A Single Image Dehazing using U-Net and Lightweight Vision Transformer
##plugins.themes.academic_pro.article.sidebar##
Published
Jun 30, 2025
Download
Statistic
Downloads
Download data is not yet available.
##plugins.themes.academic_pro.article.main##
Abstract
This research presents a single-image dehazing method that integrates a Lightweight Vision Transformer (LVT) and U-Net to capture both local and global features. LVT enhances resolution, U-Net extracts local features, and LVT refines global dependencies before fusion. Evaluations on O-Haze and HSTS datasets show PSNR scores of 27.88 (O-Haze, ResNet-50) and 28.22 (HSTS, no backbone), outperforming existing methods while maintaining competitive SSIM. The results demonstrate effectiveness in real-world haze scenarios, such as wildfire-induced haze in Indonesia.
##plugins.themes.academic_pro.article.details##
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
Aditya, D., & Yosrita, E. (2025). A Single Image Dehazing using U-Net and Lightweight Vision Transformer. Jurnal E-Komtek, 9(1), 182-197. https://doi.org/10.37339/e-komtek.v9i1.2352
References
[1] X. Jin, R. Tang, L. Liu, and J. Wu, “Vehicle license plate recognition for fog-haze environments,” IET Image Process, vol. 15, no. 6, pp. 1273–1284, 2021, doi: https://doi.org/10.1049/ipr2.12103.
[2] F. Guo, J. Yang, Z. Liu, and J. Tang, “Haze removal for single image: A comprehensive review,” Neurocomputing, vol. 537, pp. 85–109, 2023, doi: https://doi.org/10.1016/j.neucom.2023.03.061.
[3] Kementrian Lingkungan Hidup dan Kehutanan, “Kinerja pengendalian kebakaran hutan dan lahan tahun 2023,” https://ppid.menlhk.go.id/berita/siaran-pers/7579/kinerja-pengendalian-kebakaran-hutan-dan-lahan-tahun-2023, 2024.
[4] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 1956–1963. doi: 10.1109/CVPR.2009.5206515.
[5] O. D. Nurhayati, B. Surarso, W. A. Syafei, and D. M. K. Nugraheni, “Gaussian filter-based dark channel prior for image dehazing enhancement,” International Journal of Electrical and Computer Engineering, vol. 14, no. 5, pp. 5765–5778, Oct. 2024, doi: 10.11591/ijece.v14i5.pp5765-5778.
[6] W. Yan and L. Cui, “Image Dehaze Algorithm Based on Improved Atmospheric Scattering Models,” IEEE Access, vol. 12, pp. 98971–98976, 2024, doi: 10.1109/ACCESS.2024.3428568.
[7] E. Wang, S. Shu, and C. Fan, “CNN-based Single Image Dehazing via Attention Module,” in 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), 2022, pp. 683–687. doi: 10.1109/AUTEEE56487.2022.9994347.
[8] A. Zhao, L. Li, and S. Liu, “UIDF-Net: Unsupervised Image Dehazing and Fusion Utilizing GAN and Encoder–Decoder,” J Imaging, vol. 10, no. 7, 2024, doi: 10.3390/jimaging10070164.
[9] Y. Song, Z. He, H. Qian, and X. Du, “Vision Transformers for Single Image Dehazing,” IEEE Transactions on Image Processing, vol. 32, pp. 1927–1941, 2023, doi: 10.1109/TIP.2023.3256763.
[10] C. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “Image Dehazing Transformer with Transmission-Aware 3D Position Embedding,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 5802–5810. doi: 10.1109/CVPR52688.2022.00572.
[11] T. Guo and V. Monga, “Reinforced Depth-Aware Deep Learning for Single Image Dehazing,” in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 8891–8895. doi: 10.1109/ICASSP40776.2020.9054504.
[12] Z. Liu, B. Xiao, M. Alrabeiah, K. Wang, and J. Chen, “Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network,” IEEE Signal Process Lett, vol. 26, no. 6, pp. 833–837, 2019, doi: 10.1109/LSP.2019.2910403.
[13] M. A.-N. I. Fahim and H. Y. Jung, “Single Image Dehazing Using End-to-End Deep-Dehaze Network,” Electronics (Basel), vol. 10, no. 7, 2021, doi: 10.3390/electronics10070817.
[14] Y. Zhang and Y. Dong, “Single Image Dehazing via Reinforcement Learning,” in 2020 IEEE International Conference on Information Technology,Big Data and Artificial Intelligence (ICIBA), 2020, pp. 123–126. doi: 10.1109/ICIBA50161.2020.9277382.
[15] G. Kim, J. Park, and J. Kwon, “Deep Dehazing Powered by Image Processing Network,” 2023.
[16] N. Jiang, K. Hu, T. Zhang, W. Chen, Y. Xu, and T. Zhao, “Deep hybrid model for single image dehazing and detail refinement,” Pattern Recognit, vol. 136, p. 109227, 2023, doi: https://doi.org/10.1016/j.patcog.2022.109227.
[17] Z. Li, C. Zheng, H. Shu, and S. Wu, “Single Image Dehazing via Model-Based Deep-Learning,” in 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 141–145. doi: 10.1109/ICIP46576.2022.9897479.
[18] J. Gui et al., “A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning,” ACM Comput. Surv., vol. 55, no. 13s, Jul. 2023, doi: 10.1145/3576918.
[19] Y. Kang, L. Zhang, P. Hu, Y. Liu, H. Lu, and Y. He, “Learning depth-aware decomposition for single image dehazing,” Computer Vision and Image Understanding, vol. 248, p. 104069, 2024, doi: https://doi.org/10.1016/j.cviu.2024.104069.
[20] S. R. Gumma and B. M. Chintakindi, “FoNet: Focused Network for Single Image Deraining,” Circuits Syst Signal Process, 2025, doi: 10.1007/s00034-025-03009-9.
[21] D. Rawat and K. Singh, “A Comparative Study on Single Image Dehazing using Deep Learning-Based Techniques,” in 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2023, pp. 783–789. doi: 10.1109/ICAC3N60023.2023.10541689.
[22] L. Li and Y. Ning, “A review of image dehazing based on deep learning,” 2024. [Online]. Available: www.ijerm.com
[23] B. Li et al., “Benchmarking Single-Image Dehazing and Beyond,” IEEE Transactions on Image Processing, vol. 28, no. 1, pp. 492–505, 2019.
[24] C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer, “O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images,” in IEEE Conference on Computer Vision and Pattern Recognition, NTIRE Workshop , in NTIRE CVPR’18. 2018.
[25] D. Murcia-Gómez, I. Rojas-Valenzuela, and O. Valenzuela, “Impact of Image Preprocessing Methods and Deep Learning Models for Classifying Histopathological Breast Cancer Images,” Applied Sciences, vol. 12, no. 22, 2022, doi: 10.3390/app122211375.
[26] S. Roy and S. Chaudhuri, “SIVDSR-Dhaze: Single Image Dehazing with Very Deep Super Resolution Framework and Its Analysis,” Scientific Visualization, vol. 14, Feb. 2022, doi: 10.26583/sv.14.5.02.
[27] H. Zhou, Z. Chen, Q. Li, and T. Tao, “Dehaze-UNet: A Lightweight Network Based on UNet for Single-Image Dehazing,” Electronics (Basel), vol. 13, no. 11, 2024, doi: 10.3390/electronics13112082.
[28] N. Gawande, D. Goyal, and K. Sankhla, “Improved Deep Learning and Feature Fusion Techniques for Chronic Heart Failure,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 17s, pp. 67–80, 2024, [Online]. Available: https://www.ijisae.org/index.php/IJISAE/article/view/4837
[29] R. Dhivya and N. Shanmugapriya, “An Analysis Study of Various Image Preprocessing Filtering Techniques based on PSNR for Leaf Images,” in 2022 International Conference on Advanced Computing Technologies and Applications (ICACTA), 2022, pp. 1–8. doi: 10.1109/ICACTA54488.2022.9753444.
[30] S. Lee, S. Hong, G. Kim, and J. Ha, “SSIM-Based Autoencoder Modeling to Defeat Adversarial Patch Attacks,” Sensors, vol. 24, no. 19, 2024, doi: 10.3390/s24196461.
[31] B. Wang, L. Hu, B. Wei, Z. Kang, and C. Li, “Nighttime image dehazing using color cast removal and dual path multi-scale fusion strategy,” Front Comput Sci, vol. 16, no. 4, p. 164706, 2021, doi: 10.1007/s11704-021-0162-x.
[32] R. Lenka, A. Khandual, K. Dutta, and S. Nayak, “Image Enhancement: Application of Dehazing and Color Correction for Enhancement of Nighttime Low Illumination Image,” 2019, pp. 211–223. doi: 10.4018/978-1-7998-0066-8.ch011.
