Skip to main content

04.01.2025

A Multi-scale Single Ultra-High-Definition Image Dehazing Method Based on Multi-resolution Feature Fusion

verfasst von: Ping Xue, YiXin Zhang, YuRao Bai, ShiXiong Deng

Erschienen in: Circuits, Systems, and Signal Processing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Currently, significant progress has been made in conventional-size image dehazing technology, but restoring ultra-high-definition images is still a challenging task. Existing ultra-high-definition image dehazing methods usually cut down the resolution of the image to adapt to the network architecture, thereby avoiding large-scale convolution operations. However, traditional downsampling methods may result in the loss of a large amount of high-resolution information. To solve this problem, this paper proposes a multi-scale ultra-high-definition image dehazing network. Using the Laplacian pyramid to extract multiple features with different resolutions from high to low and incorporating convolution blocks and SimAM modules to improve feature expression. To achieve the restoration of high-quality haze-free images, the ResNet block in the HRNet network is adjusted to MSBlock with parallel multi-scale convolution kernels, thereby strengthening the model’s receptive field. In addition, this article uses depthwise separable convolution to reduce model computational effort, while ensuring the network dehazing speed. A large number of skip connections are introduced to retain multi-scale information, and multi-resolution subnetworks are connected in parallel. By repeatedly fusing multiple scales, we obtain rich high-resolution features, thereby generating clear haze-free images. This paper quantitatively and qualitatively compares the proposed model with several existing state-of-the-art algorithms on the 4KID, I-Haze, and O-Hzae datasets. Experimental results show that the proposed method can not only maintain real-time processing speed but also achieve a high peak signal-to-noise ratio and structural similarity.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

ATZelektronik

Die Fachzeitschrift ATZelektronik bietet für Entwickler und Entscheider in der Automobil- und Zulieferindustrie qualitativ hochwertige und fundierte Informationen aus dem gesamten Spektrum der Pkw- und Nutzfahrzeug-Elektronik. 

Lassen Sie sich jetzt unverbindlich 2 kostenlose Ausgabe zusenden.

ATZelectronics worldwide

ATZlectronics worldwide is up-to-speed on new trends and developments in automotive electronics on a scientific level with a high depth of information. 

Order your 30-days-trial for free and without any commitment.

