基于改进CycleGAN模型的图像去雾算法
Image Dehazing Algorithm Based on Improved CycleGAN Model
DOI: 10.12677/csa.2024.1411228, PDF,   
作者: 王 悦, 姜超谦：青岛大学计算机科学技术学院，山东 青岛
关键词: 图像去雾；循环生成对抗网络；MB-TaylorFormer；多尺度；Image Dehazing； CycleGan； Mb-TaylorFormer； Multi-Scale
摘要: 图像去雾一直以来都是一个极具挑战的课题。本文基于循环生成对抗网络(cycle-consistent generative adversarial network, CycleGAN)进行改进。CycleGAN的生成器模块将引入基于泰勒展开的线性Transformer网络(MB-TaylorFormer)，有效解决注意力机制的二次计算复杂度，同时使用不同大小卷积以及深度可分离卷积和可变形卷积结合进行多尺度标记，提高去雾能力。实验表明，算法改进后图像去雾任务性能有效提高。
Abstract: Image dehazing has always been a highly challenging subject. This paper presents improvements to the cycle-consistent generative adversarial network (CycleGAN). The generator module of CycleGAN incorporates an MB-Taylor Former network, which is a linear Transformer based on Taylor expansion, effectively addressing the quadratic computational complexity of the attention mechanism. Additionally, it uses convolutions of varying sizes in combination with depthwise separable convolutions and deformable convolutions to perform multi-scale marking, thereby enhancing dehazing capabilities. Experiments demonstrate that the performance of image dehazing tasks is effectively improved following the enhancement of the algorithm.
文章引用：王悦, 姜超谦. 基于改进CycleGAN模型的图像去雾算法[J]. 计算机科学与应用, 2024, 14(11): 191-198. https://doi.org/10.12677/csa.2024.1411228

参考文献

[1] 纪平, 胡学友, 张瑞琦. 基于直方图均衡算法的图像增强技术研究[J]. 蚌埠学院学报, 2021, 10(2): 40-43.
[2] Land, E.H. and McCann, J.J. (1971) Lightness and Retinex Theory. Journal of the Optical Society of America, 61, 1-11. [Google Scholar] [CrossRef] [PubMed]
[3] Gao, T., Li, K., Chen, T., Liu, M., Mei, S., Xing, K., et al. (2020) A Novel UAV Sensing Image Defogging Method. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 2610-2625. [Google Scholar] [CrossRef] 
[4] He, K., Sun, J. and Tang, X. (2011) Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 2341-2353. [Google Scholar] [CrossRef] [PubMed]
[5] Cai, B., Xu, X., Jia, K., Qing, C. and Tao, D. (2016) Dehazenet: An End-to-End System for Single Image Haze Removal. IEEE Transactions on Image Processing, 25, 5187-5198. [Google Scholar] [CrossRef] [PubMed]
[6] Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X. and Yang, M. (2016) Single Image Dehazing via Multi-Scale Convolutional Neural Networks. Computer Vision—ECCV 2016, Amsterdam, 11-14 October 2016, 154-169. [Google Scholar] [CrossRef] 
[7] Li, B., Peng, X., Wang, Z., Xu, J. and Feng, D. (2017) AOD-Net: All-in-One Dehazing Network. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 4780-4788. [Google Scholar] [CrossRef] 
[8] Qin, X., Wang, Z., Bai, Y., Xie, X. and Jia, H. (2020) FFA-Net: Feature Fusion Attention Network for Single Image Dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 11908-11915. [Google Scholar] [CrossRef] 
[9] Qiu, Y., Zhang, K., Wang, C., Luo, W., Li, H. and Jin, Z. (2023) MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, 1-6 October 2023, 12756-12767. [Google Scholar] [CrossRef] 
[10] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010.
[11] Engin, D., Genc, A. and Ekenel, H.K. (2018) Cycle-Dehaze: Enhanced CycleGAN for Single Image De-Hazing. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 825-833. [Google Scholar] [CrossRef] 
[12] Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S. and Yang, M. (2022) Restormer: Efficient Transformer for High-Resolution Image Restoration. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 18-24 June 2022, 5718-5729. [Google Scholar] [CrossRef] 
[13] Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M., et al. (2020) Learning Enriched Features for Real Image Restoration and Enhancement. Computer Vision—ECCV 2020, Glasgow, 23-28 August 2020, 492-511. [Google Scholar] [CrossRef] 
[14] Shi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A.P., Bishop, R., et al. (2016) Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 1874-1883. [Google Scholar] [CrossRef] 
[15] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Munich, 5-9 October 2015, 234-241. [Google Scholar] [CrossRef] 
[16] Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L., Tan, M., et al. (2019) Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 1314-1324. [Google Scholar] [CrossRef] 
[17] Kingma, D.P. and Ba, J. (2014) Adam: A Method for Stochastic Optimization. arXiv:1412.6980.