research-article

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention

Authors:

Zhe-Ming LuAuthors Info & Claims

IEEE Transactions on Image Processing, Volume 33

Pages 1002 - 1015

https://doi.org/10.1109/TIP.2024.3354108

Published: 01 January 2024 Publication History

Abstract

Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based methods are devoted to improving the model performance via increasing the depth or width of convolution. The learning ability of Convolutional Neural Network (CNN) structure is still under-explored. In this paper, a Detail-Enhanced Attention Block (DEAB) consisting of Detail-Enhanced Convolution (DEConv) and Content-Guided Attention (CGA) is proposed to boost the feature learning for improving the dehazing performance. Specifically, the DEConv contains difference convolutions which can integrate prior information to complement the vanilla one and enhance the representation capacity. Then by using the re-parameterization technique, DEConv is equivalently converted into a vanilla convolution to reduce parameters and computational cost. By assigning the unique Spatial Importance Map (SIM) to every channel, CGA can attend more useful information encoded in features. In addition, a CGA-based mixup fusion scheme is presented to effectively fuse the features and aid the gradient flow. By combining above mentioned components, we propose our Detail-Enhanced Attention Network (DEA-Net) for recovering high-quality haze-free images. Extensive experimental results demonstrate the effectiveness of our DEA-Net, outperforming the state-of-the-art (SOTA) methods by boosting the PSNR index over 41 dB with only 3.653 M parameters. (The source code of our DEA-Net is available at <uri>https://github.com/cecret3350/DEA-Net</uri>.)

References

[1]

R. T. Tan, “Visibility in bad weather from a single image,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2008, pp. 1–8.

[2]

B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, “DehazeNet: An end-to-end system for single image haze removal,” IEEE Trans. Image Process., vol. 25, no. 11, pp. 5187–5198, Nov. 2016.

Digital Library

[3]

B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, “AOD-Net: All-in-one dehazing network,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 4780–4788.

[4]

P. Li, J. Tian, Y. Tang, G. Wang, and C. Wu, “Deep Retinex network for single image dehazing,” IEEE Trans. Image Process., vol. 30, pp. 1100–1115, 2021.

Digital Library

[5]

X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “FFA-Net: Feature fusion attention network for single image dehazing,” in Proc. AAAI Conf. Artif. Intell., 2020, vol. 34, no. 7, pp. 11908–11915.

[6]

H. Wuet al., “Contrastive learning for compact single image dehazing,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2021, pp. 10546–10555.

[7]

W. Renet al., “Single image dehazing via multi-scale convolutional neural networks,” in Proc. Eur. Conf. Comput. Vis. Cham, Switzerland: Springer, 2016, pp. 154–169.

[8]

H. Zhang and V. M. Patel, “Densely connected pyramid dehazing network,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 3194–3203.

[9]

S. G. Narasimhan and S. K. Nayar, “Contrast restoration of weather degraded images,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 6, pp. 713–724, Jun. 2003.

[10]

H. Donget al., “Multi-scale boosted dehazing network with dense feature fusion,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2020, pp. 2154–2164.

[11]

T. Yeet al., “Perceiving and modeling density is all you need for image dehazing,” 2021, arXiv:2111.09733.

[12]

H. Wu, J. Liu, Y. Xie, Y. Qu, and L. Ma, “Knowledge transfer dehazing network for NonHomogeneous dehazing,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jun. 2020, pp. 1975–1983.

[13]

C. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “Image dehazing transformer with transmission-aware 3D position embedding,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2022, pp. 5802–5810.

[14]

Z. Yuet al., “Searching central difference convolutional networks for face anti-spoofing,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2020, pp. 5294–5304.

[15]

S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional block attention module,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 3–19.

[16]

J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-excitation networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 8, pp. 2011–2023, Aug. 2020.

Digital Library

[17]

H. Bai, J. Pan, X. Xiang, and J. Tang, “Self-guided image dehazing using progressive feature fusion,” IEEE Trans. Image Process., vol. 31, pp. 1217–1229, 2022.

[18]

M. Hong, J. Liu, C. Li, and Y. Qu, “Uncertainty-driven dehazing network,” in Proc. AAAI Conf. Artif. Intell., Jun. 2022, vol. 36, no. 1, pp. 906–913. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/19973

[19]

K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” in Proc. CVPR, 2009, pp. 1956–1963.

[20]

K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 2341–2353, Dec. 2011.

