Skip to main content
SpringerLink
Log in

Low-Light Image Enhancement via Regularized Gaussian Fields Model

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Retinex decomposition is a prevalent solution to low-light image enhancement. It is usually considered as a constrained optimization problem. To improve enhancement performance, the Retinex model is incorporated with various prior constraints, which make the optimization process complicated and difficult. In this paper, a method of low-light enhancement with regularized Gaussian Fields (RGF) model is proposed to address this issue. Firstly, we construct an RGF-based optimization model to formulate simultaneous reflectance and illumination estimation as an unconstrained optimization problem. Therefore, Retinex decomposition in RGF model can be solved by gradient descent techniques and has superiority on computational convenience. Then, to suppress noise and preserve detail in the estimated reflectance, the detail-preserving model based on Gaussian total variation (GTV) is established. The qualitative and quantitative comparisons on several public datasets demonstrate the superiority of our method over several state-of-the-arts in terms of enhancement efficiency and quality.

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
Algorithm 1
Algorithm 2
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Zhao B, Chen C, Xiao X, Xia S (2022) Towards a category-extended object detector with limited data. Patt Recognit 132:108943

    Article  Google Scholar 

  2. Chen Q, Fu K, Liu Z, Chen G, Du H, Qiu B, Shao L (2021) Ef-net: a novel enhancement and fusion network for RGB-D saliency detection. Patt Recognit 112:107740

    Article  Google Scholar 

  3. Sultana M, Mahmood A, Jung SK (2022) Unsupervised moving object segmentation using background subtraction and optimal adversarial noise sample search. Patt Recognit 129:108719

    Article  Google Scholar 

  4. Li C, Anwar S, Porikli F (2020) Underwater scene prior inspired deep underwater image and video enhancement. Patt Recognit 98:107038

    Article  Google Scholar 

  5. Jiang Q, Zhang Y, Bao F, Zhao X, Zhang C, Liu P (2022) Two-step domain adaptation for underwater image enhancement. Patt Recognit 122:108324

    Article  Google Scholar 

  6. Sazak Ç, Nelson CJ, Obara B (2019) The multiscale bowler-hat transform for blood vessel enhancement in retinal images. Patt Recognit 88:739–750

    Article  Google Scholar 

  7. Sharma A, Mishra PK (2022) Covid-manet: multi-task attention network for explainable diagnosis and severity assessment of covid-19 from CXR images. Patt Recognit 131:108826

    Article  Google Scholar 

  8. Li M, Liu J, Yang W, Sun X, Guo Z (2018) Structure-revealing low-light image enhancement via robust Retinex model. IEEE Trans Image Process 27(6):2828–2841

    Article  MathSciNet  Google Scholar 

  9. Li H, Wu X-J (2018) Densefuse: a fusion approach to infrared and visible images. IEEE Trans Image Process 28(5):2614–2623

    Article  MathSciNet  Google Scholar 

  10. Land EH (1977) The Retinex theory of color vision. Sci Am 237(6):108–129

    Article  Google Scholar 

  11. Fu X, Zeng D, Huang Y, Zhang X-P, Ding X (2016) A weighted variational model for simultaneous reflectance and illumination estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2782–2790

  12. Ren X, Yang W, Cheng W-H, Liu J (2020) Lr3m: robust low-light enhancement via low-rank regularized Retinex model. IEEE Trans Image Process 29:5862–5876

    Article  MathSciNet  Google Scholar 

  13. Hao S, Han X, Guo Y, Xu X, Wang M (2020) Low-light image enhancement with semi-decoupled decomposition. IEEE Trans Multimed 22(12):3025–3038

    Article  Google Scholar 

  14. Cheng H-D, Shi X (2004) A simple and effective histogram equalization approach to image enhancement. Digit Sign Process 14(2):158–170

    Article  Google Scholar 

  15. Abdullah-Al-Wadud M, Kabir MH, Dewan MAA, Chae O (2007) A dynamic histogram equalization for image contrast enhancement. IEEE Trans Consum Electron 53(2):593–600

    Article  Google Scholar 

  16. Pizer SM (1990) Contrast-limited adaptive histogram equalization: speed and effectiveness stephen m. pizer, r. eugene johnston, james p. ericksen, bonnie c. yankaskas, keith e. muller medical image display research group. In: Proceedings of the first conference on visualization in biomedical computing, Atlanta, Georgia, vol. 337, p 1

  17. Celik T, Tjahjadi T (2011) Contextual and variational contrast enhancement. IEEE Trans Image Process 20(12):3431–3441

    Article  MathSciNet  Google Scholar 

  18. Lee C, Lee C, Kim C-S (2013) Contrast enhancement based on layered difference representation of 2d histograms. IEEE Trans Image Process 22(12):5372–5384

    Article  Google Scholar 

  19. Jobson DJ, Rahman Z-U, Woodell GA (1997) Properties and performance of a center/surround Retinex. IEEE Trans Image Process 6(3):451–462

    Article  Google Scholar 

  20. Wang S, Luo G (2017) Naturalness preserved image enhancement using a priori multi-layer lightness statistics. IEEE Trans Image Process 27(2):938–948

