Skip to main content

Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13677))

Included in the following conference series:

Abstract

We offer a practical unpaired learning based image dehazing network from an unpaired set of clear and hazy images. This paper provides a new perspective to treat image dehazing as a two-class separated factor disentanglement task, i.e., the task-relevant factor of clear image reconstruction and the task-irrelevant factor of haze-relevant distribution. To achieve the disentanglement of these two-class factors in deep feature space, contrastive learning is introduced into a CycleGAN framework to learn disentangled representations by guiding the generated images to be associated with latent factors. With such formulation, the proposed contrastive disentangled dehazing method (CDD-GAN) employs negative generators to cooperate with the encoder network to update alternately, so as to produce a queue of challenging negative adversaries. Then these negative adversaries are trained end-to-end together with the backbone representation network to enhance the discriminative information and promote factor disentanglement performance by maximizing the adversarial contrastive loss. During the training, we further show that hard negative examples can suppress the task-irrelevant factors and unpaired clear exemples can enhance the task-relevant factors, in order to better facilitate haze removal and help image restoration. Extensive experiments on both synthetic and real-world datasets demonstrate that our method performs favorably against existing unpaired dehazing baselines.

X. Chen and Z. Fan—Contributed equally to this work.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Anvari, Z., Athitsos, V.: Dehaze-GLCGAN: unpaired single image de-hazing via adversarial training. arXiv preprint arXiv:2008.06632 (2020)

  2. Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: DehazeNet: an end-to-end system for single image haze removal. IEEE TIP 25(11), 5187–5198 (2016)

    MathSciNet  MATH  Google Scholar 

  3. Chang, C.M., Sung, C.S., Lin, T.N.: DAMix: density-aware data augmentation for unsupervised domain adaptation on single image dehazing. arXiv preprint arXiv:2109.12544 (2021)

  4. Chen, D., et al.: Gated context aggregation network for image dehazing and deraining. In: WACV, pp. 1375–1383. IEEE (2019)

    Google Scholar 

  5. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607. PMLR (2020)

    Google Scholar 

  6. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: NIPS, pp. 2180–2188 (2016)

    Google Scholar 

  7. Chen, X., et al.: Unpaired deep image deraining using dual contrastive learning. In: CVPR, pp. 2017–2026 (2022)

    Google Scholar 

  8. Chen, Z., Wang, Y., Yang, Y., Liu, D.: PSD: principled synthetic-to-real dehazing guided by physical priors. In: CVPR, pp. 7180–7189 (2021)

    Google Scholar 

  9. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)

    Google Scholar 

  10. Dong, H., et al.: Multi-scale boosted dehazing network with dense feature fusion. In: CVPR, pp. 2157–2167 (2020)

    Google Scholar 

  11. Dudhane, A., Murala, S.: CDNet: single image de-hazing using unpaired adversarial training. In: WACV, pp. 1147–1155. IEEE (2019)

    Google Scholar 

  12. Engin, D., Genç, A., Kemal Ekenel, H.: Cycle-dehaze: enhanced CycleGAN for single image dehazing. In: CVPRW, pp. 825–833 (2018)

    Google Scholar 

  13. Esser, P., Rombach, R., Ommer, B.: A disentangling invertible interpretation network for explaining latent representations. In: CVPR, pp. 9223–9232 (2020)

    Google Scholar 

  14. Han, J., Shoeiby, M., Petersson, L., Armin, M.A.: Dual contrastive learning for unsupervised image-to-image translation. In: CVPR, pp. 746–755 (2021)

    Google Scholar 

  15. He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE TPAMI 33(12), 2341–2353 (2010)

    Google Scholar 

  16. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)

    Google Scholar 

  17. Jin, Y., Gao, G., Liu, Q., Wang, Y.: Unsupervised conditional disentangle network for image dehazing. In: ICIP, pp. 963–967. IEEE (2020)

    Google Scholar 

  18. Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: AOD-Net: all-in-one dehazing network. In: ICCV, pp. 4770–4778 (2017)

    Google Scholar 

  19. Li, B., et al.: Benchmarking single-image dehazing and beyond. IEEE TIP 28(1), 492–505 (2018)

    MathSciNet  MATH  Google Scholar 

  20. 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. IJCV 129(5), 1754–1767 (2021)

    Article  Google Scholar 

  21. Li, B., Gou, Y., Liu, J.Z., Zhu, H., Zhou, J.T., Peng, X.: Zero-shot image dehazing. IEEE TIP 29, 8457–8466 (2020)

    MATH  Google Scholar 

  22. Li, B., Lin, Y., Liu, X., Hu, P., Lv, J., Peng, X.: Unsupervised neural rendering for image hazing. arXiv preprint arXiv:2107.06681 (2021)

  23. Li, L., et al.: Semi-supervised image dehazing. IEEE TIP 29, 2766–2779 (2019)

    MATH  Google Scholar 

  24. Li, R., Pan, J., Li, Z., Tang, J.: Single image dehazing via conditional generative adversarial network. In: CVPR, pp. 8202–8211 (2018)

    Google Scholar 

  25. Liu, C., Fan, J., Yin, G.: Efficient unpaired image dehazing with cyclic perceptual-depth supervision. arXiv preprint arXiv:2007.05220 (2020)

  26. Liu, R., Ge, Y., Choi, C.L., Wang, X., Li, H.: DivCo: diverse conditional image synthesis via contrastive generative adversarial network. In: CVPR, pp. 16377–16386 (2021)

