Abstract
Single image dehazing algorithms aim to recover a clear image from a hazy one. Most learning-based single image dehazing algorithms are trained on synthetic datasets and have limited inference ability to real-world scenes. We propose a graph-disentangled representation based semi-supervised single image dehazing algorithm (GDSDN). Specifically, a graph-disentangled representation network is presented to decouple the content and mask features, and the decoupled content features are employed to reconstruct dehazed results. In addition, the interaction-reconstruction strategy and contrastive loss are designed to constrain the disentangled content and mask features. Extensive experimental results on synthetic and real-world images show that our model achieves competitive results.
This work in this paper is supported by the Beijing Natural Science Foundation (No. L211017), the General Program of Beijing Municipal Education Commission (No. KM202110005027), the National Natural Science Foundation of China (No. 61971016), and the R&D Program of Beijing Municipal Education Commission (No. KZ202210005007)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Narasimhan, S.G., Nayar, S.K.: Chromatic framework for vision in bad weather. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 598–605. IEEE, Hilton Head (2000)
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)
Ju, M., Ding, C., Guo, C., et al.: IDRLP: image dehazing using region line prior. IEEE Trans. Image Process. 30, 9043–9057 (2021)
Li, B., Peng, X., Wang, Z., et al.: AOD-Net: all-in-one dehazing network. In: Proceedings IEEE International Conference on Computer Vision, pp. 4780–4788. IEEE, Italy (2017)
Li, Y., Miao, Q., Ouyang, W., et al.: LAP-Net: level-aware progressive network for image dehazing. In: Proceedings IEEE International Conference on Computer Vision, pp. 3276–3285. IEEE, Seoul (2019)
Qu, Y., Chen, Y., Huang, J., Xie, Y.: Enhanced Pix2pix dehazing network. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 8160–8168. IEEE, Long Beach (2019)
Dong, H., Pan, J., Xiang, L., et al.: Multi-scale boosted dehazing network with dense feature fusion. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2157–2167. IEEE, Seattle (2020)
Wu, H., Qu, Y., Lin, S., et al.: Contrastive learning for compact single image dehazing. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 10551–10560. IEEE, New Orleans (2022)
Li, L., Dong, Y., Ren, W., et al.: Semi-Supervised image dehazing. IEEE Trans. Image Process. 29, 2766–2779 (2020)
Shao, Y., Li, L., Ren, W., Gao, C., Sang, N.: Domain adaptation for image dehazing. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2808–2817. IEEE, Seattle (2020)
Chen, Z., Wang, Y., Yang, Y., Liu, D.: PSD: principled synthetic-to-real dehazing guided by physical priors. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 7180–7189. IEEE, Nashville (2021)
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)
Li, B., Gou, Y., Liu, J., Zhu, H., Zhou, J., Peng, X.: Zero-shot image dehazing. IEEE Trans. Image Process. 29, 8457–8466 (2020)
Yang, Y., Wang, C., Liu, R., et al.: Self-augmented unpaired image dehazing via density and depth decomposition. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2037–2046. IEEE, New Orleans (2022)
Du, W., Chen, H., Yang, H.: Learning invariant representation for unsupervised image restoration. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 14483–14492. IEEE, Seattle (2020)
Lu, B., Chen, J.C., Chellappa, R.: Unsupervised domain-specific deblurring via disentangled representations. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 10225–10234. IEEE, Long Beach (2019)
Ye, Y., Chang, Y., Zhou, H., et al.: Closing the loop: joint rain generation and removal via disentangled image translation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2053–2062. IEEE, Nashville (2021)
Ye, Y., Yu, C., Chang, Y., et al.: Unsupervised deraining: where contrastive learning meets self-similarity. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 5821–5830. IEEE, New Orleans (2022)
Guo, D., Shao, Y., Cui, Y., et al.: Graph attention tracking. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 9543–9552. IEEE, Nashville (2021)
Li, W., Liu, X., Yuan, Y.: Sigma: semantic-complete graph matching for domain adaptive object detection. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 5291–5300. IEEE, New Orleans (2022)
De Lutio, R., Becker, A., D’Aronco, S., et al.: Learning graph regularisation for guided super-resolution. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 1979–1988. IEEE, New Orleans (2022)
Zhang, B., Feng, S., Li, X., et al.: SGMNet: scene graph matching network for few-shot remote sensing scene classification. IEEE Trans. Geosci. Remote Sens. 60, 1–15 (2022)
Wei, H., Wu, Q., Li, H., et al.: Non-homogeneous haze removal via artificial scene prior and bidimensional graph representation. IEEE Trans. Image Process. 30, 9136–9149 (2021)
Li, J., Li, Y., Zhuo, L., Kuang, L., Yu, T.: USID-Net: unsupervised single image dehazing network via disentangled representations. IEEE Trans. Multimed. (2022)
Wu, R.Q., Duan, Z.P., Guo, C.L.: RIDCP: revitalizing real image dehazing via high-quality codebook priors. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Vancouver (2023)
Li, B., Ren, W., Fu, D., et al.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492–505 (2018)
Zhang, Y., Ding, L., Sharma, G.: HazeRD: an outdoor scene dataset and benchmark for single image dehazing. In: IEEE International Conference on Image Processing, pp.3205–3209. IEEE, Beijing (2017)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jia, T., Li, J., Zhuo, L. (2023). Graph Disentangled Representation Based Semi-supervised Single Image Dehazing Network. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_54
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_54
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)