AUT Journal of Electrical Engineering

AUT Journal of Electrical Engineering

Attention-Guided Dehazing: A New Architecture with Low-Level and Multi-Level Channel Attention

Document Type : Research Article

Authors
Hossein Noori
Mohammad Hossein Gholizadeh
Gholamreza Memarzadeh
Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran.
10.22060/eej.2026.24359.5691
Abstract
Single-image dehazing has become increasingly vital in recent years due to its foundational role in enhancing high-level vision tasks such as object detection, remote sensing, and autonomous driving. While numerous deep learning-based approaches have been proposed, many still fall short in fully preserving image details and capturing complex haze patterns. In this paper, a novel end-to-end architecture for single-image dehazing is presented that addresses key limitations of existing methods. The proposed network integrates two innovative modules: the Low-Level Feature Attention (LLFA) module, which emphasizes the retention of fine-grained details often lost in deeper layers, and the Multi-Level Channel Attention (MLCA) module, which dynamically fuses low- and high-level features to improve the network’s representational capacity. By leveraging these complementary modules across multiple resolution scales, the architecture achieves more effective feature extraction and superior haze removal. Extensive experiments on both synthetic and real-world datasets demonstrate that our method consistently outperforms state-of-the-art algorithms in both qualitative visual clarity and quantitative evaluation metrics. The results confirm the robustness and efficiency of the proposed approach in producing clean, detail-rich dehazed images.
Keywords
Defogging/Dehazing
Feature Attention
Deep Learning
Channel Attention
Convolutional Neural Networks
Subjects
[1] Z. Chen, Y. Wang, Y. Yang, D. Liu, PSD: Principled synthetic-to-real dehazing guided by physical priors, in:  Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 7180-7189.
[2] Y.Y. Schechner, S.G. Narasimhan, S.K. Nayar, Instant dehazing of images using polarization, in:  Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, IEEE, 2001, pp. I-I.
[3] Y.Y. Schechner, S.G. Narasimhan, S.K. Nayar, Polarization-based vision through haze, Applied optics, 42(3) (2003) 511-525.
[4] S.G. Narasimhan, S.K. Nayar, Chromatic framework for vision in bad weather, in:  Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No. PR00662), IEEE, 2000, pp. 598-605.
[5] S.K. Nayar, S.G. Narasimhan, Vision in bad weather, in:  Proceedings of the seventh IEEE international conference on computer vision, IEEE, 1999, pp. 820-827.
[6] C.O. Ancuti, C. Ancuti, Single image dehazing by multi-scale fusion, IEEE Transactions on Image Processing, 22(8) (2013) 3271-3282.
[7] J.-M. Guo, J.-y. Syue, V.R. Radzicki, H. Lee, An efficient fusion-based defogging, IEEE Transactions on Image Processing, 26(9) (2017) 4217-4228.
[8] A. Galdran, Image dehazing by artificial multiple-exposure image fusion, Signal Processing, 149 (2018) 135-147.
[9] C. Ancuti, C.O. Ancuti, C. De Vleeschouwer, A.C. Bovik, Day and night-time dehazing by local airlight estimation, IEEE Transactions on Image Processing, 29 (2020) 6264-6275.
[10] X. Liu, H. Li, C. Zhu, Joint contrast enhancement and exposure fusion for real-world image dehazing, IEEE transactions on multimedia, 24 (2021) 3934-3946.
[11] P. Pandey, R. Gupta, N. Goel, Enhancement of single foggy image using feature based fusion technique, Multimedia Tools and Applications, 84(23) (2025) 27401-27424.
[12] Y.-K. Wang, C.-T. Fan, Single image defogging by multiscale depth fusion, IEEE Transactions on image processing, 23(11) (2014) 4826-4837.
[13] W. Mao, D. Zheng, M. Chen, J. Chen, Single image defogging via multi-exposure image fusion and detail enhancement, Journal of Safety Science and Resilience, 5(1) (2024) 37-46.
[14] R. Fattal, Single image dehazing, ACM transactions on graphics (TOG), 27(3) (2008) 1-9.
[15] R. Fattal, Dehazing using color-lines, ACM transactions on graphics (TOG), 34(1) (2014) 1-14.
[16] D. Berman, S. Avidan, Non-local image dehazing, in:  Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1674-1682.
[17] Q. Zhu, J. Mai, L. Shao, A fast single image haze removal algorithm using color attenuation prior, IEEE transactions on image processing, 24(11) (2015) 3522-3533.
[18] R.T. Tan, Visibility in bad weather from a single image, in:  2008 IEEE conference on computer vision and pattern recognition, IEEE, 2008, pp. 1-8.
[19] K. He, J. Sun, X. Tang, Single image haze removal using dark channel prior, IEEE transactions on pattern analysis and machine intelligence, 33(12) (2010) 2341-2353.
[20] X. He, J. Mao, Z. Liu, J. Zhou, Y. Hua, A fast algorithm for image defogging, in:  Chinese Conference on Pattern Recognition, Springer, 2014, pp. 149-158.
