Combined Discrete Wavelet Transform and Noise-Prior Retinex Model for Noisy Low-Light Image Enhancement

Jingtian Zhao; Xueli Xie; Jiangxiang Xi; Xiaogang Yang

doi:10.5566/ias.3942

Authors

Jingtian Zhao Rocket force university of engineering
Xueli Xie Rocket force university of engineering
Jiangxiang Xi Rocket force university of engineering
Xiaogang Yang Rocket force university of engineering

DOI:

https://doi.org/10.5566/ias.3942

Keywords:

discrete wavelet transform, image enhancement, noise suppression, Retinex theory

Abstract

Retinex-based low-light image enhancement methods have drawn significant interest due to their excellent performance and extensibility. However, most of them exhibit poor robustness when images are corrupted by noise. The main reason is that traditional Retinex models cannot effectively characterize the coupling between noise, reflectance, and illumination in noisy low-light images. To address this limitation, this paper modifies the existing noise-aware Retinex model to better characterize the noise component during noisy image decomposition. To further model the noise distribution, the discrete wavelet transform (DWT) is employed to construct a noise prior in the wavelet domain, which effectively captures noise information in different frequency subbands. Furthermore, contour, texture, and noise gradient correlations are incorporated as prior terms for the illumination, reflectance, and noise components, respectively, leading to a unified optimization model. In addition, an improved illumination stretching function is designed to enhance image contrast while suppressing halo artifacts and noise. Experimental results demonstrate that the proposed algorithm achieves competitive performance compared with representative Retinex-based methods and state-of-the-art deep learning-based low-light enhancement methods in terms of noise robustness and quantitative performance.

References

Al-Hashim MA, Al-Ameen Z (2020). Retinex-based multiphase algorithm for low-light image enhancement. Traitement du Signal 37(5):733–43.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1):1–122.

Cai B, Xu X, Guo K, Jia K, Hu B, Tao DC (2017). A joint intrinsic-extrinsic prior model for retinex. 2017 IEEE International Conference on Computer Vision (ICCV), 4000–9.

Cai R, Chen Z (2023). Brain-like retinex: A biologically plausible retinex algorithm for low light image enhancement. Pattern Recognit. 136:109195.

Elad M (2005). Retinex by two bilateral filters. International Conference on Scale-Space Theories in Computer Vision, 217–29.

Fu X, Liao Y, Zeng D, Huang Y, Zhang XP, Ding XH (2015). A probabilistic method for image enhancement with simultaneous illumination and reflectance estimation. IEEE Trans. Image Process. 24(12):4965–77.

Fu X, Zeng D, Huang Y, Zhang XP, Ding XH (2016). A weighted variational model for simultaneous reflectance and illumination estimation. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2782–90.

Guo X, Li Y, Ling H (2016). LIME: Low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2):982–93.

Jiang H, Zhu X, Ren Y, Hao Y, Zou F, Lin F, Han S (2023). R2RNet: Low-light image enhancement via real-low to real-normal network. J. Vis. Commun. Image Represent. 90:103712.

Hao SJ, Hao X, Guo YR, Xu X, Wang M (2020). Low-light image enhancement with semi-decoupled decomposition. IEEE Trans. Multimed. 22(12):3025–38.

Hsieh PW, Yang SY (2026). Anisotropic pth-order TV-based Retinex decomposition with adaptive reflectance regularizer for low-light image enhancement. Pattern Recognit. 172:112468.

Huynh-Thu Q, Ghanbari M (2008). Scope of validity of PSNR in image/video quality assessment. Electron. Lett. 44(13):800–1.

Kimmel R, Elad M, Shaked D, Keshet R, Sobel I (2003). A variational framework for retinex. Int. J. Comput. Vis. 52:7–23.

Land EH, McCann JJ (1971). Lightness and retinex theory. J. Opt. Soc. Am. 61(1):1–11.

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):2828–41.

Li G, Yang Y, Qu X, Cao DP, Li KQ (2021). A deep learning-based image enhancement approach for autonomous driving at night. Knowl. Based Syst. 213:106617.