[33] C. Kim, “Region Adaptive Single Image Dehazing,” Entropy, vol. 23, no. 11, 2021, doi: 10.3390/e23111438.
[34] S. Salazar-Colores, E. U. Moya-Sánchez, J.-M. Ramos-Arreguín, E. Cabal-Yépez, G. Flores, and U. Cortés, “Fast Single Image Defogging With Robust Sky Detection,” IEEE Access, vol. 8, pp. 149176–149189, 2020, doi: 10.1109/ACCESS.2020.3015724.
[35] C. A. Hartanto and L. Rahadianti, “Single Image Dehazing Using Deep Learning,” JOIV : International Journal on Informatics Visualization, 2021, doi: http://dx.doi.org/10.30630/joiv.5.1.431.
[2] F. Guo, J. Yang, Z. Liu, and J. Tang, “Haze removal for single image: A comprehensive review,” Neurocomputing, vol. 537, pp. 85–109, 2023, doi: https://doi.org/10.1016/j.neucom.2023.03.061.
[3] Kementrian Lingkungan Hidup dan Kehutanan, “Kinerja pengendalian kebakaran hutan dan lahan tahun 2023,” https://ppid.menlhk.go.id/berita/siaran-pers/7579/kinerja-pengendalian-kebakaran-hutan-dan-lahan-tahun-2023, 2024.
[4] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 1956–1963. doi: 10.1109/CVPR.2009.5206515.
[5] O. D. Nurhayati, B. Surarso, W. A. Syafei, and D. M. K. Nugraheni, “Gaussian filter-based dark channel prior for image dehazing enhancement,” International Journal of Electrical and Computer Engineering, vol. 14, no. 5, pp. 5765–5778, Oct. 2024, doi: 10.11591/ijece.v14i5.pp5765-5778.
[6] W. Yan and L. Cui, “Image Dehaze Algorithm Based on Improved Atmospheric Scattering Models,” IEEE Access, vol. 12, pp. 98971–98976, 2024, doi: 10.1109/ACCESS.2024.3428568.
[7] E. Wang, S. Shu, and C. Fan, “CNN-based Single Image Dehazing via Attention Module,” in 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), 2022, pp. 683–687. doi: 10.1109/AUTEEE56487.2022.9994347.
[8] A. Zhao, L. Li, and S. Liu, “UIDF-Net: Unsupervised Image Dehazing and Fusion Utilizing GAN and Encoder–Decoder,” J Imaging, vol. 10, no. 7, 2024, doi: 10.3390/jimaging10070164.
[9] Y. Song, Z. He, H. Qian, and X. Du, “Vision Transformers for Single Image Dehazing,” IEEE Transactions on Image Processing, vol. 32, pp. 1927–1941, 2023, doi: 10.1109/TIP.2023.3256763.
[10] C. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “Image Dehazing Transformer with Transmission-Aware 3D Position Embedding,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 5802–5810. doi: 10.1109/CVPR52688.2022.00572.
[11] T. Guo and V. Monga, “Reinforced Depth-Aware Deep Learning for Single Image Dehazing,” in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 8891–8895. doi: 10.1109/ICASSP40776.2020.9054504.
[12] Z. Liu, B. Xiao, M. Alrabeiah, K. Wang, and J. Chen, “Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network,” IEEE Signal Process Lett, vol. 26, no. 6, pp. 833–837, 2019, doi: 10.1109/LSP.2019.2910403.
[13] M. A.-N. I. Fahim and H. Y. Jung, “Single Image Dehazing Using End-to-End Deep-Dehaze Network,” Electronics (Basel), vol. 10, no. 7, 2021, doi: 10.3390/electronics10070817.
[14] Y. Zhang and Y. Dong, “Single Image Dehazing via Reinforcement Learning,” in 2020 IEEE International Conference on Information Technology,Big Data and Artificial Intelligence (ICIBA), 2020, pp. 123–126. doi: 10.1109/ICIBA50161.2020.9277382.
[15] G. Kim, J. Park, and J. Kwon, “Deep Dehazing Powered by Image Processing Network,” 2023.
[16] N. Jiang, K. Hu, T. Zhang, W. Chen, Y. Xu, and T. Zhao, “Deep hybrid model for single image dehazing and detail refinement,” Pattern Recognit, vol. 136, p. 109227, 2023, doi: https://doi.org/10.1016/j.patcog.2022.109227.
[17] Z. Li, C. Zheng, H. Shu, and S. Wu, “Single Image Dehazing via Model-Based Deep-Learning,” in 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 141–145. doi: 10.1109/ICIP46576.2022.9897479.