    Google Scholar 

  27. Liu, X., Ma, Y., Shi, Z., Chen, J.: GridDehazeNet: attention-based multi-scale network for image dehazing. In: ICCV, pp. 7314–7323 (2019)

    Google Scholar 

  28. Liu, Y., Anwar, S., Qin, Z., Ji, P., Caldwell, S., Gedeon, T.: Disentangling noise from images: a flow-based image denoising neural network. arXiv preprint arXiv:2105.04746 (2021)

  29. Liu, Y., Pan, J., Ren, J., Su, Z.: Learning deep priors for image dehazing. In: ICCV, pp. 2492–2500 (2019)

    Google Scholar 

  30. Liu, Y., et al.: From synthetic to real: image dehazing collaborating with unlabeled real data. arXiv preprint arXiv:2108.02934 (2021)

  31. Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9(11), 2579–2605 (2008)

    MATH  Google Scholar 

  32. Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE TIP 21(12), 4695–4708 (2012)

    MathSciNet  MATH  Google Scholar 

  33. Pan, L., Tang, P., Chen, Z., Xu, Z.: Contrastive disentanglement in generative adversarial networks. arXiv preprint arXiv:2103.03636 (2021)

  34. Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319–345. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_19

    Chapter  Google Scholar 

  35. Qin, X., Wang, Z., Bai, Y., Xie, X., Jia, H.: FFA-Net: feature fusion attention network for single image dehazing. In: AAAI, vol. 34, pp. 11908–11915 (2020)

    Google Scholar 

  36. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  37. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.-H.: Single image dehazing via multi-scale convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 154–169. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_10

    Chapter  Google Scholar 

  38. Ren, W., et al.: Gated fusion network for single image dehazing. In: CVPR, pp. 3253–3261 (2018)

    Google Scholar 

  39. Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. IJCV 126(9), 973–992 (2018). Sep

    Article  Google Scholar 

  40. Shao, Y., Li, L., Ren, W., Gao, C., Sang, N.: Domain adaptation for image dehazing. In: CVPR, pp. 2808–2817 (2020)

    Google Scholar 

  41. VidalMata, R.G., Banerjee, S., RichardWebster, B., Albright, M., Davalos, P., McCloskey, S., Miller, B., Tambo, A., Ghosh, S., Nagesh, S., et al.: Bridging the gap between computational photography and visual recognition. IEEE TPAMI 43(12), 4272–4290 (2020)

    Article  Google Scholar 

  42. Wang, G., Sun, C., Xu, X., Li, J., Wang, Z., Ma, Z.: Disentangled representation learning and enhancement network for single image de-raining. In: ACM MM, pp. 3015–3023 (2021)

    Google Scholar 

  43. Wang, L., Wang, Y., Dong, X., Xu, Q., Yang, J., An, W., Guo, Y.: Unsupervised degradation representation learning for blind super-resolution. In: CVPR, pp. 10581–10590 (2021)

    Google Scholar 

  44. Wang, W., Zhou, W., Bao, J., Chen, D., Li, H.: Instance-wise hard negative example generation for contrastive learning in unpaired image-to-image translation. In: ICCV, pp. 14020–14029 (2021)

    Google Scholar 

  45. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600–612 (2004)

    Google Scholar 

  46. Wei, Y., et al.: DerainCycleGAN: rain attentive CycleGAN for single image deraining and rainmaking. IEEE TIP 30, 4788–4801 (2021)

    Google Scholar 

  47. Wu, H., et al.: Contrastive learning for compact single image dehazing. In: CVPR, pp. 10551–10560 (2021)

    Google Scholar 

  48. Yang, W., et al.: Advancing image understanding in poor visibility environments: a collective benchmark study. IEEE TIP 29, 5737–5752 (2020)

    MATH  Google Scholar 

  49. Yang, X., Xu, Z., Luo, J.: Towards perceptual image dehazing by physics-based disentanglement and adversarial training. In: AAAI, vol. 32 (2018)

    Google Scholar 

  50. Ye, Y., Chang, Y., Zhou, H., Yan, L.: Closing the loop: joint rain generation and removal via disentangled image translation. In: CVPR, pp. 2053–2062 (2021)

    Google Scholar 

  51. Yi, X., Ma, B., Zhang, Y., Liu, L., Wu, J.: Two-step image dehazing with intra-domain and inter-domain adaptation. arXiv preprint arXiv:2102.03501 (2021)

  52. Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: CVPR, pp. 3194–3203 (2018)

    Google Scholar 

  53. Zhang, H., Sindagi, V., Patel, V.M.: Image de-raining using a conditional generative adversarial network. IEEE TCSVT 30(11), 3943–3956 (2019)

    Google Scholar 

  54. Zhao, S., Zhang, L., Shen, Y., Zhou, Y.: RefinedNet: a weakly supervised refinement framework for single image dehazing. IEEE TIP 30, 3391–3404 (2021)

    Google Scholar 

  55. Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2223–2232 (2017)

    Google Scholar 

  56. Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE TIP 24(11), 3522–3533 (2015)

    MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yufeng Li .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, X. et al. (2022). Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13677. Springer, Cham. https://doi.org/10.1007/978-3-031-19790-1_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19790-1_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19789-5

  • Online ISBN: 978-3-031-19790-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics