Author:
Qin Hongyi,Belyaev Alexander G.
Abstract
AbstractThis paper presents a deep learning method for image dehazing and clarification. The main advantages of the method are high computational speed and using unpaired image data for training. The method adapts the Zero-DCE approach (Li et al. in IEEE Trans Pattern Anal Mach Intell 44(8):4225–4238, 2021) for the image dehazing problem and uses high-order curves to adjust the dynamic range of images and achieve dehazing. Training the proposed dehazing neural network does not require paired hazy and clear datasets but instead utilizes a set of loss functions, assessing the quality of dehazed images to drive the training process. Experiments on a large number of real-world hazy images demonstrate that our proposed network effectively removes haze while preserving details and enhancing brightness. Furthermore, on an affordable GPU-equipped laptop, the processing speed can reach 1000 FPS for images with 2K resolution, making it highly suitable for real-time dehazing applications.
Publisher
Springer Science and Business Media LLC
Reference39 articles.
1. He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2010)
2. Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: DehazeNet: an end-to-end system for single image haze removal. IEEE Trans. Image Process. 25(11), 5187–5198 (2016). https://doi.org/10.1109/TIP.2016.2598681
3. Liu, J., Liu, R.W., Sun, J., Zeng, T.: Rank-one prior: real-time scene recovery. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8845–8860 (2023)
4. Li, C., Guo, C., Loy, C.C.: Learning to enhance low-light image via zero-reference deep curve estimation. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4225–4238 (2021)
5. Narasimhan, S.G., Nayar, S.K.: Chromatic framework for vision in bad weather. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No. PR00662), vol. 1, pp. 598–6051 (2000). https://doi.org/10.1109/CVPR.2000.855874