[18] J. Gui et al., “A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning,” ACM Comput. Surv., vol. 55, no. 13s, Jul. 2023, doi: 10.1145/3576918.
[19] Y. Kang, L. Zhang, P. Hu, Y. Liu, H. Lu, and Y. He, “Learning depth-aware decomposition for single image dehazing,” Computer Vision and Image Understanding, vol. 248, p. 104069, 2024, doi: https://doi.org/10.1016/j.cviu.2024.104069.
[20] S. R. Gumma and B. M. Chintakindi, “FoNet: Focused Network for Single Image Deraining,” Circuits Syst Signal Process, 2025, doi: 10.1007/s00034-025-03009-9.
[21] D. Rawat and K. Singh, “A Comparative Study on Single Image Dehazing using Deep Learning-Based Techniques,” in 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2023, pp. 783–789. doi: 10.1109/ICAC3N60023.2023.10541689.
[22] L. Li and Y. Ning, “A review of image dehazing based on deep learning,” 2024. [Online]. Available: www.ijerm.com
[23] B. Li et al., “Benchmarking Single-Image Dehazing and Beyond,” IEEE Transactions on Image Processing, vol. 28, no. 1, pp. 492–505, 2019.
[24] C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer, “O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images,” in IEEE Conference on Computer Vision and Pattern Recognition, NTIRE Workshop , in NTIRE CVPR’18. 2018.
[25] D. Murcia-Gómez, I. Rojas-Valenzuela, and O. Valenzuela, “Impact of Image Preprocessing Methods and Deep Learning Models for Classifying Histopathological Breast Cancer Images,” Applied Sciences, vol. 12, no. 22, 2022, doi: 10.3390/app122211375.
[26] S. Roy and S. Chaudhuri, “SIVDSR-Dhaze: Single Image Dehazing with Very Deep Super Resolution Framework and Its Analysis,” Scientific Visualization, vol. 14, Feb. 2022, doi: 10.26583/sv.14.5.02.
[27] H. Zhou, Z. Chen, Q. Li, and T. Tao, “Dehaze-UNet: A Lightweight Network Based on UNet for Single-Image Dehazing,” Electronics (Basel), vol. 13, no. 11, 2024, doi: 10.3390/electronics13112082.
[28] N. Gawande, D. Goyal, and K. Sankhla, “Improved Deep Learning and Feature Fusion Techniques for Chronic Heart Failure,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 17s, pp. 67–80, 2024, [Online]. Available: https://www.ijisae.org/index.php/IJISAE/article/view/4837
[29] R. Dhivya and N. Shanmugapriya, “An Analysis Study of Various Image Preprocessing Filtering Techniques based on PSNR for Leaf Images,” in 2022 International Conference on Advanced Computing Technologies and Applications (ICACTA), 2022, pp. 1–8. doi: 10.1109/ICACTA54488.2022.9753444.
[30] S. Lee, S. Hong, G. Kim, and J. Ha, “SSIM-Based Autoencoder Modeling to Defeat Adversarial Patch Attacks,” Sensors, vol. 24, no. 19, 2024, doi: 10.3390/s24196461.
[31] B. Wang, L. Hu, B. Wei, Z. Kang, and C. Li, “Nighttime image dehazing using color cast removal and dual path multi-scale fusion strategy,” Front Comput Sci, vol. 16, no. 4, p. 164706, 2021, doi: 10.1007/s11704-021-0162-x.
[32] R. Lenka, A. Khandual, K. Dutta, and S. Nayak, “Image Enhancement: Application of Dehazing and Color Correction for Enhancement of Nighttime Low Illumination Image,” 2019, pp. 211–223. doi: 10.4018/978-1-7998-0066-8.ch011.
[33] C. Kim, “Region Adaptive Single Image Dehazing,” Entropy, vol. 23, no. 11, 2021, doi: 10.3390/e23111438.
[34] S. Salazar-Colores, E. U. Moya-Sánchez, J.-M. Ramos-Arreguín, E. Cabal-Yépez, G. Flores, and U. Cortés, “Fast Single Image Defogging With Robust Sky Detection,” IEEE Access, vol. 8, pp. 149176–149189, 2020, doi: 10.1109/ACCESS.2020.3015724.
[35] C. A. Hartanto and L. Rahadianti, “Single Image Dehazing Using Deep Learning,” JOIV : International Journal on Informatics Visualization, 2021, doi: http://dx.doi.org/10.30630/joiv.5.1.431.