Digital Library

[21]

D. Berman, T. Treibitz, and S. Avidan, “Non-local image dehazing,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1674–1682.

[22]

Q. Zhu, J. Mai, and L. Shao, “A fast single image haze removal algorithm using color attenuation prior,” IEEE Trans. Image Process., vol. 24, no. 11, pp. 3522–3533, Nov. 2015.

Digital Library

[23]

W. Ren, J. Pan, H. Zhang, X. Cao, and M.-H. Yang, “Single image dehazing via multi-scale convolutional neural networks with holistic edges,” Int. J. Comput. Vis., vol. 128, no. 1, pp. 240–259, Jan. 2020.

Digital Library

[24]

J. Dong and J. Pan, “Physics-based feature dehazing networks,” in Proc. Eur. Conf. Comput. Vis. Cham, Switzerland: Springer, 2020, pp. 188–204.

[25]

J. Panet al., “Physics-based generative adversarial models for image restoration and beyond,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 7, pp. 2449–2462, Jul. 2021.

[26]

W. Renet al., “Gated fusion network for single image dehazing,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 3253–3261.

[27]

X. Liu, Y. Ma, Z. Shi, and J. Chen, “GridDehazeNet: Attention-based multi-scale network for image dehazing,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2019, pp. 7313–7322.

[28]

T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, Jul. 2002.

Digital Library

[29]

F. Juefei-Xu, V. N. Boddeti, and M. Savvides, “Local binary convolutional neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 4284–4293.

[30]

Z. Yu, Y. Qin, H. Zhao, X. Li, and G. Zhao, “Dual-cross central difference network for face anti-spoofing,” in Proc. 13th Int. Joint Conf. Artif. Intell., Z.-H. Zhou, Ed. Aug. 2021, pp. 1281–1287. 10.24963/ijcai.2021/177.

[31]

Z. Suet al., “Pixel difference networks for efficient edge detection,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2021, pp. 5097–5107.

[32]

C. Wanget al., “EAA-Net: A novel edge assisted attention network for single image dehazing,” Knowl.-Based Syst., vol. 228, Sep. 2021, Art. no.

Digital Library

[33]

Z. Yu, J. Wan, Y. Qin, X. Li, S. Z. Li, and G. Zhao, “NAS-FAS: Static-dynamic central difference network search for face anti-spoofing,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 9, pp. 3005–3023, Sep. 2021.

[34]

I. Sobel and G. Feldman, “A 3×3 isotropic gradient operator for image,” Talk Stanford Artif. Intell. Lab., 1968, pp. 271–272.

[35]

J. M. Prewitt, “Object enhancement and extraction,” Picture Process. Psychopictorics, vol. 10, no. 1, pp. 15–19, 1970.

[36]

H. Scharr, “Optimal operators in digital image processing,” Ph.D. thesis, Interdiscipl. Center Sci. Comput., Heidelberg Univ., Heidelberg, Germany, 2000.

[37]

X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An extremely efficient convolutional neural network for mobile devices,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 6848–6856.

[38]

Z. He, G. Fu, Y. Cao, Y. Cao, J. Yang, and X. Li, “ESKN: Enhanced selective kernel network for single image super-resolution,” Signal Process., vol. 189, Dec. 2021, Art. no.

[39]

Z. Heet al., “Single image super-resolution based on progressive fusion of orientation-aware features,” Pattern Recognit., vol. 133, Jan. 2023, Art. no.

[40]

B. Liet al., “Benchmarking single-image dehazing and beyond,” IEEE Trans. Image Process., vol. 28, no. 1, pp. 492–505, Jan. 2019.

Digital Library

[41]

Y. Liuet al., “From synthetic to real: Image dehazing collaborating with unlabeled real data,” in Proc. 29th ACM Int. Conf. Multimedia, 2021, pp. 50–58.

[42]

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, Apr. 2004.

Digital Library

[43]

D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” in Proc. ICLR, 2015, pp. 1–15.

[44]

T. He, Z. Zhang, H. Zhang, Z. Zhang, J. Xie, and M. Li, “Bag of tricks for image classification with convolutional neural networks,” in Proc. CVPR, Jun. 2019, pp. 558–567.

[45]

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 770–778.

[46]

J. Liang, H. Zeng, and L. Zhang, “High-resolution photorealistic image translation in real-time: A Laplacian pyramid translation network,” in Proc. CVPR, 2021, pp. 9392–9400.