Weitere Produktempfehlungen anzeigen
Literatur
1.
Zurück zum Zitat M. Alesheikh, R. Feghhi, F.M. Sabzevari, A. Karimov, M. Hossain, K. Rambabu, Design of a high-power gaussian pulse transmitter for sensing and imaging of buried objects. IEEE Sens. J. 22(1), 279–287 (2021)CrossRef M. Alesheikh, R. Feghhi, F.M. Sabzevari, A. Karimov, M. Hossain, K. Rambabu, Design of a high-power gaussian pulse transmitter for sensing and imaging of buried objects. IEEE Sens. J. 22(1), 279–287 (2021)CrossRef
2.
Zurück zum Zitat C.O. Ancuti, C. Ancuti, R. Timofte, C. De Vleeschouwer, O-haze: a dehazing benchmark with real hazy and haze-free outdoor images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 754–762 (2018) C.O. Ancuti, C. Ancuti, R. Timofte, C. De Vleeschouwer, O-haze: a dehazing benchmark with real hazy and haze-free outdoor images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 754–762 (2018)
3.
Zurück zum Zitat C. Ancuti, C.O. Ancuti, R. Timofte, C. De Vleeschouwer, I-haze: a dehazing benchmark with real hazy and haze-free indoor images. Advanced Concepts for Intelligent Vision Systems: 19th International Conference, ACIVS 2018, Poitiers, France, September 24–27, 2018, Proceedings 19, pp. 620–631 (2018). Springer C. Ancuti, C.O. Ancuti, R. Timofte, C. De Vleeschouwer, I-haze: a dehazing benchmark with real hazy and haze-free indoor images. Advanced Concepts for Intelligent Vision Systems: 19th International Conference, ACIVS 2018, Poitiers, France, September 24–27, 2018, Proceedings 19, pp. 620–631 (2018). Springer
4.
Zurück zum Zitat H. Bai, J. Pan, X. Xiang, J. Tang, Self-guided image dehazing using progressive feature fusion. IEEE Trans. Image Proc. 31, 1217–1229 (2022)CrossRefMATH H. Bai, J. Pan, X. Xiang, J. Tang, Self-guided image dehazing using progressive feature fusion. IEEE Trans. Image Proc. 31, 1217–1229 (2022)CrossRefMATH
5.
Zurück zum Zitat D. Berman, S. Avidan, et al. Non-local image dehazing, in proceedings of the ieee conference on computer vision and pattern recognition, pp. 1674–1682 (2016) D. Berman, S. Avidan, et al. Non-local image dehazing, in proceedings of the ieee conference on computer vision and pattern recognition, pp. 1674–1682 (2016)
6.
Zurück zum Zitat S. Bianco, L. Celona, F. Piccoli, R. Schettini, High-resolution single image dehazing using encoder-decoder architecture, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp. 0–0 (2019) S. Bianco, L. Celona, F. Piccoli, R. Schettini, High-resolution single image dehazing using encoder-decoder architecture, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp. 0–0 (2019)
7.
Zurück zum Zitat P. Bühlmann, B. Yu, Boosting with the l 2 loss: regression and classification. J. Am. Stat. Assoc. 98(462), 324–339 (2003)MathSciNetCrossRefMATH P. Bühlmann, B. Yu, Boosting with the l 2 loss: regression and classification. J. Am. Stat. Assoc. 98(462), 324–339 (2003)MathSciNetCrossRefMATH
8.
Zurück zum Zitat B. Cai, X. Xu, K. Jia, C. Qing, D. Tao, Dehazenet: An end-to-end system for single image haze removal. IEEE Trans. Image Proc. 25(11), 5187–5198 (2016)MathSciNetCrossRefMATH B. Cai, X. Xu, K. Jia, C. Qing, D. Tao, Dehazenet: An end-to-end system for single image haze removal. IEEE Trans. Image Proc. 25(11), 5187–5198 (2016)MathSciNetCrossRefMATH
9.
Zurück zum Zitat D. Chen, M. He, Q. Fan, J. Liao, L. Zhang, D. Hou, L. Yuan, G. Hua, Gated context aggregation network for image dehazing and deraining, in 2019 IEEE winter conference on applications of computer vision (WACV), pp. 1375–1383 (2019). IEEE D. Chen, M. He, Q. Fan, J. Liao, L. Zhang, D. Hou, L. Yuan, G. Hua, Gated context aggregation network for image dehazing and deraining, in 2019 IEEE winter conference on applications of computer vision (WACV), pp. 1375–1383 (2019). IEEE
10.
Zurück zum Zitat H. Cheng, H. Wu, J. Zheng, K. Qi, W. Liu, A hierarchical self-attention augmented laplacian pyramid expanding network for change detection in high-resolution remote sensing images. ISPRS J. Photogr. Remote Sens. 182, 52–66 (2021)CrossRef H. Cheng, H. Wu, J. Zheng, K. Qi, W. Liu, A hierarchical self-attention augmented laplacian pyramid expanding network for change detection in high-resolution remote sensing images. ISPRS J. Photogr. Remote Sens. 182, 52–66 (2021)CrossRef
11.
Zurück zum Zitat F. Chollet, Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017) F. Chollet, Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
12.
Zurück zum Zitat T. Cui, J. Tian, E. Wang, Y. Tang, Single image dehazing by latent region-segmentation based transmission estimation and weighted l1-norm regularisation. IET Image Proc. 11(2), 145–154 (2017)CrossRefMATH T. Cui, J. Tian, E. Wang, Y. Tang, Single image dehazing by latent region-segmentation based transmission estimation and weighted l1-norm regularisation. IET Image Proc. 11(2), 145–154 (2017)CrossRefMATH
13.
Zurück zum Zitat Y. Ding, Z. Zhang, X. Zhao, D. Hong, W. Cai, N. Yang, B. Wang, Multi-scale receptive fields: Graph attention neural network for hyperspectral image classification. Expert Syst. Appl. 223, 119858 (2023)CrossRef Y. Ding, Z. Zhang, X. Zhao, D. Hong, W. Cai, N. Yang, B. Wang, Multi-scale receptive fields: Graph attention neural network for hyperspectral image classification. Expert Syst. Appl. 223, 119858 (2023)CrossRef
14.
Zurück zum Zitat H. Dong, J. Pan, L. Xiang, Z. Hu, X. Zhang, F. Wang, M.-H. Yang, Multi-scale boosted dehazing network with dense feature fusion, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2157–2167 (2020) H. Dong, J. Pan, L. Xiang, Z. Hu, X. Zhang, F. Wang, M.-H. Yang, Multi-scale boosted dehazing network with dense feature fusion, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2157–2167 (2020)
15.
16.
17.
Zurück zum Zitat R. Girshick, Fast r-cnn, in proceedings of the IEEE international conference on computer vision, pp. 1440–1448 (2015) R. Girshick, Fast r-cnn, in proceedings of the IEEE international conference on computer vision, pp. 1440–1448 (2015)
18.
Zurück zum Zitat K. He, J. Sun, X. Tang, Single image haze removal using dark channel prior. IEEE Trans. Patt. Anal. Mach. Intell. 33(12), 2341–2353 (2010)MATH K. He, J. Sun, X. Tang, Single image haze removal using dark channel prior. IEEE Trans. Patt. Anal. Mach. Intell. 33(12), 2341–2353 (2010)MATH
19.
Zurück zum Zitat A. Hore, D. Ziou, Image quality metrics: Psnr vs. ssim. 2010 20th international conference on pattern recognition, pp. 2366–2369 (2010). IEEE A. Hore, D. Ziou, Image quality metrics: Psnr vs. ssim. 2010 20th international conference on pattern recognition, pp. 2366–2369 (2010). IEEE
20.
Zurück zum Zitat S. Ki, H. Sim, J.-S. Choi, S. Kim, M. Kim, Fully end-to-end learning based conditional boundary equilibrium gan with receptive field sizes enlarged for single ultra-high resolution image dehazing, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 817–824 (2018) S. Ki, H. Sim, J.-S. Choi, S. Kim, M. Kim, Fully end-to-end learning based conditional boundary equilibrium gan with receptive field sizes enlarged for single ultra-high resolution image dehazing, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 817–824 (2018)
22.
23.
Zurück zum Zitat B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, Z. Wang, Benchmarking single-image dehazing and beyond. IEEE Trans. Image Proc. 28(1), 492–505 (2019)MathSciNetCrossRefMATH B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, Z. Wang, Benchmarking single-image dehazing and beyond. IEEE Trans. Image Proc. 28(1), 492–505 (2019)MathSciNetCrossRefMATH
24.
Zurück zum Zitat B. Li, Y. Gou, S. Gu, J.Z. Liu, J.T. Zhou, X. Peng, You only look yourself: Unsupervised and untrained single image dehazing neural network. Int. J. Comput. Vis. 129, 1754–1767 (2021)CrossRefMATH B. Li, Y. Gou, S. Gu, J.Z. Liu, J.T. Zhou, X. Peng, You only look yourself: Unsupervised and untrained single image dehazing neural network. Int. J. Comput. Vis. 129, 1754–1767 (2021)CrossRefMATH
25.
Zurück zum Zitat B. Lim, S. Son, H. Kim, S. Nah, K. Mu Lee, Enhanced deep residual networks for single image super-resolution, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 136–144 (2017) B. Lim, S. Son, H. Kim, S. Nah, K. Mu Lee, Enhanced deep residual networks for single image super-resolution, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 136–144 (2017)
26.
Zurück zum Zitat C. Lin, X. Rong, X. Yu, Msaff-net: multiscale attention feature fusion networks for single image dehazing and beyond. IEEE Trans. Multim. (2022) C. Lin, X. Rong, X. Yu, Msaff-net: multiscale attention feature fusion networks for single image dehazing and beyond. IEEE Trans. Multim. (2022)
27.