Li CX, He CJ (2024). Fractional structure and texture aware model for image Retinex and low-light enhancement. Appl. Math. Model. 130:496–513.

Lin S, Li Z, Zheng F, Zhao Q, Li SM (2023). Underwater image enhancement based on adaptive color correction and improved retinex algorithm. IEEE Access 11:27620–30.

Liu M, Zhou Z, Shang PH, Xu D (2019). Fuzzified image enhancement for deep learning in iris recognition. IEEE Trans. Fuzzy Syst. 28(1):92–9.

Liu S, Long W, He L, Li YY, Ding W (2021). Retinex-based fast algorithm for low-light image enhancement. Entropy 23(6):746.

Mittal A, Soundararajan R, Bovik AC (2013). Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20(3):209–12.

Ng MK, Wang W (2011). A total variation model for retinex. SIAM J. Imaging Sci. 4(1):345–65.

Palma-Amestoy R, Provenzi E, Bertalmío M, Caselles V (2008). A perceptually inspired variational framework for color enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 31(3):458–74.

Qi Y, Yang Z, Sun W, Lou M, Lian J, Zhao WW, Deng XY, Ma YD (2021). A comprehensive overview of image enhancement techniques. Arch. Computat. Methods Eng. 29:583–607.

Ren XT, Yang WH, Cheng WH, et al. (2020). LR3M: Robust low-light enhancement via low-rank regularized Retinex model. IEEE Trans. Image Process. 29:5862–76.

Veluchamy M, Subramani B (2025). Detail preserving noise aware retinex model for low light image enhancement. J. Opt. doi:10.1007/s12596-025-02610-0.

Wang S, Zheng J, Hu HM, Li B (2013). Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans. Image Process. 22(9):3538–48.

Wang L, Xiao L, Liu H (2014). Variational Bayesian method for retinex. IEEE Trans. Image Process. 23(8):3381–96.

Wang Y, Yu Y, Yang W, et al. (2023). Exposure diffusion: Learning to expose for low-light image enhancement. Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 12438–48.

Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004). Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 13(4):600–12.

Wei C, Wang W, Yang W, Liu JY (2018). Deep retinex decomposition for low-light enhancement. arXiv.

Wei R, Wei X, Xia SC, Chang K, Ling MY, Nong JX, Xu L (2025). Multi-scale wavelet feature fusion network for low-light image enhancement. Comput. Graph. 127:104182.

Xu J, Hou Y, Ren D, Liu L, Zhu F, Yu MY (2020). STAR: A structure and texture aware retinex model. IEEE Trans. Image Process. 29:5022–37.

Yan QS, Feng YX, Zhang C, Pang GS, Shi KB, Wu P, Dong W, Sun JQ, Zhang YN (2025). HVI: A new color space for low-light image enhancement. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 5678–87.

Ying Z, Li G, Gao W (2017). A bio-inspired multi-exposure fusion framework for low-light image enhancement. arXiv:1711.00591.

Yu X, Luo X, Lyu G, Luo SW (2017). A novel Retinex based enhancement algorithm considering noise. 2017 International Conference on Computer and Information Science (ICIS), 649–54.

Zhang W, Dong L, Xu W (2022). Retinex-inspired color correction and detail preserved fusion for underwater image enhancement. Comput. Electron. Agric. 192:106585.

Zhao Z, Xiong B, Wang L, et al. (2021). RetinexDIP: A unified deep framework for low-light image enhancement. IEEE Trans. Circuits Syst. Video Technol. 32(3):1076–88.

Zhu Z, Yang X, Lu R, Shen T, Zhang T, Wang S (2025). Ghost imaging in the dark: A multi-illumination estimation network for low-light image enhancement. IEEE Trans. Circuits Syst. Video Technol. 35(2):1576–90.

Guo H, Wei J, Zhang H (2025). Improved multiscale Retinex low-light image enhancement based on wavelet transform. Proc. SPIE 13942:139422X.