Semi-supervised single-image dehazing based on spatial-channel feature enhancement
Abstract
Visibility reduction in haze-laden environments significantly hinders object discernment, presenting a substantial challenge in image processing. Current supervised dehazing methods are heavily reliant on the quality and diversity of their training datasets, which limits their generalization capabilities and incurs high costs due to the need for accurately paired training images. To address these limitations, this paper introduces a semi-supervised single-image dehazing network that leverages both synthetic and real-world hazy images during training. This mixed training approach enhances the model’s applicability to diverse real-world conditions and improves its robustness against varying haze densities. Our methodology incorporates a novel spatial-channel feature enhancement module that optimally processes images with uneven feature distributions and significant interference, thus maintaining integrity in feature representation. We evaluate our approach on multiple public benchmark datasets, the proposed method achieved a PSNR score of 20.93, SSIM scores of 0.724 on the NH-HAZE dataset, where it outperforms existing supervised and unsupervised methods in terms of generalization to both synthetic and authentic hazy images.
References
[1]
Chen Y, Li W, Sakaridis C, Dai D, Van Gool L (2018) Domain adaptive faster r-cnn for object detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3339–3348
[2]
Li C, Zhou H, Liu Y, Yang C, Xie Y, Li Z, Zhu L (2023) Detection-friendly dehazing: Object detection in real-world hazy scenes. IEEE Trans Pattern Anal Mach Intell
[3]
Li, L, Zhang, X, Lian, J, Zhang, Y, Zhao, Y. Study on practical utility of image dehazing algorithms based on deep learning in computer vision scene understanding. In: Proceedings of the CAAI International Conference on Artificial Intelligence. Springer, 2022, pp. 601–612
[4]
Dai D, Sakaridis C, Hecker S, and Van Gool L Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding Int J Comput Vis 2020 128 1182-1204
[5]
Yang D, Sun J (2018) Proximal dehaze-net: A prior learning-based deep network for single image dehazing. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 702–717
[6]
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
[7]
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
[8]
Pan, J, Liu, S, Sun, D, Zhang, J, Liu, Y, Ren, J, Li, Z, Tang, J, Lu, H, Tai, Y.W, et al. Learning dual convolutional neural networks for low-level vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3070–3079
[9]
Kponou EA, Wang Zn, Wei P, Jiang Y, Ni Xl, Bah MH (2014) A faithful restoration of haze images using an optimized transmission map. In: Proceedings of the 2014 7th International Congress on Image and Signal Processing. IEEE, pp. 184–189
[10]
Li Z, Tan P, Tan RT, Zou D, Zhiying Zhou S, Cheong LF (2015) Simultaneous video defogging and stereo reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4988–4997
[11]
Liu X, Suganuma M, Sun Z, Okatani T (2019) Dual residual networks leveraging the potential of paired operations for image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7007–7016
[12]
Zhang H, Sindagi V, Patel VM (2018) Multi-scale single image dehazing using perceptual pyramid deep network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 902–911
[13]
Chen Z, Wang Y, Yang Y, Liu D (2021) PSD: Principled synthetic-to-real dehazing guided by physical priors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7180–7189
[14]
Chen Y, Li J, Xiao H, Jin X, Yan S, Feng J (2017) Dual path networks. Adv Neural Inf Process Syst 30
[15]
Sun Z, Zhang Y, Bao F, Shao K, Liu X, and Zhang C ICycleGAN: Single image dehazing based on iterative dehazing model and CycleGAN Comput Vis Image Understand 2021 203
[16]
Rupesh G, Singh N, Divya T (2024) DehazeDNet: image dehazing via depth evaluation. Signal, Image Video Process
[17]
Zhang X, Wang T, Luo W, and Huang P Multi-level fusion and attention-guided CNN for image dehazing IEEE Trans Circuits Syst Video Technol 2021 31 4162-4173
[18]
Wang T, Li Z, Huang P, Zhang X, and Xu J Haze concentration adaptive network for image dehazing Neurocomputing 2021 439 75-85
[19]
Wang T, Zhang K, Shao Z, Luo W, Stenger B, Lu T, Kim T, Liu W, Li H (2024) GridFormer: residual dense transformer with grid structure for image restoration in adverse weather conditions. Int J Comput Vis 1–23
