Image Dehazing Algorithm Based on Transformer and Gated Fusion Mechanism
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [30]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Aiming at the existing image dehazing algorithms which still have problems such as incomplete dehazing, blurred edges of dehazed images, and detail information loss, this study presents an image dehazing algorithm based on Transformer and gated fusion mechanism. Global features of the image are extracted by the improved channel self-attention mechanism to improve the efficiency of the model in processing images. A multi-scale gated fusion block is designed to capture features of different scales. The gated fusion mechanism improves the adaptability of the model to different degrees of dehazing by dynamically adjusting weights while better preserving the image edges and detail information. Residual connections are used to enhance the reusability of features and improve the generalization ability of the model. Experimental verification shows that the proposed dehazing algorithm can effectively restore the content information in real hazy images. On the synthesized hazy image dataset SOTS, the peak signal-to-noise ratio reaches 34.841 dB, and the structural similarity reaches 0.984. The dehazed image has complete content information without blurred detail information and incomplete dehazing.

    Reference
    [1] Kaplan NH. Real-world image dehazing with improved joint enhancement and exposure fusion. Journal of Visual Communication and Image Representation, 2023, 90: 103720.
    [2] You JY, Korhonen J. Transformer for image quality assessment. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP). Anchorage: IEEE, 2021. 1389–1393.
    [3] Cheng BW, Misra I, Schwing AG, et al. Masked-attention mask Transformer for universal image segmentation. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022. 1280–1289.
    [4] Cai YH, Bian H, Lin J, et al. Retinexformer: One-stage Retinex-based Transformer for low-light image enhancement. Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris: IEEE, 2023. 12470–12479.
    [5] Aswini B, Josemartin MJ. Adaptive heuristic histogram equalisation approach combined with gamma transformation for image contrast enhancement. Proceedings of the 4th International Conference on Microelectronics, Signals & Systems (ICMSS). Kollam: IEEE, 2021. 1–6.
    [6] Di SY, Sun WS. Research on low illumination image processing algorithm based on adaptive parameter homomorphic filtering. Proceedings of the 2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML). Hangzhou: IEEE, 2022. 681–685.
    [7] 游达章, 陶加涛, 张业鹏, 等. 基于灰度变换及改进Retinex的低照度图像增强. 红外技术, 2023, 45(2): 161–170.
    [8] Cantor A. Optics of the atmosphere: Scattering by molecules and particles. IEEE Journal of Quantum Electronics, 1978, 14(9): 698–699.
    [9] He KM, Sun J, Tang XO. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341–2353.
    [10] Zhu QS, Mai JM, Shao L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 2015, 24(11): 3522–3533.
    [11] 杨振舰, 尚佳美, 张众维, 等. 基于残差注意力机制的图像去雾算法. 西北工业大学学报, 2021, 39(4): 901–908.
    [12] 寇大磊, 钱敏, 权冀川, 等. 基于多尺度卷积网络的快速图像去雾算法. 计算机工程与应用, 2020, 56(20): 191–198.
    [13] Cai BL, Xu XM, Jia K, et al. DehazeNet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187–5198.
    [14] Ren WQ, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks. Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer, 2016. 154–169.
    [15] Li BY, Peng XL, Wang ZY, et al. AOD-Net: All-in-one dehazing network. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017. 4780–4788.
    [16] Ren WQ, Ma L, Zhang JW, et al. Gated fusion network for single image dehazing. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 3253–3261.
    [17] Liu XH, Ma YR, Shi ZH, et al. GridDehazeNet: Attention-based multi-scale network for image dehazing. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE, 2019. 7313–7322.
    [18] Li Y, Cheng D, Zhang DW, et al. Single image dehazing with an independent detail-recovery network. Knowledge-based Systems, 2022, 254: 109579.
    [19] Yi QS, Li JC, Fang FM, et al. Efficient and accurate multi-scale topological network for single image dehazing. IEEE Transactions on Multimedia, 2022, 24: 3114–3128.
    [20] Xiao J, Fu XY, Liu AP, et al. Image de-raining Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 12978–12995.
    [21] Zhao HY, Gou YB, Li BY, et al. Comprehensive and delicate: An efficient Transformer for image restoration. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE, 2023. 14122–14132.
    [22] 张凯丽, 王安志, 熊娅维, 等. 基于Transformer的单幅图像去雾算法综述. 计算机科学与探索, 2024, 18(5): 1182–1196.
    [23] Chen HT, Wang YH, Guo TY, et al. Pre-trained image processing Transformer. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE, 2021. 12294–12305.
    [24] Liu Z, Lin YT, Cao Y, et al. Swin Transformer: Hierarchical vision Transformer using shifted windows. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal: IEEE, 2021. 9992–10002.
    [25] Liang JY, Cao JZ, Sun GL, et al. SwinIR: Image restoration using swin Transformer. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal: IEEE, 2021. 1833–1844.
    [26] Wang ZD, Cun XD, Bao JM, et al. UFormer: A general U-shaped Transformer for image restoration. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022. 17662–17672.
    [27] Zamir SW, Arora A, Khan S, et al. Restormer: Efficient Transformer for high-resolution image restoration. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022. 5718–5729.
    [28] Zhao D, Li J, Li HY, et al. Complementary feature enhanced network with vision Transformer for image dehazing. arXiv:2109.07100, 2021.
    [29] Song YD, He ZQ, Qian H, et al. Vision Transformers for single image dehazing. IEEE Transactions on Image Processing, 2023, 32: 1927–1941.
    [30] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929v2, 2021.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

王燕,陈燕燕,刘晶晶,胡津源.基于Transformer和门控融合机制的图像去雾算法.计算机系统应用,2025,34(2):1-10

Copy
Share
Article Metrics
  • Abstract:286
  • PDF: 1038
  • HTML: 190
  • Cited by: 0
History
  • Received:July 22,2024
  • Revised:September 03,2024
  • Online: December 09,2024
Article QR Code
You are the first990331Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063