IEEE TIP 28, 4364–4375 (2019)

    MathSciNet  Google Scholar 

  17. Wang, L.W., Liu, Z.S., Siu, W.C., Lun, D.P.K.: Lightening network for low-light image enhancement. IEEE TIP 29, 7984–7996 (2020)

    Google Scholar 

  18. Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., et al.: EnlightenGAN: deep light enhancement without paired supervision. IEEE TIP 30, 2340–2349 (2021)

    Google Scholar 

  19. Zheng, S., Gupta, G.: Semantic-guided zero-shot learning for low-light image/video enhancement. In: IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (2022)

  20. Afifi, M., Derpanis, K.G., Ommer, B., Brown, M.S.: Learning multi-scale photo exposure correction. In: CVPR, pp. 9153–9163 (2021)

  21. Eyiokur, F.I., Yaman, D., Ekenel, H.K., Waibel, A.: Exposure correction model to enhance image quality. In: CVPR (2022)

  22. Huang, J., Liu, Y., Fu, X., Zhou, M., Wang, Y., Zhao, F., Xiong, Z.: Exposure normalization and compensation for multiple-exposure correction. In: CVPR (2022)

  23. Yang, K.F., Cheng, C., Zhao, S.X., Yan, H.M., Zhang, X.S., Li, Y.J.: Learning to adapt to light. IJCV 131, 1022–1041 (2023)

  24. Wang, R., Zhang, Q., Fu, C.W., Shen, X., Zheng, W.S., Jia, J.: Underexposed photo enhancement using deep illumination estimation. In: CVPR, pp. 6842–6850 (2019)

  25. Guo, C., Li, C., Guo, J., Loy, C.C., Hou, J., Kwong, S., Cong, R.: Zero-reference deep curve estimation for low-light image enhancement. In: CVPR, pp. 1777–1786 (2020)

  26. Ma, L., Liu, R., Zhang, J., Fan, X., Luo, Z.: Learning deep context-sensitive decomposition for low-light image enhancement. IEEE Trans. Neural Netw. Learn. Syst. 33, 1–15 (2021)

  27. Tang, H., Fei, L., Zhu, H., Tao, H., Xie, C.: A two-stage network for zero-shot low-illumination image restoration. Sensors 23, 792 (2023)

    Article  Google Scholar 

  28. Lu, Y., Jian, S.: Automatic exposure correction of consumer photographs. In: ECCV, pp. 771–785 (2012)

  29. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)

  30. Nair, V., Hinton, G.E.: Rectified linear units improve Restricted Boltzmann machines. In: ICML (2010)

  31. Girshick, R.: Fast R-CNN. In: ICCV (2015)

  32. Paszke, A., Gross, S., Massa, F., Lerer, et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems (2019)

  33. Kingma, D.P., Ba, J.L.: Adam: a method for stochastic gradient descent. In: ICLR, pp. 1–15 (2015)

  34. Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: CVPR, pp. 97–104 (2011)

  35. Hordley, S.D., Finlayson, G.D.: Reevaluation of color constancy algorithm performance. J. Opt. Soc. Am. A 23, 1008–1020 (2006)

    Article  Google Scholar 

  36. Sharma, G., Wu, W., Dalal, E.N.: The CIEDE2000 color-difference formula: implementation notes, supplementary test data, and mathematical observations. Color Res. Appl. 30, 21–30 (2005)

    Article  Google Scholar 

  37. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13, 600–612 (2004)

    Google Scholar 

Download references

Funding

Partial financial support was received from the National Natural Science Foundation of China (Project No. 62305255), the Natural Science Foundation of Hubei Province (Project No. 2022CFB537, 2020CFB386) and the Youth Talent Project of Department of Education of Hubei Provincial (Project No. Q20221706).

Author information

Authors and Affiliations

  1. School of Computer Science and Artificial Intelligence, Wuhan Textile University, No.1 Sunshine Avenue, Wuhan, 430200, Hubei, China

    Hang Luo, Jinxing Liang & Xiaoyun Yan

Authors
  1. Hang Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jinxing Liang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Xiaoyun Yan
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

HL and JL wrote the main manuscript text and XY prepared Figs. 1, 2, 3, 4 and 5. All authors reviewed the manuscript.

Corresponding author

Correspondence to Jinxing Liang.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

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

Luo, H., Liang, J. & Yan, X. Exposure correction by deep curve estimation. SIViP 18, 813–820 (2024). https://doi.org/10.1007/s11760-023-02815-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-023-02815-5

Keywords