Abstract
Most deep learning based single image dehazing methods use convolutional neural networks (CNN) to extract features, however CNN can only capture local features. To address the limitations of CNN, We propose a basic module that combines CNN and graph convolutional network (GCN) to capture both local and non-local features. The basic module consist of a CNN with triple attention modules (CAM) and a dual GCN module (DGM). CAM that combines the channel attention, spatial attention and pixel attention is designed to earn more weight from important local features. DGM combines spatial coherence computing and channel correlation computing to extract non-local information. The architecture of the network is similar to U-Net, and skip connections used in the symmetrical network can pass the image details from shallow layers to deep layers. Experimental results in several datasets indicate that the proposed method outperforms the state-of-the-arts both quantitatively and qualitatively.
Similar content being viewed by others
References
McCartney, E. J., & Hall, F. (1976). Optics of the atmosphere: Scattering by molecules and particles. Physics Today, 30, 76–77.
Narasimhan, S., & Nayar, S. (2000). Chromatic framework for vision in bad weather. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 598–605). IEEE Press
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.
Ren, W., Pan, J., Zhang, H., & Yang, M. H. (2020). Single image dehazing via multiscale convolutional neural networks with holistic edges. International Journal of Computer Vision, 128(1), 240–259.
Wang, H., Xie, Q., Wu, Y., Zhao, Q., et al. (2020). Single image rain streaks removal: A review and an exploration. International Journal of Machine Learning and Cybernetics, 11, 853–872.
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.
Kim, G., Ha, S., & Kwon, J. (2018). Adaptive patch based convolutional neural network for robust dehazing. In IEEE International Conference on Image Processing (ICIP) (pp. 2845–2849). IEEE Press.
Zhang, X. (2021). Research on remote sensing image de-haze based on GAN. Journal of Signal Processing Systems, 94, 305–313.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). IEEE Press.
Cao, X., Zhou, F., Xu, L., Meng, D., Xu, Z., & Paisley, J. (2018). Hyperspectral image classification with Markov random fields and a convolutional neural network. IEEE Transactions on Image Processing, 27(5), 2354–2367.
Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In ICLR.
Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In ICLR.
Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non- local neural networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7794–7803). IEEE Press.
Zha, Z. J., Liu, J., Chen, D., & Wu, F. (2020). Adversarial attribute-text embedding for person search with natural language query. IEEE Transactions on Multimedia, 22(7), 1836–1846.
Zhu, Y., Zha, Z. J., Zhang, T., Liu, J., & Luo, J. (2020). A structured graph attention network for vehicle reidentification. In ACM MM.
Treibitz, T., & Schechner, Y. (2009). Polarization: Beneficial for visibility enhancement?. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 525–532). IEEE Press.
Fattal, R. (2008). Single image dehazing. ACM Transactions on Graphics, 27(3), 72.
Gibson, K. B., Vo, D., & Nguyen, T. (2012). An investigation of dehazing effects on image and video coding. IEEE Transactions on Image Processing, 21(2), 662–673.
Pleschberger, M., & Schrunner, S. (2020). An explicit solution for image restoration using Markov Random Fields. Journal of Signal Processing Systems, 92(2), 257–267.
Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2016). Aod-net: All-in-one dehazing network, in Proceedings of the IEEE International Conference on Computer Vision (CVPR) (pp. 4770–4778). IEEE Press.
Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., & Yang, M. H. (2018). Gated fusion network for single image dehazing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3253– 3261.
Liu, X., Ma, Y., Shi, Z., & Chen, J. (x2019). GridDehazeNet: Attention-based multi-scale network for image dehazing. IEEE International Conference on Computer Vision (ICCV) (pp. 7313–7322). IEEE Press.
Dong, H. (2020). Multi-scale boosted dehazing network with dense feature fusion. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2157–2167). IEEE Press.
Liu, X., Suganuma, M., Sun, Z., & Okatani, T. (2019). Dual residual networks leveraging the potential of paired operations for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7007–7016).
Chen, D., He, M., Fan, Q. (2019). Gated context aggregation network for image dehazing and deraining. 2019 IEEE winter conference on applications of computer vision (WACV) (1375–1383). IEEE.
Ally, N., Nombo, J., Ibwe, K., et al. (2021). Diffusion-driven image denoising model with texture preservation capabilities. Journal of Signal Processing Systems, 93, 937–949.
Yu, W., Huang, Z., Zhang, W., Feng, L., & Xiao, N. (2019). Gradual network for single image de-raining. In ACMMM.
Qin, X., Wang, Z., Bai, Y., Xie, X., & Jia, H. (2020). FFA-Net: Feature fusion attention network for single image dehazing. AAAI.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: convolutional networks for biomedical image segmentation. In MICCAI.
Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7132–7141). IEEE Press.
Fu, X., Qi, Q., Zhu, Y., Ding, X., & Zha, Z. J. (2021). Rain streak removal via dual graph convolutional network. AAAI.
Chen, Y., Kalantidis, Y., Li, J., Yan, S., & Feng, J. (2018). Aˆ 2-nets: Double attention networks. In NeurIPS.
Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Feng, J., & Kalantidis, Y. (2019). Graph-based global reasoning networks. In CVPR.
Lim, B., Son, S., Kim, H., Nah, S., & Lee, K. M. (2017). Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Rork- shops (CVPRW) (pp. 136–144). IEEE Press.
Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., & Wang, Zh. (2019). Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1), 492–505.
Codruta, O., Ancuti, C., & Ancuti (2019). Mateu Sbert, and Radu Timofte. Dense haze: A benchmark for image dehazing with dense-haze and haze-free images. In ICIP.
Ancuti, C. O., Ancuti, C., & Timofte, R. (2020). NH-HAZE: An image dehazing benchmark with nonhomogeneous hazy and haze-free images. CVPRW.
Fattal, R. (2014). Dehazing using color-lines. ACM Transactions on Graphics, 34(1), 1–14.
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In European Conference on Computer Vision (ECCV) (pp. 746–760). Springer-Verlag.
Scharstein, D., & Szeliski, R. (2017). High-accuracy stereo depth maps using structured light. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (pp. I-I). IEEE Press.
He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (2019). Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 558–567). IEEE Press.
Acknowledgements
This work is supported by Jiangsu industry research project BY2020552.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hu, B., Yue, Z., Gu, M. et al. Hazy Removal via Graph Convolutional with Attention Network. J Sign Process Syst 95, 517–527 (2023). https://doi.org/10.1007/s11265-023-01863-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-023-01863-x