Skip to main content
Springer Nature Link
Log in

Low-light image enhancement via multi-stream vision state space module

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

Abstract

Low-light image enhancement (LLIE) aims to improve the brightness of images under low illumination while preserving details and structural information. Although methods based on Retinex theory and Transformer architectures have made significant progress, their dependence on large-scale training data and high computational costs limit practical applications. To address these challenges, researchers have proposed enhancement algorithms based on state-space models (SSM), which significantly reduce computational complexity while maintaining global modeling capabilities. However, existing methods still face issues such as color distortion and noise interference. To tackle these problems, we propose an innovative multi-stream SSM-based low-light image enhancement algorithm, MMamba-LLIE. This algorithm integrates three key modules: (1) a Color Correction Module (CCM) to effectively mitigate color distortion caused by Retinex theory; (2) a Multi-scale Feature Extraction Module (DFM) to capture both global and local structural information; and (3) a Noise Removal Module (UnoisyM) to suppress low-light noise. Experimental results demonstrate that MMamba-LLIE achieves significant improvements on the LOLv2-real dataset, with a 0.302 dB increase in PSNR, a 0.004 increase in SSIM, and a 0.65 reduction in RMSE. On the unparameterized DICM dataset, NIQE and PI are reduced by 0.026 and 0.051, respectively. Extensive experiments validate the superiority of the proposed method in both performance metrics and visual quality, providing a promising solution for low-light image enhancement. For details, please visit: https://github.com/lsaixuexi/MMamba-LLIE

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
Fig. 6

Similar content being viewed by others

References

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

    Article  MATH  Google Scholar 

  2. Reza, A.M.: Realization of the contrast limited adaptive histogram equalization (clahe) for real-time image enhancement. J. VLSI Signal Proc. Syst. Signal Image Video Technol. 38, 35–44 (2004)

    Article  MATH  Google Scholar 

  3. Hao, S., Feng, Z., Guo, Y.: Low-light image enhancement with a refined illumination map. Multi. Tools Appl. 77, 29639–29650 (2018)

    Article  MATH  Google Scholar 

  4. Wang, Z.G., Liang, Z.H., Liu, C.L.: A real-time image processor with combining dynamic contrast ratio enhancement and inverse gamma correction for pdp. Displays 30(3), 133–139 (2009)

    Article  MATH  Google Scholar 

  5. Land, E.H.: Lightness and retinex theory. J. Opt. Soc. Am. 58, 1428 (1967)

    MATH  Google Scholar 

  6. Rahman, Z., Bhutto, J.A., Aamir, M., Dayo, Z.A., Guan, Y.: Exploring a radically new exponential retinex model for multi-task environments. J. King Saud Univ. Computer Inf. Sci. 35(7), 101635 (2023)

    MATH  Google Scholar 

  7. Rahman, Z., Aamir, M., Ali, Z., Saudagar, A.K., AlTameem, A., Muhammad, K.: Efficient contrast adjustment and fusion method for underexposed images in industrial cyber-physical systems. IEEE Syst. J. 17(4), 5085–96 (2023)

    Article  MATH  Google Scholar 

  8. Rahman, Z., Ali, Z., Khan, I., Uddin, M.I., Guan, Y., Hu, Z.: Diverse image enhancer for complex underexposed image. J. Electr. Imagin. 31(4), 041213 (2022)

    MATH  Google Scholar 

  9. Ashish, V.: Attention is all you need. Adv. Neural Inf. Proc. Syst. (2017)

  10. Luo, Z., Tang, J., Hou, Y., Huang, Z., Gao, Y. Z.: Unsupervised low light image enhancement using snr-aware swin transformer. arXiv Preprint 2306, 02082 (2023)

  11. Xu, X. G., Wang, R. X., Fu, C. W., Jia, J. Y.: Snr-aware low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17714–17724 (2022)

  12. Zhang, Z. Y., Jiang, Y. T., Jiang, J., Wang, X. G., Luo, P., Gu, J. W.: Star: A structure-aware lightweight transformer for real-time image enhancement. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4106–4115 (2021)

  13. Jiang, N.F., Lin, J.H., Zhang, T., Zheng, H.F., Zhao, T.S.: Low-light image enhancement via stage-transformer-guided network. IEEE Trans. Circuits Syst. Video Technol. 33(8), 3701–3712 (2023)

    Article  MATH  Google Scholar 

  14. Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv Preprint 2312, 00752 (2023)

