AIDEDNet: anti-interference and detail enhancement dehazing network for real-world scenes

doi:10.1007/s11704-022-1523-9

Front. Comput. Sci.

2023, Vol. 17

Issue (2) : 172703 https://doi.org/10.1007/s11704-022-1523-9

RESEARCH ARTICLE

AIDEDNet: anti-interference and detail enhancement dehazing network for real-world scenes

Jian ZHANG^1,², Fazhi HE¹(

), Yansong DUAN³, Shizhen YANG¹

¹. School of Computer Science, Wuhan University, Wuhan 430072, China
². College of Sport Engineering and Information Technology, Wuhan Sports University, Wuhan 430079, China
³. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China

Download: PDF(13241 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

The haze phenomenon seriously interferes the image acquisition and reduces image quality. Due to many uncertain factors, dehazing is typically a challenge in image processing. The most existing deep learning-based dehazing approaches apply the atmospheric scattering model (ASM) or a similar physical model, which originally comes from traditional dehazing methods. However, the data set trained in deep learning does not match well this model for three reasons. Firstly, the atmospheric illumination in ASM is obtained from prior experience, which is not accurate for dehazing real-scene. Secondly, it is difficult to get the depth of outdoor scenes for ASM. Thirdly, the haze is a complex natural phenomenon, and it is difficult to find an accurate physical model and related parameters to describe this phenomenon. In this paper, we propose a black box method, in which the haze is considered an image quality problem without using any physical model such as ASM. Analytically, we propose a novel dehazing equation to combine two mechanisms: interference item and detail enhancement item. The interference item estimates the haze information for dehazing the image, and then the detail enhancement item can repair and enhance the details of the dehazed image. Based on the new equation, we design an anti-interference and detail enhancement dehazing network (AIDEDNet), which is dramatically different from existing dehazing networks in that our network is fed into the haze-free images for training. Specifically, we propose a new way to construct a haze patch on the flight of network training. The patch is randomly selected from the input images and the thickness of haze is also randomly set. Numerous experiment results show that AIDEDNet outperforms the state-of-the-art methods on both synthetic haze scenes and real-world haze scenes.

Keywords dehaze anti-interference detail enhancement network

Corresponding Author(s): Fazhi HE

About author:

Tongcan Cui and Yizhe Hou contributed equally to this work.

Just Accepted Date: 25 February 2022 Issue Date: 05 September 2022

Cite this article:

Jian ZHANG,Fazhi HE,Yansong DUAN, et al. AIDEDNet: anti-interference and detail enhancement dehazing network for real-world scenes[J]. Front. Comput. Sci., 2023, 17(2): 172703.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-1523-9
https://academic.hep.com.cn/fcs/EN/Y2023/V17/I2/172703

Fig.1 The overall framework of proposed method

Fig.2 The overall structure of the proposed Anti-Interference and Detail Enhancement Dehazing Network (AIDEDNet). In this network, red rectangle marks interference module and green rectangle marks compensation module

Fig.3 The proposed method of synthetic haze on the flight of network training

Fig.4 The training process

	Dark channel [23]	AOD-Net [25]	GCANet [27]	pix2pix [30]	Our $α$ test	Our $β$ test
BRISQUE [33]	32.17	31.49	28.82	29.36	26.53	23.63
BLIINDS-II [34]	28.1	26.7	24.3	27.5	25.6	20.5
NIMA [35]	5.42	5.48	5.87	6.19	6.37	6.45

Tab.1 Average BRISQUE [33], BLIINDS-II [34] and NIMA [35] of dehazed results on proposed test set

Fig.5 Qualitative comparisons with state-of-the-art dehazing methods for hazy images. The first column is original haze image. The comparison methods from the second column to the sixth column are: haze image, dark channel [23], AOD-Net [25], GCANet [27], pix2pix [30] and proposed

α

test,

β

test

Fig.6 Ablation comparisons. Row No.1 is the original haze image. Row No.2 is the dehazing results which only remove the interference item. Row No.3 is the dehazing results which add detail enhancement item based on row No.2

