Abstract
A semi-supervised image dehazing network was proposed which consists of the supervised branch and the unsupervised branch. In the supervision branch, the encoding–decoding neural network is used as the network structure, and the network is constrained by the supervision loss. In the unsupervised branch, two similar sub-networks are used to estimate the transmission map and atmospheric light, and the unsupervised loss is constructed through prior knowledge to constrain the unsupervised branch. In the semi-supervised image dehazing network, the supervised branch and the unsupervised branch will output dehazing result, respectively. Then by minimizing the reconstruction loss between the two images, the supervised and unsupervised branches are constrained to make the network more generalizable. The entire semi-supervised image dehazing network is trained in an end-to-end manner, and the supervised and unsupervised branch shares weights in the encoding part. Extensive experimental results show that the proposed method has good performance in image dehazing compared with six advanced dehazing methods.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig5_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig6_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig7_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-021-02265-5/MediaObjects/371_2021_2265_Fig8_HTML.jpg)
Similar content being viewed by others
References
McCartney, Earl J.: Optics of the atmosphere: scattering by molecules and particles. New York (1976)
Nayar, S.K., Narasimhan, S.G.: Vision in bad weather. Proc. Seventh IEEE Int. Conf. Comput. Vision (1999). https://doi.org/10.1109/ICCV.1999.790306
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)
Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522–3533 (2015)
Berman, D., Treibitz, T., Avidan, S.: Air-light estimation using haze-lines. 2017 IEEE International Conference on Computational Photography (ICCP) (2017). https://doi.org/10.1109/ICCPHOT.2017.7951489
Berman, D., Avidan, S.: Non-local image dehazing. Proceedings of the IEEE conference on computer vision and pattern recognition. 1674–1682 (2016)
IUBC PRIOR: Single image de-haze under non-uniform illumination using bright channel prior. J. Theor. Appl. Inform. Technol. 48(3), 1–6 (2013)
Liu, X., Zhang, H., Cheung, Y.M., You, X., Tang, Y.Y.: Efficient single image dehazing and denoising: an efficient multi-scale correlated wavelet approach. Comput. Vis. Image Underst. 162, 23–33 (2017)
Liu, X., Zhang, H., Tang, Y.Y., Du, J.X.: Scene-adaptive single image dehazing via opening dark channel model. IET Image Process. 10(11), 877–884 (2016)
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.H.: Single image dehazing via multi-scale convolutional neural networks. Comput. Vis. ECCV. 9906, 154–169 (2016)
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)
Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: Aod-net: All-in-one dehazing network. Proc. IEEE Int. Conf. Comput. Vis. 4770–4778 (2017)
Zhang, H., Patel, V. M.: Densely connected pyramid dehazing network. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 3194–3203 (2018)
Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., Yang, M. H.: Gated fusion network for single image dehazing. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 3253–3261 (2018)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 9446–9454 (2018)
Gandelsman, Y., Shocher, A., Irani, M.: "Double-DIP": Unsupervised image decomposition via coupled deep-image-priors. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 11026–11035 (2019)
An, S., Huang, X., Zheng, Z., Wang, L.: An end-to-end sea fog removal network using multiple scattering model. Plos one. 16(5), e0251337 (2021
Qin, X., Wang, Z., Bai, Y., **e, X., Jia, H.: Ffa-net: feature fusion attention network for single image dehazing. Proc. AAAI Conf. Artif. Intell. 34(7), 11908–11915 (2020)
Wang, Y., Zhuo, S., Tao, D., Bu, J., Li, N.: Automatic local exposure correction using bright channel prior for under-exposed images. Signal Process. 93(11), 3227–3238 (2013)
Wang, Z., Li, Q.: Information content weighting for perceptual image quality assessment. IEEE Trans. Image Process. 20(5), 1185–1198 (2010)
Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image/video quality assessment. Electron. Lett. 44(13), 800–801 (2008)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Zhai, G., Min, X.: Perceptual image quality assessment: a survey. Sci. China Inf. Sci. 63, 1–52 (2020)
Choi, L.K., You, J., Bovik, A.C.: Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans. Image Process. 24(11), 3888–3901 (2015)
Zhang, J., Min, X., Zhu, Y., Zhai, G., Zhou, J., Yang, X., Zhang, W.: HazDesNet: an end-to-end network for haze density prediction. IEEE Trans. Intell. Transp. Syst. (2020). https://doi.org/10.1109/TITS.2020.3030673
Min, X., Zhai, G., Gu, K., Zhu, Y., Zhou, J., Guo, G., Zhang, W.: Quality evaluation of image dehazing methods using synthetic hazy images. IEEE Trans. Multimedia. 21(9), 2319–2333 (2019)
Min, X., Zhai, G., Gu, K., Yang, X., Guan, X.: Objective quality evaluation of dehazed images. IEEE Trans. Intell. Transp. Syst. 20(8), 2879–2892 (2018)
Li, B., Gou, Y., Gu, S., Liu, J.Z., Zhou, J.T., Peng, X.: You only look yourself: unsupervised and untrained single image dehazing neural network. Int. J. Comput. Vis. 129(5), 1754–1767 (2021)
Chen, D., He, M., Fan, Q., Liao, J., Zhang, L., Hou, D., Hua, G.: Gated context aggregation network for image dehazing and deraining. IEEE Winter Conf Appl Comput Vis (2019). https://doi.org/10.1109/WACV.2019.00151
Engin, D., Genç, A., Kemal Ekenel, H.: Cycle-dehaze: Enhanced cyclegan for single image dehazing. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops. 825–833 (2018)
Sidorov, O., Yngve Hardeberg, J.: Deep hyperspectral prior: Single-image denoising, inpainting, super-resolution. Proc. IEEE/CVF Int. Conf. Comput. Vis. Workshops. 0–0 (2019)
Gou, Y., Li, B., Liu, Z., Yang, S., Peng, X.: CLEARER: Multi-Scale Neural Architecture Search for Image Restoration. Adv. Neural Inform. Proc. Syst. 33 (2020)
Wu, H., Prasad, S.: Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Trans. Image Process. 27(3), 1259–1270 (2017)
Wei, Y., Zhang, Z., Wang, Y., Zhang, H., Zhao, M., Xu, M., Wang, M.: Semi-Deraingan: a new semi-supervised single image deraining. Proc. (IEEE Int. Conf. Multimed. Expo.) (2021). https://doi.org/10.1109/ICME51207.2021.9428285
Li, L., Dong, Y., Ren, W., Pan, J., Gao, C., Sang, N., Yang, M.H.: Semi-supervised image dehazing. IEEE Trans. Image Process. 29, 2766–2779 (2019)
Xu, Z., Yang, X., Li, X., Sun, X.: The effectiveness of instance normalization: a strong baseline for single image dehazing. ar**v preprint ar**v:1805.03305 (2018)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. ar**v preprint ar**v:1505.00853 (2015)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. Comput Vis ECCV. 694–711 (2016)
Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., Wang, Z.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492–505 (2018)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Author Shunmin An declares that he has no conflict of interest. Author **xia Huang declares that she has no conflict of interest. Author Le Wang declares that he has no conflict of interest. Author Linling Wang declares that she has no conflict of interest. Author Zhang**g Zheng declares that she has no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
An, S., Huang, X., Wang, L. et al. Semi-Supervised image dehazing network. Vis Comput 38, 2041–2055 (2022). https://doi.org/10.1007/s00371-021-02265-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02265-5