Zurück zum Zitat X. Liu, Y. Ma, Z. Shi, J. Chen, Griddehazenet: Attention-based multi-scale network for image dehazing, in proceedings of the IEEE/CVF international conference on computer vision, pp. 7314–7323 (2019) X. Liu, Y. Ma, Z. Shi, J. Chen, Griddehazenet: Attention-based multi-scale network for image dehazing, in proceedings of the IEEE/CVF international conference on computer vision, pp. 7314–7323 (2019)
28.
Zurück zum Zitat X. Liu, S. Qiao, T. Zhang, C. Zhao, X. Yao, Single-image super-resolution based on an improved asymmetric laplacian pyramid structure. Dig. Signal Proc. 145, 104321 (2024)CrossRefMATH X. Liu, S. Qiao, T. Zhang, C. Zhao, X. Yao, Single-image super-resolution based on an improved asymmetric laplacian pyramid structure. Dig. Signal Proc. 145, 104321 (2024)CrossRefMATH
29.
Zurück zum Zitat M. Mahmoodpour, A. Amirany, M.H. Moaiyeri, K. Jafari, A learning based contrast specific no reference image quality assessment algorithm, in 2022 international conference on machine vision and image processing (MVIP), pp. 1–4 (2022). IEEE M. Mahmoodpour, A. Amirany, M.H. Moaiyeri, K. Jafari, A learning based contrast specific no reference image quality assessment algorithm, in 2022 international conference on machine vision and image processing (MVIP), pp. 1–4 (2022). IEEE
30.
Zurück zum Zitat G. Meng, Y. Wang, J. Duan, S. Xiang, C. Pan, Efficient image dehazing with boundary constraint and contextual regularization, in proceedings of the IEEE international conference on computer vision, pp. 617–624 (2013) G. Meng, Y. Wang, J. Duan, S. Xiang, C. Pan, Efficient image dehazing with boundary constraint and contextual regularization, in proceedings of the IEEE international conference on computer vision, pp. 617–624 (2013)
31.
Zurück zum Zitat X. Qin, Z. Wang, Y. Bai, X. Xie, H. Jia, Ffa-net: feature fusion attention network for single image dehazing. Proc. AAAI Conf. Artif. Intell. 34, 11908–11915 (2020) X. Qin, Z. Wang, Y. Bai, X. Xie, H. Jia, Ffa-net: feature fusion attention network for single image dehazing. Proc. AAAI Conf. Artif. Intell. 34, 11908–11915 (2020)
32.
Zurück zum Zitat Y. Qiu, Y. Lu, Y. Wang, H. Jiang, Idod-yolov7: image-dehazing yolov7 for object detection in low-light foggy traffic environments. Sensors 23(3), 1347 (2023)CrossRefMATH Y. Qiu, Y. Lu, Y. Wang, H. Jiang, Idod-yolov7: image-dehazing yolov7 for object detection in low-light foggy traffic environments. Sensors 23(3), 1347 (2023)CrossRefMATH
33.
Zurück zum Zitat M. Schmidt, G. Fung, R. Rosales, Fast optimization methods for l1 regularization: A comparative study and two new approaches, in machine learning: ECML 2007: 18th European conference on machine learning, Warsaw, Poland, September 17-21, 2007. Proceedings 18, pp. 286–297 (2007). Springer M. Schmidt, G. Fung, R. Rosales, Fast optimization methods for l1 regularization: A comparative study and two new approaches, in machine learning: ECML 2007: 18th European conference on machine learning, Warsaw, Poland, September 17-21, 2007. Proceedings 18, pp. 286–297 (2007). Springer
34.
Zurück zum Zitat H. Sim, S. Ki, J.-S. Choi, S. Seo, S. Kim, M. Kim, High-resolution image dehazing with respect to training losses and receptive field sizes, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 912–919 (2018) H. Sim, S. Ki, J.-S. Choi, S. Seo, S. Kim, M. Kim, High-resolution image dehazing with respect to training losses and receptive field sizes, in proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 912–919 (2018)
35.
Zurück zum Zitat D. Singh, V. Kumar, M. Kaur, Single image dehazing using gradient channel prior. Appl. Intell. 49(12), 4276–4293 (2019)CrossRefMATH D. Singh, V. Kumar, M. Kaur, Single image dehazing using gradient channel prior. Appl. Intell. 49(12), 4276–4293 (2019)CrossRefMATH
36.
Zurück zum Zitat K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5693–5703 (2019) K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5693–5703 (2019)
37.
Zurück zum Zitat R.T. Tan, Visibility in bad weather from a single image. 2008 IEEE conference on computer vision and pattern recognition, pp. 1–8 (2008). IEEE R.T. Tan, Visibility in bad weather from a single image. 2008 IEEE conference on computer vision and pattern recognition, pp. 1–8 (2008). IEEE
38.
Zurück zum Zitat J.-P. Tarel, N. Hautiere, Fast visibility restoration from a single color or gray level image. 2009 IEEE 12th international conference on computer vision, pp. 2201–2208 (2009). IEEE J.-P. Tarel, N. Hautiere, Fast visibility restoration from a single color or gray level image. 2009 IEEE 12th international conference on computer vision, pp. 2201–2208 (2009). IEEE
39.
Zurück zum Zitat T. Wang, G. Tao, W. Lu, K. Zhang, W. Luo, X. Zhang, T. Lu, Restoring vision in hazy weather with hierarchical contrastive learning. Patt. Recogn. 145, 109956 (2024)CrossRefMATH T. Wang, G. Tao, W. Lu, K. Zhang, W. Luo, X. Zhang, T. Lu, Restoring vision in hazy weather with hierarchical contrastive learning. Patt. Recogn. 145, 109956 (2024)CrossRefMATH
40.
Zurück zum Zitat Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefMATH Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefMATH
41.
Zurück zum Zitat R.-Q. Wu, Z.-P. Duan, C.-L. Guo, Z. Chai, C. Li, Ridcp: Revitalizing real image dehazing via high-quality codebook priors, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 22282–22291 (2023) R.-Q. Wu, Z.-P. Duan, C.-L. Guo, Z. Chai, C. Li, Ridcp: Revitalizing real image dehazing via high-quality codebook priors, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 22282–22291 (2023)
42.
Zurück zum Zitat K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, Y. Bengio, Neural image caption generation with visual attention. Proc. ICML 37, 2048–2057 (2015) K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, Y. Bengio, Neural image caption generation with visual attention. Proc. ICML 37, 2048–2057 (2015)
43.
Zurück zum Zitat P. Xue, S. Deng, An end-to-end multi-resolution feature fusion defogging network. Signal Image Video Proc. 17(8), 4189–4197 (2023)CrossRefMATH P. Xue, S. Deng, An end-to-end multi-resolution feature fusion defogging network. Signal Image Video Proc. 17(8), 4189–4197 (2023)CrossRefMATH
44.
Zurück zum Zitat L. Yang, R.-Y. Zhang, L. Li, X. Xie, Simam: A simple, parameter-free attention module for convolutional neural networks, in international conference on machine learning, pp. 11863–11874 (2021). PMLR L. Yang, R.-Y. Zhang, L. Li, X. Xie, Simam: A simple, parameter-free attention module for convolutional neural networks, in international conference on machine learning, pp. 11863–11874 (2021). PMLR
45.
Zurück zum Zitat X. Yang, H. Li, Y.-L. Fan, R. Chen, Single image haze removal via region detection network. IEEE Trans. Multim. 21(10), 2545–2560 (2019)CrossRefMATH X. Yang, H. Li, Y.-L. Fan, R. Chen, Single image haze removal via region detection network. IEEE Trans. Multim. 21(10), 2545–2560 (2019)CrossRefMATH
46.
Zurück zum Zitat H. Zhang, H. Shen, Q. Yuan, X. Guan, Multispectral and sar image fusion based on laplacian pyramid and sparse representation. Remote Sens. 14(4), 870 (2022)CrossRefMATH H. Zhang, H. Shen, Q. Yuan, X. Guan, Multispectral and sar image fusion based on laplacian pyramid and sparse representation. Remote Sens. 14(4), 870 (2022)CrossRefMATH
47.
Zurück zum Zitat Y. Zheng, J. Zhan, S. He, J. Dong, Y. Du, Curricular contrastive regularization for physics-aware single image dehazing, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5785–5794 (2023) Y. Zheng, J. Zhan, S. He, J. Dong, Y. Du, Curricular contrastive regularization for physics-aware single image dehazing, in proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5785–5794 (2023)
48.
Zurück zum Zitat Z. Zheng, W. Ren, X. Cao, X. Hu, T. Wang, F. Song, X. Jia, Ultra-high-definition image dehazing via multi-guided bilateral learning, in 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 16180–16189 (2021). IEEE Z. Zheng, W. Ren, X. Cao, X. Hu, T. Wang, F. Song, X. Jia, Ultra-high-definition image dehazing via multi-guided bilateral learning, in 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 16180–16189 (2021). IEEE
49.
Zurück zum Zitat Q. Zhu, J. Mai, L. Shao, A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Proc. 24(11), 3522–3533 (2015)MathSciNetCrossRefMATH Q. Zhu, J. Mai, L. Shao, A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Proc. 24(11), 3522–3533 (2015)MathSciNetCrossRefMATH
Metadaten
Titel
A Multi-scale Single Ultra-High-Definition Image Dehazing Method Based on Multi-resolution Feature Fusion
verfasst von
Ping Xue
YiXin Zhang
YuRao Bai
ShiXiong Deng
Publikationsdatum
04.01.2025
Verlag
Springer US
Erschienen in
Circuits, Systems, and Signal Processing
Print ISSN: 0278-081X
Elektronische ISSN: 1531-5878
DOI
https://doi.org/10.1007/s00034-024-02970-1