  15. Fu, D. Y., Dao, T., Saab, K. K., Thomas, A. W., Rudra, A., Ré, C.: Hungry hungry hippos: Towards language modeling with state space models. arXiv Preprint 2212, 14052 (2022)

  16. Smith, J. T. H., Warrington, A., Linderman, S. W.: Simplified state space layers for sequence modeling. arXiv Preprint 2208, 04933 (2022)

  17. Gu, A., Dao, T., Ermon, S., Rudra, A., Ré, C.: Hippo: recurrent memory with optimal polynomial projections. Adv. Neural Inf. Proc. Syst. 33, 1474–87 (2020)

    Google Scholar 

  18. Liu, Z.B., Chen, L.Y.: A novel contrast enhancement method for low-light image using deep convolutional neural network. J. Electron. Imaging 28, 053011 (2019)

    MATH  Google Scholar 

  19. Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R., Geselowitz, A., Greer, T., ter Haar Romeny, B., Zimmerman, J.B., Zuiderveld, K.: Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing 39(3), 355–368 (1987)

    Article  Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

  21. Rahman, S., Rahman, M.M., Abdullah-Al-Wadud, M., Al-Quaderi, G.D., Shoyaib, M.: An adaptive gamma correction for image enhancement. EURASIP J. Image Video Proc. 2016, 1–13 (2016)

    MATH  Google Scholar 

  22. Hai, J., Xuan, Z., Yang, R., Hao, Y.T., Zou, F.Z., Lin, F., Han, S.C.: R2rnet: low-light image enhancement via real-low to real-normal network. J. Vis. Commun. Image Represent. 90, 103712 (2023)

    Article  Google Scholar 

  23. Cai, J.R., Gu, S.H., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Proc. 27(4), 2049–2062 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  24. Feng, S., Zhang, L., Zhang, H.W.: Low-light image enhancement based on deep convolutional neural network. Comput. Vis. Image Underst. 172, 16–25 (2018)

    MATH  Google Scholar 

  25. Rahman, Z., Yi-Fei, P., Aamir, M., Wali, S., Guan, Y.: Efficient image enhancement model for correcting uneven illumination images. IEEE Access 8, 109038–53 (2020)

    Article  Google Scholar 

  26. Roth, T., Richter, J., Bala, R.: Low light image enhancement using deep learning. IEEE Trans. Image Process. 29, 3498–3510 (2020)

    MATH  Google Scholar 

  27. Alexey, D.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  28. Xiaogang, X., Ruixing, W., Chi-Wing, F., Jiaya, J.: Snr-aware low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17714–17724 (2022)

  29. Nuo, S., Borui, Z., Junlin, X., Xiaohan, S.: Low-light image enhancement via transformer-based network. In: Proceedings of the 2022 4th International Conference on Image, Video and Signal Processing, pp. 41–47 (2022)

  30. Yuanhao, C., Hao, B., Jing, L., Haoqian, W., Radu, T., Yulun, Z.: Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12504–12513 (2023)

  31. Zhu, B. T., Zhang, L., Yang, Q.: A novel dark-channel prior based approach for low-light image enhancement. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9 (2019)

  32. Huang, D.Y., Li, S.J., Zhang, L.: Multi-scale contrast enhancement using a novel fusion-based algorithm. J. Vis. Commun. Image Represent. 33, 33–45 (2016)

    MATH  Google Scholar 

  33. Choi, H., Kwon, J., Park, C., Kim, H.Y.: Low-light image enhancement via adaptive deep learning. IEEE Trans. Image Proc. 27(12), 5674–5684 (2018)

    MATH  Google Scholar 

  34. Chen, Y.F., Wang, Z.G.: A novel enhancement algorithm for low-light images based on dark channel prior. IEEE Trans. Image Proc. 30, 4984–4996 (2021)

    MATH  Google Scholar 

  35. Yang, X.Q., Zhu, W.: Low-light image enhancement based on neural network. J. Image Gr. 34(2), 176–183 (2022)

    MATH  Google Scholar 

  36. Cai, B., Yang, F.Z., Liu, Y.: Low-light image enhancement using gan and high-frequency texture restoration. Signal Proc.: Image Commun. 91, 115966 (2021)

    MATH  Google Scholar 

  37. Hang, G., Jinmin, L., Tao, D., Zhihao, O., Xudong, R., Shu-Tao, X.: Mambair: A simple baseline for image restoration with state-space model. In: European Conference on Computer Vision, pp. 222–241 (2025). Springer