1	E J McCartney. Optics of the Atmosphere: Scattering by Molecules and Particles. New York: Wiley, 1976
2	M, Ju C, Ding W, Ren Y, Yang D, Zhang Y J Guo . IDE: image dehazing and exposure using an enhanced atmospheric scattering model. IEEE Transactions on Image Processing, 2021, 30: 2180– 2192
3	A, Golts D, Freedman M Elad . Unsupervised single image dehazing using dark channel prior loss. IEEE Transactions on Image Processing, 2020, 29: 2692– 2701
4	H, Zhang V M Patel. Densely connected pyramid dehazing network. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 3194− 3203
5	A, Dutta G, Ashishkumar C V R Rao . Performance analysis of ASR system in hybrid DNN-HMM framework using a PWL Euclidean activation function. Frontiers of Computer Science, 2021, 15( 4): 154705
6	Y, Chen F, He H, Li D, Zhang Y Wu . A full migration BBO algorithm with enhanced population quality bounds for multimodal biomedical image registration. Applied Soft Computing, 2020, 93: 106335
7	H, Zhang Y, Zhang Y Geng . Practical age estimation using deep label distribution learning. Frontiers of Computer Science, 2021, 15( 3): 153318
8	H, Kim C, Yeo I D, Lee D Mun . Deep-learning-based retrieval of piping component catalogs for plant 3D CAD model reconstruction. Computers in Industry, 2020, 123: 103320
9	Y, Liang F, He X Zeng . 3D mesh simplification with feature preservation based on whale optimization algorithm and differential evolution. Integrated Computer-Aided Engineering, 2020, 27( 4): 417– 435
10	X, Zhang Q, Liu D, Wang L, Zhao N, Gu S Maybank . Self-taught semisupervised dictionary learning with nonnegative constraint. IEEE Transactions on Industrial Informatics, 2020, 16( 1): 532– 543
11	Y, Yan F, Nie W, Li C, Gao Y, Yang D Xu . Image classification by cross-media active learning with privileged information. IEEE Transactions on Multimedia, 2016, 18( 12): 2494– 2502
12	Y, Song F, He Y, Duan Y, Liang X Yan . A kernel correlation-based approach to adaptively acquire local features for learning 3D point clouds. Computer-Aided Design, 2022, 146: 103196
13	S F, Ali M A, Khan A S Aslam . Fingerprint matching, spoof and liveness detection: classification and literature review. Frontiers of Computer Science, 2021, 15( 1): 151310
14	Y, Liang F, He X, Zeng J Luo . An improved loop subdivision to coordinate the smoothness and the number of faces via multi-objective optimization. Integrated Computer-Aided Engineering, 2022, 29( 1): 23– 41 https://doi.org/10.3233/ICA-210661
15	C, Yeo S, Kim H, Kim S, Kim D Mun . Deep learning applications in an industrial process plant: repository of segmented point clouds for pipework components. JMST Advances, 2020, 2( 1): 15– 24
16	H, Wu F, He Y, Duan X Yan. Perceptual metric-guided human image generation. Integrated Computer-Aided Engineering, 2021, DOI: https://doi.org/10.3233/ICA-210672
17	Q, Wu J, Zhang W, Ren W, Zuo X Cao . Accurate transmission estimation for removing haze and noise from a single image. IEEE Transactions on Image Processing, 2020, 29: 2583– 2597
18	L, Li Y, Dong W, Ren J, Pan C, Gao N, Sang M H Yang . Semi-supervised image dehazing. IEEE Transactions on Image Processing, 2020, 29: 2766– 2779
19	G, Koppe A, Meyer-Lindenberg D Durstewitz . Deep learning for small and big data in psychiatry. Neuropsychopharmacology, 2021, 46( 1): 176– 190
20	T T, Høye J, Ärje K, Bjerge O L, Hansen A, Iosifidis F, Leese H M R, Mann K, Meissner C, Melvad J Raitoharju . Deep learning and computer vision will transform entomology. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118( 2): e2002545117
21	S, Zhang F He . DRCDN: learning deep residual convolutional dehazing networks. The Visual Computer, 2020, 36( 9): 1797– 1808
22	W, Ren J, Pan H, Zhang X, Cao M H Yang . Single image dehazing via multi-scale convolutional neural networks with holistic edges. International Journal of Computer Vision, 2020, 128( 1): 240– 259
23	K, He J, Sun X Tang . Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33( 12): 2341– 2353
24	J, Zhang F, He Y Chen . A new haze removal approach for sky/river alike scenes based on external and internal clues. Multimedia Tools and Applications, 2020, 79( 3): 2085– 2107
25	B, Li X, Peng Z, Wang J, Xu D Feng. AOD-Net: All-in-one dehazing network. In: Proceedings of 2017 IEEE International Conference on Computer Vision. 2017, 4780− 4788
26	W, Ren L, Ma J, Zhang J, Pan X, Cao W, Liu M H Yang. Gated fusion network for single image dehazing. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 3253− 3261
27	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: Proceedings of 2019 IEEE Winter Conference on Applications of Computer Vision. 2019, 1375− 1383
28	D, Engin A, Genç Ekenel H Kemal. Cycle-dehaze: enhanced CycleGAN for single image dehazing. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2018, 825− 833
29	C, Li C, Guo J, Guo P, Han H, Fu R Cong . PDR-Net: perception-inspired single image dehazing network with refinement. IEEE Transactions on Multimedia, 2020, 22( 3): 704– 716
30	Y, Qu Y, Chen J, Huang Y Xie. Enhanced pix2pix dehazing network. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 8152− 8160
31	C, Ancuti C O, Ancuti Vleeschouwer C De. D-HAZY: a dataset to evaluate quantitatively dehazing algorithms. In: Proceedings of 2016 IEEE International Conference on Image Processing. 2016, 2226− 2230
32	B, Li W, Ren D, Fu D, Tao D, Feng W, Zeng Z Wang . Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 2019, 28( 1): 492– 505
33	L S, Chow H Rajagopal . Modified-BRISQUE as no reference image quality assessment for structural MR images. Magnetic Resonance Imaging, 2017, 43: 74– 87
34	A, Yadav S, Sohoni D Chandler. GPGPU based implementation of a high performing no reference (NR)-IQA algorithm, BLIINDS-II. IS and T International Symposium on Electronic Imaging Science and Technology, 2017, Part F130046(12): 21− 25
35	H, Talebi P Milanfar . NIMA: neural image assessment. IEEE Transactions on Image Processing, 2018, 27( 8): 3998– 4011
36	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 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020, 2154− 2164
37	J, Pan J, Dong Y, Liu J, Zhang J, Ren J, Tang Y W, Tai M H Yang . Physics-based generative adversarial models for image restoration and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43( 7): 2449– 2462
38	Y, Pan F, He H Yu . Learning social representations with deep autoencoder for recommender system. World Wide Web, 2020, 23( 4): 2259– 2279
39	L, Qiao F, Zhang X, Huang K, Li E Chen . