Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
research-article

LCDA-Net: Efficient Image Dehazing with Contrast-Regularized and Dilated Attention

Published: 14 August 2023 Publication History

Abstract

To address the issues of incomplete dehazing and low dehazing efficiency in existing dehazing networks, this study introduces a Lightweight Contrast-Regularized Dilated Attention Network (LCDA-Net) for single-image dehazing. Initially, Attention Context Encoding (ACE) is employed to decompose the input image into high-frequency and low-frequency features. For the low-frequency features, which are significantly impacted by haze, a pyramid dehazing module based on large-kernel dilated convolutional attention is devised, facilitating efficient dehazing through complementary semantic information. In contrast, for high-frequency features, a detail enhancement module based on deformable convolution is designed to restore fine texture information. Subsequently, high-frequency and low-frequency features are merged to reconstruct a clear image. Lastly, a loss function is designed by incorporating contrast regularization and edge loss strategies, effectively guiding the network to generate more realistic images. In this network, depthwise separable convolutions replace traditional convolutions, significantly reducing model complexity while maintaining satisfactory dehazing performance. Experimental results on the RESIDE benchmark dataset demonstrate that, compared to other advanced methods, the proposed approach achieves superior dehazing outcomes for both synthetic and real haze images, effectively mitigating artifacts, distortions, and incomplete dehazing. The PSNR on the SOTS indoor and outdoor test sets reaches 31.73 dB and 29.31 dB, respectively, with a network parameter size of merely 2 M. Additionally, the proposed method exhibits the lowest model complexity while achieving optimal performance metrics and the highest FPS, indicating both its superior dehazing performance and low complexity.

