Keywords:-
Article Content:-
Abstract
Outdoor videos captured in poor weather conditions, such as haze or fog, often suffer from reduced visibility, affecting both cinematography and surveillance applications. The light scattering and absorption caused by aerosols in the atmosphere and airlight reflection result in images with faded colors and decreased contrast. This paper presents a novel approach to video dehazing by leveraging Deep Learning (DL), specifically utilizing the Denoising Diffusion Probabilistic Model (DDPM) for haze removal and a Multi-Scale Boosted Dehazing Network (MSBDN) with Dense Feature Fusion for enhanced image quality. We refine the transmission map using trilateral filtering to achieve smooth edge transitions and improve dehazing performance. Our method is evaluated on both synthetic and real-world datasets, demonstrating its robustness and effectiveness compared to state-of-the-art dehazing algorithms.
References:-
References
Duminil, Edward, Laurent Risser, Marie Péron, and Jean-Baptiste Thomas. "VIREDA: A Real-World Video Defogging Dataset and Transformer-CNN-Based Defogging Model." Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Shrivastava, Abhishek, Ravi Kumar Gupta, Prashant Srivastava, and Amit Raj. "Video Decomposition Prior: Learning Video Decomposition Without Task-Specific Datasets." Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Han, Congwei, Yifan Zhang, Xiaolong Liu, and Zhen Li. "MAVDN: Multiscale Attention Video Dehazing Network for Improved Video Clarity." IEEE Transactions on Image Processing, vol. 33, pp. 1-14, 2024.
Zhang, Yiming, Rui Li, Zhenhong Chen, and Xiaofei Wang. "REVIDE: A Real-World Video Dehazing Dataset for Supervised Learning." Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Li, Jianhua, Minghao Wu, Sheng Zhang, and Lijun Yang. "A Survey on Diffusion Models for Image Restoration: Supervised and Zero-Shot Approaches." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 2, pp. 1234-1250, 2024.
Vishwakarma, Rohit, Anuj Shukla, Deepak Kumar, and Nandini Agrawal. "CA-VAE: Contrastive Attention Over Variational Auto-Encoders for Single Image Dehazing." IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 1, pp. 567-579, 2023.
Imai, Wataru, Hiroshi Takagi, Kenta Nakamura, and Satoshi Fujita. "Enhanced Multi-Scale Attention Network (EMSAN) for Single Image Dehazing." Pattern Recognition Letters, vol. 182, pp. 45-56, 2024.
Jiang, Yiyang. "Research on Denoising Diffusion Probabilistic Models." Neural Computation, vol. 36, no. 4, pp. 789-812, 2024.
Amin, Nisha; Rajput, G G (2025), “Real-World Video Datasets for Haze Removal”, Mendeley Data, V3, doi: 10.17632/fm8g8k6js7.3
Amin, N., Geeta, B., Raibagkar, R. L., & Rajput, G. G. (2024). Single image dehazing using dark channel prior and type-2 fuzzy sets. International Journal of Signal Processing, 9, 28–34
Lee, S., Yun, S., Nam, JH. et al. A review on dark channel prior based image dehazing algorithms. J Image Video Proc. 2016, 4 (2016). https://doi.org/10.1186/s13640-016-0104-y
Ke, N., Chen, J.: “Real-time visibility restoration from a single image”. In: Proceedings on IEEE International Conference on Image Processing, pp. 923–927 (2013)
Chen, S.-Z & Ren, Z.-G & Qiusheng, Lian. (2016). Single image dehazing algorithm based on improved dark channel prior and guided filter. 42. 455-465. 10.16383/j.aas.2016.c150212.
Feng Yu, Chunmei Qing, Xiangmin, Xu, Bolun Cai, “Image and video dehazing using view-based cluster segmentation”, 2016.
Yongmin Park, Tae-Hwan kim, “Fast execution scheme for dark-channel-prior outdoor video dehazing”, IEEE, ACCESS, vol. 6, pp. 10003-10014, March 2018.