A COMPREHENSIVE REVIEW OF SINGLE IMAGE DEHAZING METHODS: FROM CLASSIC PRIORS TO DEEP LEARNING
DOI:
https://doi.org/10.35631/JISTM.1144051Keywords:
Atmospheric Scattering, Domain Generalization, Deep Neural Networks, Image DehazingAbstract
Fog and haze not only reduce visibility, but also remove the contrast of the image, mute its colour, and erase the fine texture. Restoring such an image, a task called single image dehazing, has become a standard preprocessing step in many visual channels. In the past decade, handmade prior knowledge and deep learning models have been developed rapidly, but neither of them has solved the problem of reliable dehazing in the real environment. Most investigations remain in a family of methods a priori, transformer, or diffusion models. This review has a broader perspective. It regards a priori based, deep learning and hybrid methods as part of a story, and always focuses on the actual obstacles to deployment. We start with the atmospheric scattering model, which is the physical basis of most recovery frameworks. On this basis, we focus on the development of this field: Handmade prior knowledge, such as dark channel prior knowledge, convolutional network, generative confrontation model, attention-based transformers and diffusion model. In this process, our concerns are often pushed aside by cross domain generalization, the computational cost of edge devices, and the gap between the composite benchmark score and the perceived quality of the real world. Finally, we determined the direction that we should do more work: physical knowledge learning, unsupervised adaptation and lightweight system design. These directions are related to the deployment of infrastructure monitoring, autonomous navigation and public safety, in which reliable dehazing is not optional.
Downloads
References
An, S., Huang, X., Cao, L., & Wang, L. (2024). A comprehensive survey on image dehazing for different atmospheric scattering models. Multimedia Tools and Applications, 83(14), 40963-40993.
Ancuti, C. O., Ancuti, C., & Timofte, R. (2020, June). NH-HAZE: An image dehazing benchmark with non-homogeneous hazy and haze-free images. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1798-1805). IEEE.
Ancuti, C. O., Ancuti, C., Sbert, M., & Timofte, R. (2019, September). Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images. In 2019 IEEE international conference on image processing (ICIP) (pp. 1014-1018). IEEE.
Anvari, Z., & Athitsos, V. (2020, October). Evaluating single image dehazing methods under realistic sunlight haze. In International Symposium on Visual Computing (pp. 436-447). Cham: Springer International Publishing.
Ayoub, A., El-Shafai, W., El-Samie, F. E. A., Hamad, E. K., & EL-Rabaie, E. S. M. (2025). Review of dehazing techniques: challenges and future trends. Multimedia Tools and Applications, 84(3), 1103-1131.
Berman, D., & Avidan, S. (2016). Non-local image dehazing. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1674-1682).
Bhavsar, A. (2025). Hazedefy: A Lightweight Real-Time Image and Video Dehazing Pipeline for Practical Deployment. arXiv preprint, arXiv:2512.16609.
Cai, B., Xu, X., Jia, K., Qing, C., & Tao, D. (2016). Dehazenet: An end-to-end system for single image haze removal. IEEE transactions on image processing, 25(11), 5187-5198.
Chang, C. L., Tsai, F. J., Huang, Z., Gu, L., & Lin, C. W. (2025). Rehazing for Dehazing: A Physics-guided Parametric Augmentation Net. IEEE Journal of Selected Topics in Signal Processing.
Chen, W., & Cui, X. (2026). Image Dehazing in the Era of Generative AI: A Survey. IEEE Access.
Chen, Z., Cao, Y., Feng, Y., Hou, X., & Qian, X. (2026). Learning-based haze visibility ranking score for real-world traffic surveillance images. Journal of Visual Communication and Image Representation, 104770.
Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., & Yang, M. H. (2020, June). Multi-scale boosted dehazing network with dense feature fusion. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2154-2164). IEEE.
Engin, D., Genç, A., & Ekenel, H. K. (2018, June). Cycle-dehaze: Enhanced cyclegan for single image dehazing. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 938-9388). IEEE.
Fattal, R. (2008). Single image dehazing. ACM transactions on graphics (TOG), 27(3), 1-9.
Fu, M., Liu, H., Yu, Y., Chen, J., & Wang, K. (2021, June). Dw-gan: A discrete wavelet transform gan for nonhomogeneous dehazing. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 203-212). IEEE.