References

[1]
Kumar A and Srivastava S Object detection system based on convolution neural networks using single shot multi-box detector Proc Comput Sci 2020 171 2610-2617
[2]
Mo Y, Wu Y, Yang X, Liu F, and Liao Y Review the state-of-the-art technologies of semantic segmentation based on deep learning Neurocomputing 2022 493 626-646
[3]
Lauer J, Zhou M, Ye S, Menegas W, Schneider S, Nath T, Rahman MM, Di Santo V, Soberanes D, Feng G, et al. Multi-animal pose estimation, identification and tracking with deeplabcut Nat Methods 2022 19 4 496-504
[4]
McCartney EJ (1976) Optics of the atmosphere: scattering by molecules and particles. New York
[5]
He K, Sun J, and Tang X Single image haze removal using dark channel prior IEEE Trans Pattern Anal Mach Intell 2010 33 12 2341-2353
[6]
Zhu Q, Mai J, and Shao L A fast single image haze removal algorithm using color attenuation prior IEEE Trans Image Process 2015 24 11 3522-3533
[7]
Fattal R Dehazing using color-lines ACM Trans Graph 2014 34 1 1-14
[8]
Berman D, Avidan S, et al (2016) Non-local image dehazing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1674–1682
[9]
Liu J, Liu W, Sun J, Zeng T (2021) Rank-one prior: toward real-time scene recovery. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 14802–14810
[10]
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 11 5187-5198
[11]
Ren W, Liu S, Zhang H, Pan J, Cao X, Yang M-H (2016) Single image dehazing via multi-scale convolutional neural networks. In: Proceedings of 14th European conference computer vision–ECCV 2016:, Amsterdam, The Netherlands, October 11-14, 2016, Part II 14. Springer, pp 154–169
[12]
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
[13]
Liu X, Ma Y, Shi Z, Chen J (2019) Griddehazenet: attention-based multi-scale network for image dehazing. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 7314–7323
[14]
Chen D, He M, Fan Q, Liao J, Zhang L, Hou D, Yuan L, Hua G (2019) Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp 1375–1383. IEEE
[15]
Qin X, Wang Z, Bai Y, Xie X, Jia H (2020) Ffa-net: feature fusion attention network for single image dehazing. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11908–11915
[16]
Zhang X, Wang T, Wang J, Tang G, and Zhao L Pyramid channel-based feature attention network for image dehazing Comput Vis Image Underst 2020 197
[17]
Song Y, He Z, Qian H, and Du X Vision transformers for single image dehazing IEEE Trans Image Process 2023 32 1927-1941
[18]
Yang Y, Wang C, Liu R, Zhang L, Guo X, Tao D (2022) 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
[19]
Ullah H, Muhammad K, Irfan M, Anwar S, Sajjad M, Imran AS, and Albuquerque VHC Light-dehazenet: a novel lightweight CNN architecture for single image dehazing IEEE Trans Image Process 2021 30 8968-8982
[20]
Niu Z, Zhong G, and Yu H A review on the attention mechanism of deep learning Neurocomputing 2021 452 48-62
[21]
Su YZ, He C, Cui ZG, Li AH, and Wang N Physical model and image translation fused network for single-image dehazing Pattern Recogn 2023 142
[22]
Wang N, Cui Z, Su Y, He C, and Li A Multiscale supervision-guided context aggregation network for single image dehazing IEEE Signal Process Lett 2021 29 70-74
[23]
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 IEEE/CVF conference on computer vision and pattern recognition, pp 10551–10560
[24]
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30
[25]
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929
[26]
Lindeberg T Scale-space theory: a basic tool for analyzing structures at different scales J Appl Stat 1994 21 1–2 225-270
[27]
Chen Y, Fan H, Xu B, Yan Z, Kalantidis Y, Rohrbach M, Yan S, Feng J (2019) Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3435–3444
[28]
Xu K, Yang X, Yin B, Lau RW (2020) Learning to restore low-light images via decomposition-and-enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2281–2290
[29]
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
[30]
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
[31]
Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848–6856
[32]
Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116–131
[33]
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456. PMLR
[34]
Nie D, Lan R, Wang L, Ren X (2022) Pyramid architecture for multi-scale processing in point cloud segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 17284–17294
[35]
Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764–773
[36]
Shao Y, Li L, Ren W, Gao C, Sang N (2020) Domain adaptation for image dehazing. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2808–2817
[37]
You Y, Chen T, Sui Y, Chen T, Wang Z, and Shen Y Graph contrastive learning with augmentations Adv Neural Inf Process Syst 2020 33 5812-5823
[38]
Tian Y, Sun C, Poole B, Krishnan D, Schmid C, and Isola P What makes for good views for contrastive learning? Adv Neural Inf Process Syst 2020 33 6827-6839
[39]
Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp 1597–1607. PMLR
[40]
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
[41]
Qu Y, Chen Y, Huang J, Xie Y (2019) Enhanced pix2pix dehazing network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8160–8168
[42]
Liu S, Ding W, Liu C, Liu Y, Wang Y, and Li H Ern: Edge loss reinforced semantic segmentation network for remote sensing images Remote Sensing 2018 10 9 1339
[43]
Wang Z, Bovik AC, Sheikh HR, and Simoncelli EP Image quality assessment: from error visibility to structural similarity IEEE Trans Image Process 2004 13 4 600-612
[44]
Venkatanath N, Praneeth D, Bh MC, Channappayya SS, Medasani SS (2015) Blind image quality evaluation using perception based features. In: 2015 twenty first national conference on communications (NCC), pp 1–6. IEEE
[45]
Mittal A, Soundararajan R, and Bovik AC Making a “completely blind” image quality analyzer IEEE Signal Process Lett 2012 20 3 209-212
[46]
Mittal A, Moorthy AK, and Bovik AC No-reference image quality assessment in the spatial domain IEEE Trans Image Process 2012 21 12 4695-4708
[47]
Ren W, Ma L, Zhang J, Pan J, Cao X, Liu W, Yang M-H (2018) Gated fusion network for single image dehazing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3253–3261
[48]
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
[49]
Zhang J and Tao D Famed-net: a fast and accurate multi-scale end-to-end dehazing network IEEE Trans Image Process 2019 29 72-84
[50]
Li W, Fan G, Gan M (2023) Progressive encoding-decoding image dehazing network. Multimed Tools Appl, pp 1–23

Cited By

View all
  • (2024)Weak Change Detection of Wide field Foggy Video ImageProceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms10.1145/3690407.3690580(1041-1046)Online publication date: 21-Jun-2024

Index Terms

  1. LCDA-Net: Efficient Image Dehazing with Contrast-Regularized and Dilated Attention
        Index terms have been assigned to the content through auto-classification.

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image Neural Processing Letters
        Neural Processing Letters  Volume 55, Issue 8
        Dec 2023
        1592 pages

        Publisher

        Kluwer Academic Publishers

        United States

        Publication History

        Published: 14 August 2023
        Accepted: 31 July 2023

        Author Tags

        1. Image dehazing
        2. CNN
        3. Contrast regularization
        4. Large kernel attention

        Qualifiers

        • Research-article

        Funding Sources

        • National Natural Science Foundation of China
        • National Natural Science Foundation of China

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • Downloads (Last 12 months)0
        • Downloads (Last 6 weeks)0
        Reflects downloads up to 12 Jan 2025

        Other Metrics

        Citations

        Cited By

        View all
        • (2024)Weak Change Detection of Wide field Foggy Video ImageProceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms10.1145/3690407.3690580(1041-1046)Online publication date: 21-Jun-2024

        View Options

        View options

        Media

        Figures

        Other

        Tables

        Share

        Share

        Share this Publication link

        Share on social media