    Article  MathSciNet  Google Scholar 

  21. Jobson DJ, Rahman Z-U, Woodell GA (1997) A multiscale Retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans Image process 6(7):965–976

    Article  Google Scholar 

  22. Ma W, Morel J-M, Osher S, Chien A (2011) An l 1-based variational model for Retinex theory and its application to medical images. In: CVPR 2011, IEEE, pp 153–160

  23. Ng MK, Wang W (2011) A total variation model for Retinex. SIAM J Imag Sci 4(1):345–365

    Article  MathSciNet  Google Scholar 

  24. Ma W, Osher S (2012) A tv Bregman iterative model of Retinex theory. Inverse Probl Imag 6(4):697–708

    Article  MathSciNet  Google Scholar 

  25. Wang W, Ng MK (2014) A nonlocal total variation model for image decomposition: illumination and reflectance. Numer Math: Theory Methods Appl 7(3):334–355

    MathSciNet  Google Scholar 

  26. Guo X, Li Y, Ling H (2016) Lime: Low-light image enhancement via illumination map estimation. IEEE Trans Image Process 26(2):982–993

    Article  MathSciNet  Google Scholar 

  27. Jha M, Bhandari AK (2022) Camera response based nighttime image enhancement using concurrent reflectance. IEEE Trans Instrum Measurement 71:1–11

    Google Scholar 

  28. Yang J, Jiang X, Pan C, Liu C-L (2016) Enhancement of low light level images with coupled dictionary learning. In: 2016 23rd international conference on pattern recognition (ICPR), IEEE, pp 751–756

  29. Lore KG, Akintayo A, Sarkar S (2017) Llnet: a deep autoencoder approach to natural low-light image enhancement. Patt Recognit 61:650–662

    Article  Google Scholar 

  30. Yang W, Wang S, Fang Y, Wang Y, Liu J (2020) From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3063–3072

  31. Zhao Z, Xiong B, Wang L, Ou Q, Yu L, Kuang F (2021) Retinexdip: a unified deep framework for low-light image enhancement. IEEE Trans Circ Syst Video Technol 32(3):1076–1088

    Article  Google Scholar 

  32. Zhang H, Yang J, Xie J, Qian J, Zhang B (2017) Weighted sparse coding regularized nonconvex matrix regression for robust face recognition. Inf Sci 394:1–17

    MathSciNet  Google Scholar 

  33. Zhang H, Qian F, Zhang B, Du W, Qian J, Yang J (2022) Incorporating linear regression problems into an adaptive framework with feasible optimizations. IEEE Trans Multimed

  34. Min C, Gu Y, Li Y, Yang F (2020) Non-rigid infrared and visible image registration by enhanced affine transformation. Patt Recognit 106:107377

    Article  Google Scholar 

  35. Loke MH, Barker RD (1996) Rapid least-squares inversion of apparent resistivity pseudosections by a quasi-newton method1. Geophys Prospect 44(1):131–152

    Article  Google Scholar 

  36. Marques TP, Branzan Albu A (2020) L2uwe: a framework for the efficient enhancement of low-light underwater images using local contrast and multi-scale fusion. In: 2020 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), pp 2286–2295. https://doi.org/10.1109/CVPRW50498.2020.00277

  37. Wei C, Wang W, Yang W, Liu J (2018) Deep Retinex decomposition for low-light enhancement

  38. Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans Image Process 16(8):2080–2095

    Article  MathSciNet  Google Scholar 

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

  40. Ma J, Zhao J, Ma Y, Tian J (2015) Non-rigid visible and infrared face registration via regularized gaussian fields criterion. Patt Recognit 48(3):772–784

    Article  Google Scholar 

  41. Wang S, Ma K, Yeganeh H, Wang Z, Lin W (2015) A patch-structure representation method for quality assessment of contrast changed images. IEEE Sign Process Lett 22(12):2387–2390

    Article  Google Scholar 

  42. Mittal A, Soundararajan R, Bovik AC (2012) Making a “completely blind’’ image quality analyzer. IEEE Sign Process Lett 20(3):209–212

    Article  Google Scholar 

Download references

Acknowledgements

The authors gratefully acknowledge the financial support from the National Natural Science Foundation of China (No. 61901157).

Author information

Author notes

  1. Chaobo Min, Mengchen Shao, Huijie Zheng and Qingfeng Lv have contributed equally to this work.

Authors and Affiliations

  1. School of Internet of Things Engineering, Hohai University, Changzhou, 213022, China

    Xiang Yi, Chaobo Min, Mengchen Shao, Huijie Zheng & Qingfeng Lv

Authors
  1. Xiang Yi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chaobo Min
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengchen Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huijie Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qingfeng Lv
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chaobo Min.

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

Yi, X., Min, C., Shao, M. et al. Low-Light Image Enhancement via Regularized Gaussian Fields Model. Neural Process Lett 55, 12017–12037 (2023). https://doi.org/10.1007/s11063-023-11407-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-023-11407-w

Keywords

Search

Navigation