这是indexloc提供的服务，不要输入任何密码
Skip to main content
Springer Nature Link
Log in

DehazeDNet: image dehazing via depth evaluation

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Haze is a natural phenomenon that negatively affects image clarity and quality, posing challenges across various image-related applications. Traditional dehazing models often suffer from overfitting when trained on synthetic hazy-clean image pairs, which do not generalize well to real-world hazy conditions. To tackle this, recent methodologies have explored training models on unpaired data, better reflecting the variability encountered in natural scenes. This dual capability of CycleGAN is particularly beneficial for overcoming the overfitting issues associated with synthetic datasets. By incorporating CycleGAN into our DehazeDNet framework, we ensure that our dehazing model not only translates images effectively but also respects the physical characteristics of haze. Inspired by the D4 model, our approach includes a Depth Evaluation Block to estimate scene depth from images. Since haze density often correlates with scene depth, this depth information is crucial for accurate haze modeling. We utilize the U-Net architecture for the Depth Evaluation Block due to its proven efficiency in image-to-image translation tasks. To preserve the accuracy of the dehazed images, we incorporate an identity loss function into our model. Identity loss ensures that the dehazed output retains the essential characteristics of the input image. Our results demonstrate an increase in SSIM and PSNR compared to other unsupervised dehazing models, highlighting the efficiency of our method in maintaining image quality and details while removing haze.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+
from $39.99 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

Data availability

The manuscript has no associated data.

References

  1. Dong, W., Zhang, L., Shi, G., Wu, X.: Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans. Image Process. 20(7), 1838–1857 (2011). https://doi.org/10.1109/TIP.2011.2108306

    Article  MathSciNet  Google Scholar 

  2. He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2011). https://doi.org/10.1109/TPAMI.2010.168

    Article  Google Scholar 

  3. Kim, K.I., Kwon, Y.: Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1127–1133 (2010). https://doi.org/10.1109/TPAMI.2010.25

    Article  Google Scholar 

  4. Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990). https://doi.org/10.1109/34.56205

    Article  Google Scholar 

  5. Roth, S., Black, M.J.: Fields of experts: a framework for learning image priors. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 2, pp. 860–8672 (2005). https://doi.org/10.1109/CVPR.2005.160

  6. Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60(1–4), 259–268 (1992). https://doi.org/10.1016/0167-2789(92)90242-F

    Article  MathSciNet  Google Scholar 

  7. Zhu, S.-C., Mumford, D.: Prior learning and gibbs reaction-diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 19, 1236–1250 (1997)

    Article  Google Scholar 

  8. Dai, T., Cai, J., Zhang, Y., Xia, S.-T., Zhang, L.: Second-order attention network for single image super-resolution. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11057–11066 (2019). https://doi.org/10.1109/CVPR.2019.01132

  9. Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., Shi, W.: Photo-realistic single image super-resolution using a generative adversarial network (2017)

  10. Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C.C., Luo, P.: Exploiting deep generative prior for versatile image restoration and manipulation (2020)

  11. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.-H., Shao, L.: CycleISP: real image restoration via improved data synthesis (2020)

  12. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.-H., Shao, L.: Learning Enriched features for real image restoration and enhancement (2020)

  13. Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep cnn for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017). https://doi.org/10.1109/TIP.2017.2662206

    Article  MathSciNet  Google Scholar 

  14. Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep CNN denoiser prior for image restoration (2017)

  15. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image restoration (2020)

  16. Yang, Y., Wang, C., Liu, R., Zhang, L., Guo, X., Tao, D.: Self-augmented unpaired image dehazing via density and depth decomposition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2037–2046 (2022)

  17. Shi, W., Liu, H., Liu, M.: Identity-sensitive loss guided and instance feature boosted deep embedding for person search. Neurocomputing 415, 1–14 (2020). https://doi.org/10.1016/j.neucom.2020.07.062

    Article  Google Scholar 

  18. Aharon, M., Elad, M., Bruckstein, A.: K-svd: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006). https://doi.org/10.1109/TSP.2006.881199

    Article  Google Scholar 

  19. Luo, Y., Xu, Y., Ji, H.: Removing rain from a single image via discriminative sparse coding. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 3397–3405 (2015). https://doi.org/10.1109/ICCV.2015.388

  20. Mairal, J., Elad, M., Sapiro, G.: Sparse representation for color image restoration. IEEE Trans. Image Process. 17(1), 53–69 (2008). https://doi.org/10.1109/TIP.2007.911828