[20]
Wang T, Tao G, Lu W, Zhang K, Luo W, Zhang X, and Lu T Restoring vision in hazy weather with hierarchical contrastive learning Pattern Recogn 2024 145
[21]
Raikwar SC and Tapaswi S Lower bound on transmission using non-linear bounding function in single image dehazing IEEE Trans Image Process 2020 29 4832-4847
[22]
Wang J, Xu Y, Chen W (2020) Multi-Patch and Feature Fusion Network for Single Image Dehazing. In: Proceedings of the 2020 International Conference on Intelligent Computing, Automation and Systems (ICICAS). IEEE, pp. 282–285
[23]
Jia T, Li J, Xiao H, Zhuo L, and Zhang J Self-guided disentangled representation learning for single image dehazing Neural Netw 2024 172
[24]
Wang X, Chen X, Ren W, Han Z, Fan H, Tang Y, and Liu L Compensation atmospheric scattering model and two-branch network for single image dehazing IEEE Trans Emerg Topics Comput Intell 2024 8 2880-2896
[25]
He K, Sun J, and Tang X Single image haze removal using dark channel prior IEEE Trans Pattern Anal Mach Intell 2010 33 2341-2353
[26]
Wang P, Fan Q, Zhang Y, Bao F, and Zhang C A novel dehazing method for color fidelity and contrast enhancement on mobile devices IEEE Trans Consum Electron 2018 65 47-56
[27]
Golts A, Freedman D, and Elad M Unsupervised single image dehazing using dark channel prior loss IEEE Trans Image Process 2019 29 2692-2701
[28]
Zhang S, Zhen A, Stevenson RL GAN based image deblurring using dark channel prior. arXiv preprint arXiv:1903.001072019
[29]
Tarel JP, Hautiere N (2009) Fast visibility restoration from a single color or gray level image. In: Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. IEEE, pp. 2201–2208
[30]
Fattal R Dehazing using color-lines ACM Trans Graph (TOG) 2014 34 1-14
[31]
Nishino K, Kratz L, and Lombardi S Bayesian defogging Int J Comput Vis 2012 98 263-278
[32]
Cai B, Xu X, Jia K, Qing C, and Tao D Dehazenet: an end-to-end system for single image haze removal IEEE Trans Image Process 2016 25 5187-5198
[33]
Wang P, Zhu H, Huang H, Zhang H, Wang N (2022) TMS-GAN: A twofold multi-scale generative adversarial network for single image Dehazing. IEEE Trans Circuits Syst Video Technol, p. 2760-2772.
[34]
Song Y, He Z, Qian H, and Du X Vision transformers for single image dehazing IEEE Trans Image Process 2023 32 1927-1941
[35]
Lai WS, Huang JB, Yang MH (2017) Semi-supervised learning for optical flow with generative adversarial networks. Adv Neural Inf Process Syst 30
[36]
Huang S, Wang K, Liu H, Chen J, Li Y (2023) Contrastive semi-supervised learning for underwater image restoration via reliable bank. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18145–18155
[37]
Cui X, Wang C, Ren D, Chen Y, and Zhu P Semi-supervised image deraining using knowledge distillation IEEE Trans Circuits Syst Video Technol 2022 32 8327-8341
[38]
Li L, Dong Y, Ren W, Pan J, Gao C, Sang N, and Yang MH Semi-supervised image dehazing IEEE Trans Image Process 2019 29 2766-2779
[39]
Xia B, Zhang Y, Wang S, Wang Y, Wu X, Tian Y, Yang W, Van Gool L (2023) Diffir: Efficient diffusion model for image restoration. In: Proceedings of the IEEE/CVF International Conference on Computer Vision
[40]
Wang Z, Cun X, Bao J, Zhou W, Liu J, Li H (2022) Uformer: A general u-shaped transformer for image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17683–17693
[41]
Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang MH (2022) Restormer: Efficient transformer for high-resolution image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728–5739
[42]
Li J, Wen Y, He L (2023) SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6153–6162
[43]
Wang C, Zheng Z, Quan R, Sun Y, Yang Y (2023) Context-lsition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18186–18195
[44]
Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang MH, and Shao L Learning enriched features for fast image restoration and enhancement IEEE Trans Pattern Anal Mach Intell 2022 45 1934-1948
[45]
Ba JL, Kiros JR, Hinton GE Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
[46]
Ledig C, Theis L, Huszár F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681–4690
[47]
Pan J, Sun D, Pfister H, Yang MH (2016) Blind image deblurring using dark channel prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1628–1636
[48]
Golts A, Freedman D, Elad M (2020) Unsupervised single image dehazing using dark channel prior loss. IEEE Trans Image Process.
