Abstract
Haze-free images are the prerequisites for many high-level visual tasks, and thus image dehazing has become an active topic in computer vision. However, the existing image dehazing algorithms are limited in face of unevenly distributed haze and dense haze in some scenes. In this paper, we propose a Pyramid Spatially Weighted Pixel Attention Network (PSPAN) for single image dehazing by leveraging complementarity among different levels of features in a pyramid manner with unique attention methods. The proposed PSPAN utilizes the feature pyramid as the core network and consists of three modules: an efficient Multi-scale Feature Extraction Attention module, a pyramid Spatially Weighted Pixel Attention module, and an image reconstruction module. Specifically, PSPAN preprocesses hazy images first before acquiring abundant shared features. After that, these features are sent to different branches. To effectively fuse useful information from these different branches and obtain better-dehazed results, we propose an efficient feature aggregation attention module. Finally, the image reconstruction module is used to restore clear images. Meanwhile, a loss function that combines a mean square error loss part, an edge loss part, and a perceptual loss part is employed in PSPAN which can better preserve image details. Experimental results demonstrate that the proposed PSPAN achieves superior performance to other existing state-of-the-art algorithms in terms of accuracy and visual effect.
Similar content being viewed by others
Data Availability Statements
The datasets analysed during the current study are available in the public RESIDE Dataset and public LIVE Image Defogging Database. And the different algorithms’ results which performed in datasets during the current study are available from the public paper or the corresponding author on reasonable request.
References
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. https://doi.org/10.1109/TIP.2016.2598681
Kansal, I, Kasana, SS (2018) Minimum preserving subsampling-based fast image de-fogging. Journal of Modern Optics, 65(18):2103–2123. https://doi.org/10.1080/09500340.2018.1499976
Fattal, R (2008) Single image dehazing. ACM transactions on graphics (TOG) 27(3):1–9. https://doi.org/10.1145/1360612.1360671
Tan, RT (2008) Visibility in bad weather from a single image. In: 2008 IEEE conference on computer vision and pattern recognition, pp 1–8. https://doi.org/10.1109/CVPR.2008.4587643. IEEE
Fattal, R (2014) Dehazing using color-lines. ACM transactions on graphics (TOG), 34(1):1–14. https://doi.org/10.1145/2651362
Zhu, Q, Mai, J, Shao, L (2015) A fast single image haze removal algorithm using color attenuation prior. IEEE transactions on image processing, 24(11):3522–3533 . https://doi.org/10.1109/TIP.2015.2446191
Dong Y, Liu Y, Zhang H, Chen S, Qiao Y (2020) Fd-gan: Generative adversarial networks with fusion-discriminator for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence 34:10729–10736. https://doi.org/10.1609/aaai.v34i07.6701
Fattal R (2008) Single image dehazing. ACM transactions on graphics (TOG) 27(3):1–9. https://doi.org/10.1145/1360612.1360671
Fattal R (2014) Dehazing using color-lines. ACM transactions on graphics (TOG) 34(1):1–14. https://doi.org/10.1145/2651362
Yang, H, Pan, J, Yan, Q, Sun, W, Ren, J, Tai, Y-W (2017) Image dehazing using bilinear composition loss function. https://doi.org/10.48550/arXiv.1710.00279
Li, C, Guo, J, Porikli, F, Fu, H, Pang, Y (2018) A cascaded convolutional neural network for single image dehazing. IEEE Access, 6:24877–24887. https://doi.org/10.1109/ACCESS.2018.2818882
Li, B, Peng, X, Wang, Z, Xu, J, Feng, D (2017) Aod-net: All-in-one dehazing network. In: Proceedings of the IEEE international conference on computer vision, pp 4770–4778
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. https://doi.org/10.1109/TPAMI.2010.168
Mei, K, Jiang, A, Li, J, Wang, M (2018) Progressive feature fusion network for realistic image dehazing. In: Asian Conference on Computer Vision, pp 203–215. https://doi.org/10.1007/978-3-030-20887-5_13. Springer
Qu, Y, Chen, Y, Huang, J, Xie, Y (2019) Enhanced pix2pix dehazing network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 8160–8168
Dong, H, Pan, J, Xiang, L, Hu, Z, Zhang, X, Wang, F, Yang, M-H (2020) Multi-scale boosted dehazing network with dense feature fusion. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2157–2167. https://doi.org/10.48550/arXiv.2004.1338
Kansal I, Kasana SS (2018) Minimum preserving subsampling-based fast image de-fogging. J Modern Optics 65(18):2103–2123. https://doi.org/10.1080/09500340.2018.1499976
Kansal I, Kasana SS (2018) Fusion-based image de-fogging using dual tree complex wavelet transform. Int J Wavelets Multiresolution Inf Process 16(06):1850054. https://doi.org/10.1142/S0219691318500546
Kansal I, Kasana SS (2020) Improved color attenuation prior based image de-fogging technique. Multimed Tools Appl 79(17–18):12069–12091. https://doi.org/10.1007/s11042-019-08240-6
Lan Y, Cui Z, Su Y, Wang N, Li A, Zhang W, Li Q, Zhong X (2022) Online knowledge distillation network for single image dehazing. Scientific Reports 12(1):1–13. https://doi.org/10.1038/s41598-022-19132-5
Hu, J, Shen, L, Sun, G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.48550/arXiv.1709.01507
Li C, Guo J, Porikli F, Fu H, Pang Y (2018) A cascaded convolutional neural network for single image dehazing. IEEE Access 6:24877–24887. https://doi.org/10.1109/ACCESS.2018.2818882
Li B, Ren W, Fu D, Tao D, Feng D, Zeng W, Wang Z (2018) Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing 28(1):492–505. https://doi.org/10.1109/TIP.2018.2867951
Mnih, V, Heess, N, Graves, A, et al (2014) Recurrent models of visual attention. Advances in neural information processing systems, vol 27
Lu H, Li Y, Nakashima S, Serikawa S (2016) Single image dehazing through improved atmospheric light estimation. Multimed Tools Appl 75(24):17081–17096. https://doi.org/10.1007/s11042-015-2977-7
Qin, X, Wang, Z, Bai, Y, Xie, X, Jia, H (2020) Ffa-net: Feature fusion attention network for single image dehazing. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11908–11915. https://doi.org/10.1609/aaai.v34i07.6865
He, K, Zhang, X, Ren, S, Sun, J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770–778
Qin X, Wang Z, Bai Y, Xie X, Jia H (2020) Ffa-net: Feature fusion attention network for single image dehazing. Proceedings of the AAAI conference on artificial intelligence 34:11908–11915. https://doi.org/10.1609/aaai.v34i07.6865
Wang, Q, Wu, B, Zhu, P, Li, P, Zuo, W, Hu, Q (2020) Supplementary material for ’eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the 2020 IEEE/CVF conference on computer vision and pattern recognition, IEEE, Seattle, WA, USA, pp 13–19
Xu, K, Ba, J, Kiros, R, Cho, K, Courville, A, Salakhudinov, R, Zemel, R, Bengio, Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, pp 2048–2057. PMLR
Vaswani, A, Shazeer, N, Parmar, N, Uszkoreit, J, Jones, L, Gomez, A.N, Kaiser, Ł, Polosukhin, I (2017) Attention is all you need. Advances in neural information processing systems, 30
Wang, X, Girshick, R, Gupta, A, He, K (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7794–7803. https://doi.org/10.48550/arXiv.1711.07971
Hong, M, Xie, Y, Li, C, Qu, Y (2020) Distilling image dehazing with heterogeneous task imitation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3462–3471
Gilbarg, D, Trudinger, NS (1983) Elliptic partial differential equations of second order, grundlehren der mathematischen wissenschaften. Berlin Heidelberg New York ed
Simonyan, K, Zisserman, A (2014) Very deep convolutional networks for large-scale image recognition. https://doi.org/10.48550/arXiv:1409.1556
Johnson, J, Alahi, A, Fei-Fei, L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision, pp 694–711. https://doi.org/10.1007/978-3-319-46475-6_43. Springer
Zhang, H, Patel, VM (2018) Densely connected pyramid dehazing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3194–3203. https://doi.org/10.48550/arXiv.1803.08396
Ren, W, Liu, S, Zhang, H, Pan, J, Cao, X, Yang, M-H (2016) Single image dehazing via multi-scale convolutional neural networks. In: European conference on computer vision, pp 154–169. Springer
Chen, D, He, M, Fan, Q, Liao, J, Zhang, L, Hou, D, Yuan, L, Hua, G (2019) Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE winter conference on applications of computer vision (WACV):pp 1375–1383. https://doi.org/10.1109/WACV.2019.00151
Lan, Y, Cui, Z, Su, Y, Wang, N, Li, A, Zhang, W, Li, Q, Zhong, X (2022) Online knowledge distillation network for single image dehazing. Scientific Reports, 12(1):1–13. https://doi.org/10.1038/s41598-022-19132-5
Kansal, I, Kasana, SS (2018) Fusion-based image de-fogging using dual tree complex wavelet transform. International Journal of Wavelets, Multiresolution and Information Processing, 16(06):1850054. https://doi.org/10.1142/S0219691318500546
Choi, LK, A.C.B. You, J (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. Image Process, 24(11). https://doi.org/10.1109/TIP.2015.2456502
Li, B, Ren, W, Fu, D, Tao, D, Feng, D, Zeng, W, Wang, Z (2018) Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing 28(1):492–505. https://doi.org/10.1109/TIP.2018.2867951
Zhang X, Jiang R, Wang T, Huang P, Zhao L (2021) Attention-based interpolation network for video deblurring. Neurocomputing 453:865–875. https://doi.org/10.1016/j.neucom.2020.04.147
Zhu Q, Mai J, Shao L (2015) A fast single image haze removal algorithm using color attenuation prior. IEEE transactions on image processing 24(11):3522–3533. https://doi.org/10.1109/TIP.2015.2446191
Acknowledgements
This work is partially supported by Heilongjiang Province Natural Science Foundation (LH2022F005) and Northeast Petroleum University Guiding Innovation Fund (No.15071202202).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interests.
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
Zhang, Y., Xu, T. & Tian, K. PSPAN:pyramid spatially weighted pixel attention network for image dehazing. Multimed Tools Appl 83, 11367–11385 (2024). https://doi.org/10.1007/s11042-023-15844-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15844-6