[47]

Z. Zhenget al., “Ultra-high-definition image dehazing via multi-guided bilateral learning,” in Proc. CVPR, 2021, pp. 16185–16194.

Cited By

He JWeng SYu LChen D(2025)Steganalysis Network With Two-Branch Preprocessing for Spatial and JPEG DomainsIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2024.347080935:2(1451-1463)Online publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1109/TCSVT.2024.3470809
Tang AWu YZhang Y(2025)RamIR: Reasoning and action prompting with Mamba for all-in-one image restorationApplied Intelligence10.1007/s10489-024-06226-y55:4Online publication date: 3-Jan-2025
https://dl.acm.org/doi/10.1007/s10489-024-06226-y
Guo QFeng XXue PSun SLi X(2025)Dual-domain multi-scale feature extraction for image dehazingMultimedia Systems10.1007/s00530-024-01630-331:1Online publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1007/s00530-024-01630-3
Show More Cited By

Index Terms

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention
1. Computing methodologies

Index terms have been assigned to the content through auto-classification.

Recommendations

FDDN: frequency-guided network for single image dehazing
Abstract
Haze appearing in natural scene images generally contains nonhomogeneous characteristics such as filaments, masses, and mist. The high-frequency part of hazy images contains variable background textures and haze shapes, whereas regions with mostly ...
Single Image Dehazing via Image Generating
Image and Video Technology
Abstract
Outdoor images taken in bad weather conditions often suffer from poor visibility. However, single image haze removal is an ill-posed problem, because the number of the equations is smaller than the number of unknowns. In this paper, a deep ...
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 ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Image Processing

IEEE Transactions on Image Processing Volume 33, Issue

2024

6889 pages

ISSN:1057-7149

Issue’s Table of Contents

1941-0042 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 01 January 2024

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 23 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

He JWeng SYu LChen D(2025)Steganalysis Network With Two-Branch Preprocessing for Spatial and JPEG DomainsIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2024.347080935:2(1451-1463)Online publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1109/TCSVT.2024.3470809
Tang AWu YZhang Y(2025)RamIR: Reasoning and action prompting with Mamba for all-in-one image restorationApplied Intelligence10.1007/s10489-024-06226-y55:4Online publication date: 3-Jan-2025
https://dl.acm.org/doi/10.1007/s10489-024-06226-y
Guo QFeng XXue PSun SLi X(2025)Dual-domain multi-scale feature extraction for image dehazingMultimedia Systems10.1007/s00530-024-01630-331:1Online publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1007/s00530-024-01630-3
Wang SHou QLi JLiu J(2025)TSID-Net: a two-stage single image dehazing framework with style transfer and contrastive knowledge transferThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-024-03511-241:3(1921-1938)Online publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1007/s00371-024-03511-2
Su L(2024)Study on an Intelligent English Translation Method Using an Improved Convolutional Neural Network ModelInternational Journal of e-Collaboration10.4018/IJeC.35755620:1(1-14)Online publication date: 7-Nov-2024
https://dl.acm.org/doi/10.4018/IJeC.357556
Liu ZTao QRen XWan ZPan WChen PDong H(2024)Denoising and Segmentation of Ultra-Low Field Magnetic Resonance Imaging Based on TriNetProceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering10.1145/3711129.3711166(202-208)Online publication date: 18-Oct-2024
https://dl.acm.org/doi/10.1145/3711129.3711166
Zhang RYang HYang YFu YPan L(2024)LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze DatasetProceedings of the 6th ACM International Conference on Multimedia in Asia10.1145/3696409.3700178(1-1)Online publication date: 3-Dec-2024
https://dl.acm.org/doi/10.1145/3696409.3700178
Fang WWang CLi ZGrau ALai TChen J(2024)TAENet: transencoder-based all-in-one image enhancement with depth awarenessApplied Intelligence10.1007/s10489-024-05569-w54:15-16(7509-7530)Online publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1007/s10489-024-05569-w
Wu MJiang AChen HYe J(2024)Physical-prior-guided single image dehazing network via unpaired contrastive learningMultimedia Systems10.1007/s00530-024-01462-130:5Online publication date: 6-Sep-2024
https://dl.acm.org/doi/10.1007/s00530-024-01462-1
Qin HBelyaev A(2024)Fast no-reference deep image dehazingMachine Vision and Applications10.1007/s00138-024-01601-835:5Online publication date: 29-Aug-2024
https://dl.acm.org/doi/10.1007/s00138-024-01601-8
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents