AN ENHANCED DARK CHANNEL PRIOR WITH ITERATIVE TRANSMISSION UPDATE FOR SINGLE
DOI:
https://doi.org/10.35631/JISTM.1142001Keywords:
Atmospheric Scattering Model, Dark Channel Prior, Iterative Transmission Update, Single Image DehazingAbstract
Hazy images suffer from visibility degradation and colour distortion due to light scattering and atmospheric attenuation, which complicates downstream vision tasks and human interpretation. The Dark Channel Prior (DCP) remains a simple yet effective physically grounded method for single image dehazing; however, it tends to underestimate transmission in bright or textureless regions (e.g., sky or specular surfaces), leading to halo artefacts and colour distortions. To address this, this paper introduces a physically interpretable corrective term from the DCP-derived transmission–radiance pair to compensate for local violations of the dark-channel assumption. The proposed method iteratively refines both the transmission map and scene radiance without requiring region segmentation. Experiments on the RESIDE and NH-HAZE datasets demonstrate that our method achieves superior PSNR, SSIM, and colour fidelity than four representative model-based dehazing algorithms, while maintaining competitive computational efficiency. Overall, the proposed iterative refinement substantially enhances the robustness and visual quality of traditional prior-based dehazing while avoiding the computational burden and data dependency of deep learning approaches.
Downloads
References
Berman, D., Treibitz, T., & Avidan, S. (2020). Single image dehazing using haze-lines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(3), 720–734. https://doi.org/10.1109/TPAMI.2018.2882478
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. https://doi.org/10.1109/TIP.2016.2598681
Chen, D., He, M., Fan, Q., Liao, J., Zhang, L., Hou, D., Yuan, L., & Hua, G. (2019). Gated context aggregation network for image dehazing and deraining. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 1375-1383). https://doi.org/10.1109/WACV.2019.00151
Cui, Y., Zhi, S., Liu, W., Deng, J., & Ren, J. (2022). An improved dark channel defogging algorithm based on the HSI colour space. IET Image Processing, 16(3), 823–838. https://doi.org/10.1049/ipr2.12389
Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., & Yang, M. H. (2020). Multi-scale boosted dehazing network with dense feature fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2157-2167). https://doi.org/10.1109/CVPR42600.2020.00223
Deng, H., Li, Z., Zhang, F., Lu, Q., Cao, Z., Shao, Y., Gu, S., Gao, C., & Sang, N. (2025). Learning unpaired image dehazing with physics-based rehazy generation. arXiv. https://doi.org/10.48550/arXiv.2506.12824
Guo, C. L., Yan, Q., Anwar, S., Cong, R., Ren, W., & Li, C. (2022). Image dehazing transformer with transmission-aware 3D position embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5812-5820).
He, K., Sun, J., & Tang, X. (2011). Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), 2341–2353. https://doi.org/10.1109/TPAMI.2010.168
He, K., Sun, J., & Tang, X. (2012). Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(6), 1397–1409. https://doi.org/10.1109/TPAMI.2012.213
Jiang, A., Wu, M., Liu, F., Liu, B., & Zhang, C. (2024). PDUNet: Physical-prior-guided single image dehazing network via unpaired contrastive learning. SSRN. https://doi.org/10.2139/ssrn.4682033
Jiang, K., Wang, Z., Yi, P., Chen, C., Huang, B., Luo, Y., ... & Jiang, J. (2020). Multi-scale progressive fusion network for single image deraining. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 8346-8355). https://openaccess.thecvf.com/content_CVPR_2020/html/Jiang_Multi-Scale_Progressive_Fusion_Network_for_Single_Image_Deraining_CVPR_2020_paper.html
Kim, J., Ng, T. S., & Teoh, A. B. J. (2024). Enhancing image dehazing with a multi-DCP approach with adaptive airlight and gamma correction. Applied Sciences, 14(17), 7978. https://doi.org/10.3390/app14177978
Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2017). AOD-Net: All-in-one dehazing network. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 4770-4778). https://doi.org/10.1109/ICCV.2017.511
Tong, L., Liu, Y., Li, W., Chen, L., & Chen, E. (2024). Haze-aware attention network for single-image dehazing. Applied Sciences, 14(13), 5391. https://doi.org/10.3390/app14135391
Wu, H., Qu, Y., Lin, S., Zhou, J., Qiao, R., Zhang, Z., ... & Ma, L. (2021). Contrastive learning for compact single image dehazing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10551-10560).
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. https://doi.org/10.1109/TIP.2015.2446191