[21] Z. Tufail, K. Khurshid, A. Salman, I.F. Nizami, K. Khurshid, B. Jeon, Improved dark channel prior for image defogging using RGB and YCbCr color space, IEEE Access, 6 (2018) 32576-32587.
[22] A. Kumari, S. Sahdev, S. Sahoo, Improved single image and video dehazing using morphological operation, in:  2015 International Conference on VLSI Systems, Architecture, Technology and Applications (VLSI-SATA), IEEE, 2015, pp. 1-5.
[23] K. He, J. Sun, X. Tang, Guided image filtering, IEEE transactions on pattern analysis and machine intelligence, 35(6) (2012) 1397-1409.
[24] S. Wen, Y. Zhao, J. Ma, H. keung Lam, H. Wang, Image defogging algorithm based on image bright and dark channels, in:  2018 WRC Symposium on Advanced Robotics and Automation (WRC SARA), IEEE, 2018, pp. 269-274.
[25] C. Zhen, S. Jihong, P. Roth, Single Image Defogging Algorithm based on Dark Channel Priority, Journal of Multimedia, 8(4) (2013).
[26] Z. Tufail, K. Khurshid, A. Salman, K. Khurshid, Optimisation of transmission map for improved image defogging, IET Image Processing, 13(7) (2019) 1161-1169.
[27] F. Guo, H. Peng, J. Tang, A new restoration algorithm for single image defogging, in:  Chinese Conference on Pattern Recognition, Springer, 2014, pp. 169-178.
[28] R.M. Yousaf, H.A. Habib, Z. Mehmood, A. Banjar, R. Alharbey, O. Aboulola, Single Image Dehazing and Edge Preservation Based on the Dark Channel Probability‐Weighted Moments, Mathematical Problems in Engineering, 2019(1) (2019) 9721503.
[29] L. He, J. Zhao, N. Zheng, D. Bi, Haze removal using the difference-structure-preservation prior, IEEE transactions on image processing, 26(3) (2016) 1063-1075.
[30] M. Ju, D. Zhang, X. Wang, Single image dehazing via an improved atmospheric scattering model, The Visual Computer, 33(12) (2017) 1613-1625.
[31] I. Yoon, S. Kim, D. Kim, M.H. Hayes, J. Paik, Adaptive defogging with color correction in the HSV color space for consumer surveillance system, IEEE transactions on consumer electronics, 58(1) (2012) 111-116.
[32] J.-P. Tarel, N. Hautiere, Fast visibility restoration from a single color or gray level image, in:  2009 IEEE 12th international conference on computer vision, IEEE, 2009, pp. 2201-2208.
[33] A. Sabir, K. Khurshid, A. Salman, Segmentation-based image defogging using modified dark channel prior, EURASIP Journal on Image and Video Processing, 2020(1) (2020) 6.
[34] M.I. Anwar, A. Khosla, Vision enhancement through single image fog removal, Engineering science and technology, an international journal, 20(3) (2017) 1075-1083.
[35] F. Yang, Y. Hu, Improved Dark Channel Prior for Image Defogging, in:  2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT), IEEE, 2022, pp. 1-4.
[36] C. Qin, X. Gu, A single image dehazing method based on decomposition strategy, Journal of Systems Engineering and Electronics, 33(2) (2022) 279-293.
[37] X. Kang, Z. Fei, P. Duan, S. Li, Fog model-based hyperspectral image defogging, IEEE Transactions on Geoscience and Remote Sensing, 60 (2021) 1-12.
[38] S.E. Kim, T.H. Park, I.K. Eom, Fast single image dehazing using saturation based transmission map estimation, IEEE Transactions on Image Processing, 29 (2019) 1985-1998.
[39] P. Ling, H. Chen, X. Tan, Y. Jin, E. Chen, Single image dehazing using saturation line prior, IEEE Transactions on Image Processing, 32 (2023) 3238-3253.
[40] W. Zhang, L. Dong, X. Pan, J. Zhou, L. Qin, W. Xu, Single image defogging based on multi-channel convolutional MSRCR, IEEE Access, 7 (2019) 72492-72504.
[41] H. Noori, M.H. Gholizadeh, H.K. Rafsanjani, Digital image defogging using joint Retinex theory and independent component analysis, Computer Vision and Image Understanding, 245 (2024) 104033.
[42] J. Wang, K. Lu, J. Xue, N. He, L. Shao, Single image dehazing based on the physical model and MSRCR algorithm, IEEE Transactions on Circuits and Systems for Video Technology, 28(9) (2017) 2190-2199.
[43] G. Qingqing, W. Xiangping, W. Ke, W. Shuang, H. Shaowei, Adaptive Retinex image defogging algorithm based on the depth of field information, in:  2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), IEEE, 2022, pp. 1-7.
[44] F. Guo, J. Yang, Z. Liu, J. Tang, Haze removal for single image: A comprehensive review, Neurocomputing, 537 (2023) 85-109.
[45] Y. Xu, J. Wen, L. Fei, Z. Zhang, Review of video and image defogging algorithms and related studies on image restoration and enhancement, Ieee Access, 4 (2015) 165-188.
[46] J. Wang, H. Wang, Y. Sun, J. Yang, Improved retinex-theory-based low-light image enhancement algorithm, Applied Sciences, 13(14) (2023) 8148.
[47] M. Yang, Z. Li, J. Liu, Super-pixel based single image haze removal, in:  2016 Chinese Control and Decision Conference (CCDC), IEEE, 2016, pp. 1965-1969.
[48] B. Cai, X. Xu, K. Jia, C. Qing, D. Tao, Dehazenet: An end-to-end system for single image haze removal, IEEE transactions on image processing, 25(11) (2016) 5187-5198.
[49] S. Yin, X. Yang, R. Lu, Z. Deng, Y.-H. Yang, Visual Attention and ODE-inspired Fusion Network for image dehazing, Engineering Applications of Artificial Intelligence, 130 (2024) 107692.
[50] B. Xiao, Z. Zheng, Y. Zhuang, C. Lyu, X. Jia, Single UHD image dehazing via interpretable pyramid network, Signal Processing, 214 (2024) 109225.
[51] B. Li, X. Peng, Z. Wang, J. Xu, D. Feng, Aod-net: All-in-one dehazing network, in:  Proceedings of the IEEE international conference on computer vision, 2017, pp. 4770-4778.
[52] Z. Chen, Z. He, Z.-M. Lu, DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention, IEEE transactions on image processing, 33 (2024) 1002-1015.
[53] H. Zhang, V.M. Patel, Densely connected pyramid dehazing network, in:  Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3194-3203.
[54] Z. Zheng, W. Ren, X. Cao, X. Hu, T. Wang, F. Song, X. Jia, Ultra-high-definition image dehazing via multi-guided bilateral learning, in:  2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2021, pp. 16180-16189.
[55] X. Qin, Z. Wang, Y. Bai, X. Xie, H. Jia, FFA-Net: Feature fusion attention network for single image dehazing, in:  Proceedings of the AAAI conference on artificial intelligence, 2020, pp. 11908-11915.
[56] D. Chen, M. He, Q. Fan, J. Liao, L. Zhang, D. Hou, L. Yuan, G. Hua, Gated context aggregation network for image dehazing and deraining, in:  2019 IEEE winter conference on applications of computer vision (WACV), IEEE, 2019, pp. 1375-1383.
[57] X. Liu, Y. Ma, Z. Shi, J. Chen, Griddehazenet: Attention-based multi-scale network for image dehazing, in:  Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 7314-7323.
[58] Y. Qu, Y. Chen, J. Huang, Y. Xie, Enhanced pix2pix dehazing network, in:  Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 8160-8168.
[59] J. Ming, Z. Cai, S. Li, S. Bi, Y. Ning, Single image dehazing based on convolutional neural network and multiple attention fusion, Signal, Image and Video Processing, 19(4) (2025) 294.
[60] L. Lu, Q. Xiong, B. Xu, D. Chu, Mixdehazenet: Mix structure block for image dehazing network, in:  2024 International Joint Conference on Neural Networks (IJCNN), IEEE, 2024, pp. 1-10.
[61] Y. Song, Z. He, H. Qian, X. Du, Vision transformers for single image dehazing, IEEE Transactions on Image Processing, 32 (2023) 1927-1941.
[62] J. Li, Y. Li, L. Zhuo, L. Kuang, T. Yu, USID-Net: Unsupervised single image dehazing network via disentangled representations, IEEE transactions on multimedia, 25 (2022) 3587-3601.
[63] J. Chen, G. Zhao, Contrastive multiscale transformer for image dehazing, Sensors, 24(7) (2024) 2041.
[64] W. Li, D. Fan, Q. Zhu, Z. Gao, H. Sun, HEDehazeNet: Unpaired image dehazing via enhanced haze generation, Image and Vision Computing, 150 (2024) 105236.
[65] L.K. Choi, J. You, A.C. Bovik, Referenceless prediction of perceptual fog density and perceptual image defogging, IEEE Transactions on Image Processing, 24(11) (2015) 3888-3901.
[66] A. Mittal, R. Soundararajan, A.C. Bovik, Making a “completely blind” image quality analyzer, IEEE Signal processing letters, 20(3) (2012) 209-212.
[67] M. Yu, S. Xu, H. Sun, Y. Zheng, W. Yang, Hierarchical slice interaction and multi-layer cooperative decoding networks for remote sensing image dehazing, Image and Vision Computing, 148 (2024) 105129.
[68] B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, Z. Wang, Benchmarking single-image dehazing and beyond, IEEE transactions on image processing, 28(1) (2018) 492-505.
AUT Journal of Electrical Engineering
Volume 58, Issue 2
2026
Pages 383-404