  38. Tao, H., Xiaohuan, P., Shan, Y., Fei, W., Chen, Q., Chang, X.: Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338 (2024)

  39. Jiesong, B., Yuhao, Y., Qiyuan, H., Yuanxian, L., Xiaofeng, Z.: Retinexmamba: Retinex-based mamba for low-light image enhancement. arXiv preprint arXiv:2405.03349 (2024)

  40. Gupta, P., Rathi, M., Khan, M.T.: Low-light image enhancement using the weighted least squares optimization. Comput. Vis. Image Underst. 181, 38–50 (2019)

    MATH  Google Scholar 

  41. Kim, H.M., Kim, J.H., Yoo, H.M.: Image enhancement using contrast-limited adaptive histogram equalization. IEEE Trans. Consum. Electron. 45, 746–749 (1999)

    MATH  Google Scholar 

  42. Lee, C., Lee, C., Kim, C.S.: Contrast enhancement based on layered difference representation of 2D histograms. IEEE Transa. Image Proc. 22(12), 5372–84 (2013)

  43. Wang, S., Zheng, J., Hu, H.M., Li, B.: Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Transa. Image Proc. 22(9), 3538–48 (2013)

    Article  MATH  Google Scholar 

  44. Vonikakis, V., Kouskouridas, R., Gasteratos, A.: On the evaluation of illumination compensation algorithms. Multimed. Tools Appl. 77, 9211–31 (2018)

    Article  MATH  Google Scholar 

  45. He, K., Sun, J.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397–1409 (2013)

  46. Yin, Y., Ma, L., Zhang, Y., Zhou, J.: A review of low-light image enhancement techniques. J. Imaging Sci. Technol. 63, 20303 (2019)

    MATH  Google Scholar 

  47. Liu, L.F., Zhu, H.Y., Zhang, L.H.: Contrast enhancement for low-light images. Pattern Recogn. Lett. 52, 169–177 (2015)

    MATH  Google Scholar 

  48. Zhang, J.L., Wu, S.F., Li, Y.H.: Low-light image enhancement using histogram equalization. J. Vis. Commun. Image Represent. 31, 233–241 (2015)

    MATH  Google Scholar 

  49. Zhu, X.F., Xu, X., Li, Z.: Low-light image enhancement via deep learning-based fusion. Signal Proc.: Image Commun. 85, 115947 (2020)

    Google Scholar 

  50. Li, L.F., Li, Y., Yang, X.G.: Low-light image enhancement using the retinex model. J. Vis. Commun. Image Represent. 23(6), 896–907 (2012)

    MathSciNet  MATH  Google Scholar 

  51. He, K., Sun, J.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2011)

    Article  MATH  Google Scholar 

  52. Guo, H., Li, J., Dai, T., Ouyang, Z., Ren, X., Xia, S.-T.: Mambair: A simple baseline for image restoration with state-space model. In: European Conference on Computer Vision, pp. 222–241. Springer, Berlin, Germany (2025)

  53. Jiang, H., Luo, A., Liu, X., Han, S., Liu, S.: Lightendiffusion: Unsupervised low-light image enhancement with latent-retinex diffusion models. In: European Conference on Computer Vision (2024)

  54. Hou, J., Zhu, Z., Hou, J., Liu, H., Zeng, H., Yuan, H.: Global structure-aware diffusion process for low-light image enhancement. Advances in Neural Information Processing Systems 36 (2024)

  55. Zhou, D., Yang, Z., Yang, Y.: Pyramid diffusion models for low-light image enhancement. arXiv preprint arXiv:2305.10028 (2023)

Download references

Funding

This work was supported by the Beijing Natural Science Foundation (No. 4252036), the National Natural Science Foundation of China (Nos. 62172045 and 62272049), and the Academic Research Projects of Beijing Union University (No. ZKZD202301).

Author information

Authors and Affiliations

  1. Smart City College, Beijing Union University, Chaoyang, Beijing, 100101, China

    Shuai Liu, JinHua Wang, Sen Zhang, PengCheng Yu & XiaoYue Ma

Authors
  1. Shuai Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. JinHua Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sen Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. PengCheng Yu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. XiaoYue Ma
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to JinHua Wang.

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

Liu, S., Wang, J., Zhang, S. et al. Low-light image enhancement via multi-stream vision state space module. SIViP 19, 244 (2025). https://doi.org/10.1007/s11760-025-03832-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11760-025-03832-2

Keywords