    Article  MathSciNet  Google Scholar 

  21. Chan, T.F., Wong, C.: Total variation blind deconvolution. IEEE Trans. Image Process. 7(3), 370–375 (1998). https://doi.org/10.1109/83.661187

    Article  Google Scholar 

  22. Buades, A., Coll, B., Morel, J.-M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 2, pp. 60–652 (2005). https://doi.org/10.1109/CVPR.2005.38

  23. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007). https://doi.org/10.1109/TIP.2007.901238

    Article  MathSciNet  Google Scholar 

  24. Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27(3), 73 (2008). https://doi.org/10.1145/1360612.1360672

    Article  Google Scholar 

  25. Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1107–1114 (2013). https://doi.org/10.1109/CVPR.2013.147

  26. Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: Dehazenet: an end-to-end system for single image haze removal. CoRR arXiv:1601.07661v2 [cs.CV] (2016)

  27. Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: An all-in-one network for dehazing and beyond (2017)

  28. Li, H., Li, J., Zhao, D., Xu, L.: Dehazeflow: Multi-scale conditional flow network for single image dehazing. In: Proceedings of the 29th ACM International Conference on Multimedia. MM ’21, pp. 2577–2585. Association for Computing Machinery, New York, NY, USA (2021). https://doi.org/10.1145/3474085.3475432

  29. Su, Y.Z., He, C., Cui, Z.G., Li, A.H., Wang, N.: Physical model and image translation fused network for single-image dehazing. Pattern Recognit. 142, 109700 (2023). https://doi.org/10.1016/j.patcog.2023.109700

    Article  Google Scholar 

  30. Wang, N., Cui, Z., Su, Y., He, C., Li, A.: Multiscale supervision-guided context aggregation network for single image dehazing. IEEE Signal Process. Lett. 29, 70–74 (2022). https://doi.org/10.1109/LSP.2021.3125272

    Article  Google Scholar 

  31. Wang, N., Cui, Z., Su, Y., He, C., Lan, Y., Li, A.: Prior-guided multiscale network for single-image dehazing. IET Image Process. 15(13), 3368–3379 (2021). https://doi.org/10.1049/ipr2.12333

    Article  Google Scholar 

  32. Wang, N., Cui, Z., Su, Y., Li, A.: RGNAM: recurrent grid network with an attention mechanism for single-image dehazing. J. Electron. Imaging 30(3), 033026 (2021). https://doi.org/10.1117/1.JEI.30.3.033026

    Article  Google Scholar 

  33. Cui, Z., Wang, N., Su, Y., Zhang, W., Lan, Y., Li, A.: Ecanet: enhanced context aggregation network for single image dehazing. SIViP 17(2), 471–479 (2023). https://doi.org/10.1007/s11760-022-02252-w

    Article  Google Scholar 

  34. Lan, Y., Cui, Z., Su, Y., Wang, N., Li, A., Zhang, W., Li, Q., Zhong, X.: Online knowledge distillation network for single image dehazing. Sci. Rep. 12(1), 14927 (2022). https://doi.org/10.1007/s11760-022-02252-w

    Article  Google Scholar 

  35. Dudhane, A., Murala, S.: CDNet: single image de-hazing using unpaired adversarial training (2019). https://doi.org/10.1109/wacv.2019.00127

  36. 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. Vision 129(5), 1754–1767 (2021). https://doi.org/10.1007/s11263-021-01431-5

    Article  Google Scholar 

  37. Liu, W., Hou, X., Duan, J., Qiu, G.: End-to-end single image fog removal using enhanced cycle consistent adversarial networks. IEEE Trans. Image Process. 29, 7819–7833 (2020). https://doi.org/10.1109/tip.2020.3007844

    Article  Google Scholar 

  38. Atila, U., Ucar, M., Akyol, K., Ucar, E.: Plant leaf disease classification using EfficientNet deep learning model. Eco. Inform. 61, 101182 (2021). https://doi.org/10.1016/j.ecoinf.2020.101182

    Article  Google Scholar 

  39. Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation (2015)

  40. Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z.: Multi-class generative adversarial networks with the L2 loss function. CoRR arXiv:1611.04076v1 [cs.CV] (2016)

  41. 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 (2019)

    Article  MathSciNet  Google Scholar 

  42. Ancuti, C., Ancuti, C.O., Timofte, R., Vleeschouwer, C.D.: I-haze: a dehazing benchmark with real hazy and haze-free indoor images. In: International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS), pp. 620–631. Springer, Berlin (2018)

  43. Fattal, R.: Dehazing using color-lines. ACM Trans. Graphics 34(1), 1–14 (2014)

    Article  Google Scholar 

  44. He, N.K., Sun, N.J., Tang, N.X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2011). https://doi.org/10.1109/tpami.2010.168

    Article  Google Scholar 

  45. Chen, Z., Wang, Y., Yang, Y., Liu, D.: PSD: principled synthetic-to-real dehazing guided by physical priors (2021). https://doi.org/10.1109/cvpr46437.2021.00710

  46. Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks (2017). https://doi.org/10.1109/iccv.2017.244

  47. Engin, D., Genc, A., Ekenel, H.K.: Cycle-dehaze: enhanced cyclegan for single image dehazing (2018). https://doi.org/10.1109/cvprw.2018.00127

  48. Yang, X., Xu, Z., Luo, J.: Towards perceptual image dehazing by physics-based disentanglement and adversarial training. Proceedings of the ... AAAI Conference on Artificial Intelligence 32(1) (2018). https://doi.org/10.1609/aaai.v32i1.12317

  49. Zhao, S., Zhang, L., Shen, Y., Zhou, Y.: Refinednet: a weakly supervised refinement framework for single image dehazing. IEEE Trans. Image Process. 30, 3391–3404 (2021). https://doi.org/10.1109/tip.2021.3060873

    Article  Google Scholar 

  50. Yang, A., Liu, Y., Wang, J., Li, X., Cao, J., Ji, Z., Pang, Y.: Visual-quality-driven unsupervised image dehazing. Neural Netw. 167, 1–9 (2023). https://doi.org/10.1016/j.neunet.2023.08.010

    Article  Google Scholar 

  51. Wen, Y., Gao, T., Zhang, J., Li, Z., Chen, T.: Encoder-free multiaxis physics-aware fusion network for remote sensing image dehazing. IEEE Trans. Geosci. Remote Sens. 61, 1–15 (2023). https://doi.org/10.1109/TGRS.2023.3325927

    Article  Google Scholar 

  52. Li, J., Li, Y., Zhuo, L., Kuang, L., Yu, T.: USID-Net: unsupervised single image dehazing network via disentangled representations. IEEE Trans. Multimedia 25, 3587–3601 (2023). https://doi.org/10.1109/TMM.2022.3163554

    Article  Google Scholar 

  53. Wang, X., Chen, X., Ren, W., Han, Z., Fan, H., Tang, Y., Liu, L.: Compensation atmospheric scattering model and two-branch network for single image dehazing. IEEE Trans. Emerg. Top. Comput. Intell. 8(4), 2880–2896 (2024). https://doi.org/10.1109/TETCI.2024.3386838

    Article  Google Scholar 

Download references

Acknowledgements

The authors express their gratitude to the Indian Institute of Information Technology Allahabad (IIIT-A), India, for the obtained financial support in performing this research work. This work is one of the outcomes of the project entitled "Deep Learning based Solutions for Vehicle Detection in Rainy and Foggy Climates under Smart City Environment" with sanction no. IIITA/RO/2022/409 dated 01.12.2022, sponsored by IIIT-A, Ministry of Education, India.

Funding

The work is sponsored by IIIT-A, Ministry of Education, India, for the project entitled "Deep Learning based Solutions for Vehicle Detection in Rainy and Foggy Climates under Smart City Environment" with sanction no. IIITA/RO/2022/409 dated 01.12.2022.

Author information

Authors and Affiliations

  1. Computer Vision and Biometrics Lab, Department of Information Technology, Indian Institute of Information Technology Allahabad, Jhalwa, Prayagraj, Uttar Pradesh, 211015, India

    G. Rupesh, Navjot Singh & Tekumudi Divya

Authors
  1. G. Rupesh
    View author publications

    Search author on:PubMed Google Scholar

  2. Navjot Singh
    View author publications

    Search author on:PubMed Google Scholar

  3. Tekumudi Divya
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Navjot Singh.

Ethics declarations

Conflict of interest

There is 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

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rupesh, G., Singh, N. & Divya, T. DehazeDNet: image dehazing via depth evaluation. SIViP 18, 9387–9395 (2024). https://doi.org/10.1007/s11760-024-03553-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1007/s11760-024-03553-y

Keywords