Gade, H. B., Odugu, V. K., Amreddy, M. R., Jaladi, M., Harivardhagini, S., & Pendem, S. (2025, December). High-Throughput Hardware Architecture for Hybrid Image Dehazing in Imaging Systems. In 2025 International Conference on Emerging Trends in Signal Processing & Computational Intelligence (ICCSPCI) (pp. 1-6). IEEE.
Gao, G., Cao, J., Bao, C., Hao, Q., Ma, A., & Li, G. (2022). A novel transformer-based attention network for image dehazing. Sensors, 22(9), 3428.
Gui, J., Cong, X., Cao, Y., Ren, W., Zhang, J., Zhang, J., ... & Tao, D. (2023). A comprehensive survey and taxonomy on single image dehazing based on deep learning. ACM Computing Surveys, 55(13s), 1-37.
Guo, C., Yan, Q., Anwar, S., Cong, R., Ren, W., & Li, C. (2022, June). Image dehazing transformer with transmission-aware 3d position embedding. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5802-5810). IEEE.
Guo, Y., Gao, Y., Liu, W., Lu, Y., Qu, J., He, S., & Ren, W. (2023). SCANet: Self-paced semi-curricular attention network for non-homogeneous image dehazing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 1885-1894).
Halford, G., Depoian, A. C., & Bailey, C. P. (2025, November). A computationally efficient deep learning model for real-time image dehazing on edge devices. In 2025 IEEE MetroCon (pp. 1-3). IEEE.
He, K., Sun, J., & Tang, X. (2010). Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence, 33(12), 2341-2353.
Huang, Y., Lin, Z., Xiong, S., & Sun, T. (2024). Diffusion models based null-space learning for remote sensing image dehazing. IEEE Geoscience and Remote Sensing Letters, 21, 1-5.
Jia, T., Li, J., Zhuo, L., & Zhang, J. (2024). Self-guided disentangled representation learning for single image dehazing. Neural Networks, 172, 106107.
Ju, M., Ding, C., Guo, C. A., Ren, W., & Tao, D. (2021). IDRLP: Image dehazing using region line prior. IEEE Transactions on Image Processing, 30, 9043-9057.
Kankanala, S., Raju, N., Thatikonda, R., & Chintakindi, B. M. (2026). A review of real-time single image dehazing architectures for embedded vision under adverse weather conditions. IEEE Access.
Lee, G. Y., Chen, J., Dam, T., Ferdaus, M. M., Poenar, D. P., & Duong, V. N. (2024). Dehazing remote sensing and uav imagery: A review of deep learning, prior-based, and hybrid approaches. arXiv preprint, arXiv:2405.07520.
Li, B., Gou, Y., Gu, S., Liu, J. Z., Zhou, J. T., & Peng, X. (2021). You only look yourself: Unsupervised and untrained single image dehazing neural network. International Journal of Computer Vision, 129(5), 1754-1767.
Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2017, October). Aod-net: All-in-one dehazing network. In 2017 IEEE international conference on computer vision (ICCV) (pp. 4780-4788). Ieee.
Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., & Wang, Z. (2018). Benchmarking single-image dehazing and beyond. IEEE transactions on image processing, 28(1), 492-505.
Li, G., Li, J., Chen, G., Wang, Z., Jin, S., Ding, C., & Zhang, W. (2023). Delving deeper into image dehazing: A survey. IEEE Access, 11, 131759-131774.
Li, L., Dong, Y., Ren, W., Pan, J., Gao, C., Sang, N., & Yang, M. H. (2019). Semi-supervised image dehazing. IEEE Transactions on Image Processing, 29, 2766-2779.
Li, Y., You, S., Brown, M. S., & Tan, R. T. (2017). Haze visibility enhancement: A survey and quantitative benchmarking. Computer Vision and Image Understanding, 165, 1-16.
Li, Z., Shu, H., & Zheng, C. (2021). Multi-scale single image dehazing using Laplacian and Gaussian pyramids. arXiv preprint, arXiv:2111.05700.
Li, Z., Zheng, C., Shu, H., & Wu, S. (2022). Dual-scale single image dehazing via neural augmentation. IEEE Transactions on Image Processing, 31, 6213-6223.
Liang, M. H., & Xu, G. L. (2025). Single Image Dehazing Method Guided by Edge Prior Information [J]. Advances in Lasers and Optoelectronics, 62(10), 478-486.
Liang, Y., Li, S., Cheng, D., Wang, W., Li, D., & Liang, J. (2025). Image dehazing via self-supervised depth guidance. Pattern Recognition, 158, 111051.
Liang, Y., Wang, B., Zuo, W., Liu, J., & Ren, W. (2022, July). Self-supervised learning and adaptation for single image dehazing. In IJCAI (pp. 1137-1143).
Liu, X., Ma, Y., Shi, Z., & Chen, J. (2019, October). Griddehazenet: Attention-based multi-scale network for image dehazing. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 7313-7322). IEEE.
Liu, Y., Liu, H., Li, L., Wu, Z., & Chen, J. (2023, June). A data-centric solution to nonhomogeneous dehazing via vision transformer. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1406-1415). IEEE.
McCartney, E. J., & Hall Jr, F. F. (1977). Optics of the atmosphere: scattering by molecules and particles.
Narasimhan, S. G., & Nayar, S. K. (2002). Vision and the atmosphere. International journal of computer vision, 48(3), 233-254.
Narasimhan, S. G., & Nayar, S. K. (2003). Contrast restoration of weather degraded images. IEEE transactions on pattern analysis and machine intelligence, 25(6), 713-724.
Nayar, S. K., & Narasimhan, S. G. (1999, September). Vision in bad weather. In Proceedings of the seventh IEEE international conference on computer vision (Vol. 2, pp. 820-827). IEEE.
Odugu, V. K., Gade, H. B., Charugundla, N. S., Inguva, A., Chinthareddy, V. R., & Banothu, B. (2026). FPGA and ASIC realization of a saturation-driven image dehazing technique for advanced driver assistance systems. Computers and Electrical Engineering, 137, 111247.
Qiao, Y. J., Shao, M. W., Tan, X. D., & Meng, L. Z. (2024, September). Uncertainty-aware diffusion model for real-world image dehazing. In 2024 International Conference on Machine Learning and Cybernetics (ICMLC) (pp. 65-70). IEEE.
Qin, X., Wang, Z., Bai, Y., Xie, X., & Jia, H. (2020, April). FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 07, pp. 11908-11915).
Rafiq, G., Rafiq, M., Jung, H. Y., & Choi, G. S. (2026). Evaluation Metrics for Single Image Dehazing: A Domain-Specific Composite Evaluation Framework and Comprehensive Review. IEEE Access.
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., & Yang, M. H. (2016, September). Single image dehazing via multi-scale convolutional neural networks. In European conference on computer vision (pp. 154-169). Cham: Springer International Publishing.
Rupesh, G., Singh, N., & Divya, T. (2024). DehazeDNet: image dehazing via depth evaluation. Signal, Image and Video Processing, 18(12), 9387-9395.
Sakaridis, C., Dai, D., & Van Gool, L. (2018). Semantic foggy scene understanding with synthetic data. International Journal of Computer Vision, 126(9), 973-992.
Song, Y., He, Z., Qian, H., & Du, X. (2022). Vision transformers for single image dehazing. arXiv preprint, arXiv:2204.03883.
Song, Z., Li, R., Zhang, Z., Wang, T., Lu, J., Yu, X., & Zhang, K. (2026). Deep image restoration in adverse weather: A survey. Neural Networks, *2026*, Article 109472.
Su, X., Li, S., Cui, Y., Cao, M., Zhang, Y., Chen, Z., ... & Yuan, X. (2025, April). Prior-guided hierarchical harmonization network for efficient image dehazing. In Proceedings of the AAAI conference on artificial intelligence (Vol. 39, No. 7, pp. 7042-7050).
Sun, H., Luo, Z., Ren, D., Du, B., Chang, L., & Wan, J. (2024). Unsupervised multi-branch network with high-frequency enhancement for image dehazing. Pattern Recognition, 156, 110763.
Sun, Z., Zhang, Y., Bao, F., Shao, K., Liu, X., & Zhang, C. (2021). ICycleGAN: Single image dehazing based on iterative dehazing model and CycleGAN. Computer Vision and Image Understanding, 203, 103133.
Tang, J., Che, W. G., & Gao, S. X. (2023). An image dehazing method based on multi-scale convolution with attention mechanism. Computer Engineering & Science, 45(08), 1453.
Tarel, J. P., & Hautiere, N. (2009, September). Fast visibility restoration from a single color or gray level image. In 2009 IEEE 12th international conference on computer vision (pp. 2201-2208). IEEE.
