2611005639
  • Open Access
  • Article

BayeUNet-NLM: A Bayesian U-Net with Uncertainty-Guided Non-Local Means Post-Processing for Extreme Low-Light Denoising

  • Ibrahim Sadok *,† and 
  • Tariq Benahmed †

Received: 13 August 2026 | Revised: 09 November 2026 | Accepted: 10 November 2026 | Published: 19 November 2026

Abstract

Extreme low-light image denoising, where photon shot noise and read noise dominate, remains a critical challenge for computer vision and computational photography. While deep learning models, particularly U-Net architectures, have shown remarkable performance, they often produce over-smoothed results and lack robust uncertainty quantification. This limitation is fundamentally rooted in the ill-posed, one-to-many nature of the low-light enhancement problem, which deterministic models fail to capture. This paper introduces BayeUNet-NLM, a novel two-stage framework that marries the representational power of a Bayesian deep network with the interpretable, structure-preserving capability of a classical denoiser. In the first stage, a Bayesian U-Net with Monte Carlo Dropout at test time generates both a denoised image and a per-pixel uncertainty map. This map quantifies the model's confidence, highlighting regions where data is ambiguous (e.g., due to extreme noise or missing textures). In the second stage, this uncertainty map is explicitly used to guide the classical Non-Local Means (NLM) post-processor, adaptively modulating its local bandwidth and its donor-reliability weights: high-uncertainty regions receive stronger non-local regularization from similar, more confident patches elsewhere in the image, while low-uncertainty regions are preserved. This synergy allows the model to recover fine details with high confidence while robustly denoising highly uncertain regions without introducing artifacts. Extensive experiments on benchmark datasets (SID, LOL) demonstrate that BayeUNet-NLM outperforms the deep learning and traditional methods included in our comparison in both quantitative metrics (PSNR, SSIM) and qualitative visual quality, particularly in preserving textures and avoiding over-smoothing. Our work highlights the value of Bayesian uncertainty for guiding hybrid denoising pipelines.

References 

  • 1.

    Sung Cheol Park; Min Kyu Park; Moon Gi Kang. Super-resolution image reconstruction: a technical overview. IEEE Signal Process. Mag. 2003, 20, 21–36. https://doi.org/10.1109/msp.2003.1203207.

  • 2.

    Puetter, R.C.; Gosnell, T.R.; Yahil, A. Digital Image Reconstruction: Deblurring and Denoising. Annu. Rev. Astron. Astrophys. 2005, 43, 139–194. https://doi.org/10.1146/annurev.astro.43.112904.104850.

  • 3.

    Belthangady, C.; Royer, L.A. Applications, promises, and pitfalls of deep learning for fluorescence image reconstruction. Nat. Methods 2019, 16, 1215–1225. https://doi.org/10.1038/s41592-019-0458-z.

  • 4.

    Hasinoff, S.W.; Sharlet, D.; Geiss, R.; et al. Burst photography for high dynamic range and low-light imaging on mobile cameras. ACM Trans. Graph. 2016, 35, 1–12. https://doi.org/10.1145/2980179.2980254.

  • 5.

    Foi, A.; Trimeche, M.; Katkovnik, V.; et al. Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data. IEEE Trans. Image Process. 2008, 17, 1737–1754. https://doi.org/10.1109/tip.2008.2001399.

  • 6.

    Ce Liu; Szeliski, R.; Sing Bing Kang; et al. Automatic Estimation and Removal of Noise from a Single Image. IEEE Trans. Pattern Anal. Mach. Intell. 2008, 30, 299–314. https://doi.org/10.1109/tpami.2007.1176.

  • 7.

    Buades, A.; Coll, B.; Morel, J.M. A Non-Local Algorithm for Image Denoising. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 20–26 June 2005; Volume 2, pp. 60–65. https://doi.org/10.1109/cvpr.2005.38.

  • 8.

    Dabov, K.; Foi, A.; Katkovnik, V.; et al. Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Trans. Image Process. 2007, 16, 2080–2095. https://doi.org/10.1109/tip.2007.901238.

  • 9.

    Plotz, T.; Roth, S. Benchmarking Denoising Algorithms with Real Photographs. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21 July–26 July 2017; pp. 1586–1595. https://doi.org/10.1109/cvpr.2017.294.

  • 10.

    Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4.

  • 11.

    Chen, C.; Chen, Q.; Xu, J.; et al. Learning to see in the dark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 19–21 June 2018; pp. 3291–3300.

  • 12.

    Gu, J.; Lu, H.; Zuo, W.; et al. Blind Super-Resolution With Iterative Kernel Correction. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–20 June 2019; pp. 1604–1613. https://doi.org/10.1109/cvpr.2019.00170.

  • 13.

    Gal, Y.; Ghahramani, Z. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of the 33rd International Conference on Machine Learning, New York City, NY, USA, 19–24 June 2016; Volume 48, pp. 1050–1059. https://proceedings.mlr.press/v48/gal16.

  • 14.

    Kendall, A.; Gal, Y. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 5574–5584.

  • 15.

    Guo, S.; Yan, Z.; Zhang, K.; et al. Toward Convolutional Blind Denoising of Real Photographs. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–20 June 2019; pp. 1712–1722. https://doi.org/10.1109/cvpr.2019.00181.

  • 16.

    Donoho, D.L. De-noising by soft-thresholding. IEEE Trans. Inf. Theory 1995, 41, 613–627. https://doi.org/10.1109/18.382009.

  • 17.

    Perona, P.; Malik, J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 1990, 12, 629–639. https://doi.org/10.1109/34.56205.

  • 18.

    Mairal, J.; Bach, F.; Ponce, J.; et al. Non-local sparse models for image restoration. In Proceedings of the 2009 IEEE 12th International Conference on Computer Vision (ICCV), Kyoto, Japan, 29 September–2 October 2009; pp. 2272–2279. https://doi.org/10.1109/iccv.2009.5459452.

  • 19.

    Zribi, M.; Sadok, I.; Marhaba, B. Kernel-Diffeomorphism Bayesian Bootstrap Filter to reduce speckle noise on SAR images. Comput. Stat. 2025, 40, 3613–3643. https://doi.org/10.1007/s00180-025-01650-1.

  • 20.

    Zhang, K.; Zuo, W.; Chen, Y.; et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Trans. Image Process. 2017, 26, 3142–3155. https://doi.org/10.1109/tip.2017.2662206.

  • 21.

    Zamir, S.W.; Arora, A.; Khan, S.; et al. Learning Enriched Features for Real Image Restoration and Enhancement. In Proceedings of the European Conference on Computer Vision, Cham, Switzerland, 23–28 August 2020; pp. 492–511. https://doi.org/10.1007/978-3-030-58595-2 30.

  • 22.

    Zamir, S.W.; Arora, A.; Khan, S.; et al. Multi-Stage Progressive Image Restoration. In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 14821–14831. https://doi.org/10.1109/cvpr46437.2021.01458.

  • 23.

    Hu, J.; Shen, L.; Sun, G. Squeeze-and-Excitation Networks. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–22 June 2018; pp. 7132–7141. https://doi.org/10.1109/cvpr.2018.00745.

  • 24.

    Cai, Y.; Bian, H.; Lin, J.; et al. Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 1–6 October 2023; pp. 12504–12513. https://doi.org/10.1109/iccv51070.2023.01149.

  • 25.

    Bai, J.; Yin, Y.; He, Q. RetinexMamba: Retinex-based Mamba for low-light image enhancement. arXiv 2024, arXiv:2405.03349.

  • 26.

    Adhikarla, E.; Zhang, K.; Chen, G.; et al. From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision. In Proceedings of the 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 6–10 March 2026; pp. 6956–6967. https://doi.org/10.1109/wacv61042.2026.00672.

  • 27.

    Gharbi, M.; Chaurasia, G.; Paris, S.; et al. Deep joint demosaicking and denoising. ACM Trans. Graph. 2016, 35, 1–12. https://doi.org/10.1145/2980179.2982399.

  • 28.

    Lakshminarayanan, B.; Pritzel, A.; Blundell, C. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 6402–6413.

  • 29.

    Hua, Y.; Shu, X.; Wang, Z.; et al. Uncertainty-guided voxel-level supervised contrastive learning for semi-supervised medical image segmentation.Int. J. Neural Syst. 2022, 32, 2250016. https://doi.org/10.1142/S0129065722500162.

  • 30.

    Roy, A.G.; Conjeti, S.; Navab, N.; et al. Bayesian QuickNAT: Model uncertainty in deep whole-brain segmentation for structure-wise quality control. NeuroImage 2019, 195, 11–22. https://doi.org/10.1016/j.neuroimage.2019.03.042.

  • 31.

    Sadok, I.; Zribi, M.; Fillali, O. Unsupervised Brain MRI Image Segmentation Based on the Finite Mixture of α-Stable Distributions with EM Algorithm. Math. Methods Stat. 2025, 34, 323–341. https://doi.org/10.3103/s1066530724600234.

  • 32.

    Julliand, T.; Nozick, V.; Talbot, H. Image Noise and Digital Image Forensics. In Proceedings of the International Workshop on Digital Watermarking (IWDW 2015), Tokyo, Japan, 7–10 October 2015; Lecture Notes in Computer Science; Springer: Cham, Switzerland, 2016; Volume 9569, pp. 3–17. https://doi.org/10.1007/978-3-319-31960-5 1.

  • 33.

    Sadok, I.; Masmoudi, A.; Zribi, M. Integrating the EM algorithm with particle filter for image restoration with exponential dispersion noise. Commun. Stat.-Theory Methods 2023, 52, 446–462. https://doi.org/10.1080/03610926.2021.1915336.

  • 34.

    Sadok, I.; Zribi, M. Image Restoration Using Weibull Particle Filters. In Proceedings of the 2022 4th International Conference on Pattern Analysis and Intelligent Systems (PAIS), Oum El Bouaghi, Algeria, 12–13 October 2022; pp. 1–6. https://doi.org/10.1109/pais56586.2022.9946893.

  • 35.

    Bigdeli, S.A.; Zwicker, M.; Favaro, P.; et al. Deep Mean-Shift Priors for Image Restoration. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 763–772.

  • 36.

    Wang, Y.; Wan, R.; Yang, W.; et al. Low-Light Image Enhancement with Normalizing Flow. Proc. AAAI Conf. Artif. Intell. 2022, 36, 2604–2612. https://doi.org/10.1609/aaai.v36i3.20162.

  • 37.

    He, K.; Sun, J.; Tang, X. Guided Image Filtering. IEEE Trans. Pattern Anal. Mach. Intell. 2013, 35, 1397–1409. https://doi.org/10.1109/tpami.2012.213.

  • 38.

    Yan, Q.; Shen, X.; Xu, L.; et al. Cross-Field Joint Image Restoration via Scale Map. In Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 1–8 December 2013; pp. 1537–1544. https://doi.org/10.1109/iccv.2013.194.

  • 39.

    Tian, C.; Fei, L.; Zheng, W.; et al. Deep learning on image denoising: An overview. Neural Netw. 2020, 131, 251–275. https://doi.org/10.1016/j.neunet.2020.07.025.

  • 40.

    Hoffman, M.D.; Blei, D.M.; Wang, C.; et al. Stochastic variational inference. J. Mach. Learn. Res. 2013, 14, 1303–1347.

  • 41.

    Buades, A.; Coll, B.; Morel, J.M. Nonlocal Image and Movie Denoising. Int. J. Comput. Vis. 2008, 76, 123–139. https://doi.org/10.1007/s11263-007-0052-1.

  • 42.

    Loshchilov, I.; Hutter, F. Decoupled weight decay regularization. Proc. ICLR 2019, 7, 11.

  • 43.

    Wang, W.; Wei, C.; Yang, W.; et al. GLADNet: Low-Light Enhancement Network with Global Awareness. In Proceedings of the 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), Xi’an, China, 15–19 May 2018; pp. 751–755. https://doi.org/10.1109/fg.2018.00118.

  • 44.

    Zhang, Y.; Zhang, J.; Guo, X. Kindling the Darkness: A Practical Low-light Image Enhancer. In Proceedings of the MM’19: The 27th ACM International Conference on Multimedia, Nice, France, 21–25 October 2019; pp. 1632–1640. https://doi.org/10.1145/3343031.3350926.

Share this article:
How to Cite
Sadok, I.; Benahmed, T. BayeUNet-NLM: A Bayesian U-Net with Uncertainty-Guided Non-Local Means Post-Processing for Extreme Low-Light Denoising. Applied Mathematics and Statistics 2026, 3 (2), 24. https://doi.org/10.53941/ams.2026.100024.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2026 by the authors.
Article Metrics
19
Article Views
0
Citations