Nighttime Image Dehazing: A Review
DOI:
https://doi.org/10.54097/ntztnp83Keywords:
Nighttime Image Dehazing, Traditional Methods, Deep LearningAbstract
Nighttime image dehazing is a core technology for improving the performance of all-weather visual systems, and its key challenge lies in overcoming the degradation of image quality caused by the coupling of multiple factors including haze degradation, inhomogeneous illumination, multi-light source interference and low signal-to-noise ratio (SNR). Traditional physics-based methods have inherent limitations under the complex illumination conditions of nighttime, while deep learning and multimodal fusion technologies have brought new breakthroughs to this field. The integration of data-driven approaches and physical constraints has significantly improved dehazing performance and scene adaptability. This paper systematically reviews the recent research advances in this field: firstly, it elaborates on the particularity of nighttime image degradation; secondly, it classifies and analyzes the mechanisms of existing methods; furthermore, it compares the performance of typical algorithms through subjective and objective experiments. Current research still faces challenges such as the scarcity of real-world data, insufficient model generalization ability and low computational efficiency. In the future, developing efficient, robust and physically interpretable algorithms, constructing high-quality datasets, and promoting end-to-end optimization with high-level vision tasks will become important research directions in this field. This paper aims to provide a systematic reference and technical outlook for subsequent research in this area.
Downloads
References
[1] Zhang J, Cao Y, Zha Z J, et al. Nighttime dehazing with a synthetic benchmark [C]//Proceedings of the 28th ACM international conference on multimedia. 2020: 2355-2363.
[2] Yan W, Tan R T, Dai D. Nighttime defogging using high-low frequency decomposition and grayscale-color networks [C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 473-488.
[3] McCartney E J. Optics of the atmosphere: scattering by molecules and particles [J]. New york, 1976.
[4] He K, Sun J, Tang X. Single image haze removal using dark channel prior [J]. IEEE transactions on pattern analysis and machine intelligence, 2010, 33(12): 2341-23534.
[5] Pei S C, Lee T Y. Nighttime haze removal using color transfer pre-processing and dark channel prior [C]//2012 19th IEEE International conference on image processing. IEEE, 2012: 957-960.
[6] Reinhard E, Adhikhmin M, Gooch B, et al. Color transfer between images [J]. IEEE Computer raphics and applications, 2001, 21(5): 34-41.
[7] Zhang J, Cao Y, Wang Z. Nighttime haze removal with illumination correction [J]. arXiv preprint arXiv:1606.01460, 2016.
[8] Li Y, Tan R T, Brown M S. Nighttime haze removal with glow and multiple light colors [C]//Proceedings of the IEEE international conference on computer vision. 2015: 226-234.
[9] McCartney E J. Optics of the atmosphere: scattering by molecules and particles [J]. New york, 1976.
[10] Zhang J, Cao Y, Fang S, et al. Fast haze removal for nighttime image using maximum reflectance prior [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7418-7426.
[11] YU S Y, ZHU H. Lighting model construction and haze removal for nighttime hazy images [J]. Optics and Precision Engineering, 2017, 25(3):729.
[12] Jobson D J, Rahman Z, Woodell G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes [J]. IEEE Transactions on Image processing, 1997, 6(7): 965-976.
[13] Shi Z, Zhu M, Guo B, et al. A photographic negative imaging inspired method for low illumination night-time image enhancement [J]. Multimedia Tools and Applications, 2017, 76(13): 15027-15048.
[14] Shi Z, Zhu M M, Guo B, et al. Nighttime low illumination image enhancement with single image using bright/dark channel prior [J]. EURASIP Journal on Image and Video Processing, 2018, 2018: 1-15.
[15] Ancuti C, Ancuti C O, De Vleeschouwer C, et al. Night-time dehazing by fusion [C]//2016 IEEE international conference on image processing (ICIP). IEEE, 2016: 2256-2260.
[16] FANG S Y, ZHAO Y K, LI X K, et al. Nighttime image dehazing based on illumination estimation [J]. Acta Electronica Sinica, 2016, 44(11): 2569-257.
[17] ZHOU T. Analysis of nighttime image dehazing and clarification based on structure-texture stratification [J]. Electronics World, 2020 (2): 107-107.
[18] TANG C M, DONG Y C, SUN X, et al. Restoration algorithm for single nighttime low-illumination haze image [J]. Journal of Computer-Aided Design & Computer Graphics, 2018, 55(6): 95-102.
[19] Xu L, Yan Q, Xia Y, et al. Structure extraction from texture via relative total variation [J]. ACM transactions on graphics (TOG), 2012, 31(6): 1-10.
[20] YANG A P, ZHAO M Q, WANG H X, et al. Nighttime image dehazing based on low-pass filtering and multi-feature joint optimization [J]. Acta Optica Sinica, 2018, 38(10): 1010006.
[21] Finlayson G D, Rey P A T, Trezzi E. Generalp constrained approach for colour constancy [C]//2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops). IEEE, 2011: 790-797.
[22] Kuanar S, Rao K R, Mahapatra D, et al. Night time haze and glow removal using deep dilated convolutional network [J]. arXiv preprint arXiv:1902.00855, 2019.
[23] Yu F. Multi-scale context aggregation by dilated convolutions [J]. arXiv preprint arXiv:1511.07122, 2015.
[24] Tang C, Yao W. NDPC-Net: A dehazing network in nighttime hazy traffic environments [C]//2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS). IEEE, 2022: 312-317.
[25] Yang C, Ke X, Hu P, et al. NightDNet: A Semi-Supervised Nighttime Haze Removal Frame Work for Single Image [C]//2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). IEEE, 2021: 716-719.
[26] Kis A, Ancuti C O. Night-time image dehazing using deep hierarchical network trained on day-time hazy images [C]//2022 International Symposium ELMAR. IEEE, 2022: 199-202.
[27] Oliveira M, Sappa A D, Santos V. Unsupervised local color correction for coarsely registered images[C]//CVPR 2011. IEEE, 2011: 201-208.
[28] Wang W, Wang A, Liu C. Variational single nighttime image haze removal with a gray haze-line prior [J]. IEEE Transactions on Image Processing, 2022, 31: 1349-1363.
[29] Yan W, Tan R T, Dai D. Nighttime defogging using high-low frequency decomposition and grayscale-color networks [C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 473-488.
[30] Liu Y, Yan Z, Chen S, et al. Nighthazeformer: Single nighttime haze removal using prior query transformer [C]//Proceedings of the 31st ACM International Conference on Multimedia. 2023: 4119-4128.
[31] Jin Y, Lin B, Yan W, et al. Enhancing visibility in nighttime haze images using guided apsf and gradient adaptive convolution [C]//Proceedings of the 31st ACM international conference on multimedia. 2023: 2446-2457.
[32] Cong X, Gui J, Zhang J, et al. A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 2631-2640.
[33] Lin B, Jin Y, Wending Y, et al. Nighthaze: Nighttime image dehazing via self-prior learning [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2025, 39(5): 5209-5217.
[34] Koo B, Kim G. Nighttime haze removal with glow decomposition using GAN [C]//Asian Conference on Pattern Recognition. Cham: Springer International Publishing, 2019: 807-820.
[35] Jin Y, Lin B, Yan W, et al. Enhancing visibility in nighttime haze images using guided apsf and gradient adaptive convolution [C]//Proceedings of the 31st ACM international conference on multimedia. 2023: 2446-2457.
[36] Pratt W K. Digital Image Processing [M]. New York: John Wiley & Sons, 1978.
[37] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