Tran, L. A., Moon, S., & Park, D. C. (2022). A novel encoder-decoder network with guided transmission map for single image dehazing. Procedia Computer Science, 204, 682-689.
Tsai, F. J., Peng, Y. T., Lin, Y. Y., & Lin, C. W. (2025, October). Phatnet: A physics-guided haze transfer network for domain-adaptive real-world image dehazing. In 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 5591-5600). IEEE.
Wang, C., & Fan, Y. (2025). HazeTrendNet: Single‐Image Dehazing via Haze‐Concentration‐Trend Guidance. Electronics Letters, 61(1), e70396.
Wang, J., & Hu, H. (2024, January). Image dehazing based on iterative-refining diffusion model. In Proceedings of the 2024 7th International Conference on Image and Graphics Processing (pp. 355-362).
Wang, J., Wu, S., Yuan, Z., Tong, Q., & Xu, K. (2024). Frequency compensated diffusion model for real-scene dehazing. Neural Networks, 175, 106281.
Wang, P., Zhu, H., Huang, H., Zhang, H., & Wang, N. (2021). TMS-GAN: A twofold multi-scale generative adversarial network for single image dehazing. IEEE Transactions on Circuits and Systems for Video Technology, 32(5), 2760-2772.
Wang, Z., Zhao, H., Peng, J., Yao, L., & Zhao, K. (2024, June). Odcr: Orthogonal decoupling contrastive regularization for unpaired image dehazing. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 25479-25489). IEEE.
Wasi, A., & Shiney, O. J. (2023, November). Dhformer: A vision transformer-based attention module for image dehazing. In International Conference on Computer Vision and Image Processing (pp. 148-159). Cham: Springer Nature Switzerland.
Xiao, X., Ren, Y., Li, Z., Zhang, N., & Zhou, W. (2023). Self-supervised zero-shot dehazing network based on dark channel prior. Frontiers of Optoelectronics, 16(1), 7.
Xie, S., Li, F., & Ju, M. (2024, July). Frequency-based and physics-guiding diffusion model for single image dehazing. In 2024 43rd Chinese Control Conference (CCC) (pp. 7262-7267). IEEE.
Xiong, J., Yan, X., Wang, Y., Zhao, W., Zhang, X. P., & Wei, M. (2024). RSHazeDiff: A unified Fourier-aware diffusion model for remote sensing image dehazing. IEEE Transactions on Intelligent Transportation Systems, 26(1), 1055-1070.
Yang, F., & Zhang, Q. (2022). Depth aware image dehazing: F. Yang, Q. Zhang. The Visual Computer, 38(5), 1579-1587.
Yin, S., Shi, Y., Wang, Y., & Yang, Y. H. (2025). When aware haze density meets diffusion model for synthetic-to-real dehazing. IEEE Transactions on Circuits and Systems for Video Technology, 35(5), 4242-4255.
Zhang, K., Wang, A., Xiong, Y., & Liu, Y. (2024). Survey of Transformer-Based Single Image Dehazing Methods. Journal of Frontiers of Computer Science & Technology, 18(5), 1182.
Zhang, L., Bai, W., & Xiao, C. (2024, October). Density‐Aware Diffusion Model for Efficient Image Dehazing. In Computer Graphics Forum (Vol. 43, No. 7, p. e15221).
Zheng, C., Ying, W., & Hu, Q. (2025). Comparative analysis of dehazing algorithms on real-world hazy images. Scientific Reports, 15(1), 10822.
Zhou, H., Liu, X., Zhang, Z., Yun, J., Li, C., Yang, Y., ... & Wu, X. J. (2026). Remote sensing image dehazing: A systematic review of progress, challenges, and prospects. ISPRS Journal of Photogrammetry and Remote Sensing, 235, 318-348.
Zhou, S., Liu, Y., Hao, C., Liu, Z., & Tian, J. (2025). IDDM: Bridging Synthetic-to-Real Domain Gap from Physics-Guided Diffusion for Real-world Image Dehazing. arXiv e-prints, arXiv-2504.
Zhu, L., Su, Y., Cui, Z., Lan, Y., Wang, N., Zhang, L., & Cai, Y. (2026). Diffusion Models and Its Applications in Image Dehazing: A Survey. IET Image Processing, 20(1), e70346.
Zhu, Q., Mai, J., & Shao, L. (2015). A fast single image haze removal algorithm using color attenuation prior. IEEE transactions on image processing, 24(11), 3522-3533.