[49]
Qin X, Wang Z, Bai Y, Xie X, and Jia H FFA-Net: feature fusion attention network for single image dehazing Proc AAAI Conf Artif Intell 2020
[50]
Ye T, Jiang M, Zhang Y, Chen L, Chen E, Chen P, Lu Z Perceiving and modeling density is all you need for image dehazing. arXiv preprint arXiv:2111.09733 (2021)
[51]
Guo CL, Yan Q, Anwar S, Cong R, Ren W, Li C (2022) Image dehazing transformer with transmission-aware 3d position embedding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5812–5820
[52]
Sun H, Luo Z, Ren D, Du D, Chang L, and Wan J Unsupervised multi-branch network with high-frequency enhancement for image dehazing Pattern Recogn 2024 156
[53]
Jia T, Li J, Zhuo L, and Yu T Semi-supervised single-image dehazing network via disentangled meta-knowledge IEEE Trans Multim 2024 26 2634-2647
[54]
Wu H, Qu Y, Lin S, Zhou J, Qiao R, Zhang Z, Xie Y, Ma L (2021) Contrastive learning for compact single image dehazing. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun
[55]
Li B, Ren W, Fu D, Tao D, Feng D, Zeng W, and Wang Z Benchmarking single-image dehazing and beyond IEEE Trans Image Process 2019
[56]
Ancuti C, Ancuti C, Sbert M, Timofte R Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images. arXiv Computer Vision and Pattern Recognition (2019)
[57]
Ancuti C, Ancuti C, Timofte R NH-HAZE: An image dehazing benchmark with non-homogeneous hazy and haze-free images. arXiv Computer Vision and Pattern Recognition (2020)
[58]
Ancuti C, Ancuti C, Timofte R, Vleeschouwer D (2018) I-haze: A dehazing benchmark with real hazy and haze-free outdoor images. In: Proceedings of International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 754–762
[59]
Ancuti C, Ancuti C, Timofte R, Vleeschouwer D (2018) I-haze: A dehazing benchmark with real hazy and haze-free indoor images. In: Proceedings of International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 620–631
[60]
Zhao S, Zhang L, Huang S, Shen Y, and Zhao S Dehazing evaluation: real-world benchmark datasets, criteria, and baselines IEEE Trans Image Process 2020
[61]
Wang Z, Bovik A, Sheikh H, and Simoncelli E Image quality assessment: from error visibility to structural similarity IEEE Trans Image Process 2004
[62]
Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in PyTorch
[63]
Kingma D, Ba J (2014) Adam: A method for stochastic optimization. arXiv Learning
[64]
Xiao X, Ren Y, Li Z (2024) Self-supervised zero-shot dehazing network based on dark channel prior. Front Optoelectron 16
Index Terms
- Semi-supervised single-image dehazing based on spatial-channel feature enhancement
Index terms have been assigned to the content through auto-classification.
Recommendations
SADnet: Semi-supervised Single Image Dehazing Method Based on an Attention Mechanism
Many real-life tasks such as military reconnaissance and traffic monitoring require high-quality images. However, images acquired in foggy or hazy weather pose obstacles to the implementation of these real-life tasks; consequently, image dehazing is an ...
Semi-Supervised image dehazing network
AbstractA 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 ...
Graph Disentangled Representation Based Semi-supervised Single Image Dehazing Network
Advanced Intelligent Computing Technology and ApplicationsAbstractSingle 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-...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. 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.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 13 November 2024
Accepted: 29 October 2024
Author Tags
Qualifiers
- Research-article
Funding Sources
- the Talent Project of Shandong Women’s University
- the Opening Fund of Shandong Provincial Key Laboratory of Network-based Intelligent Computing
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 23 Feb 2025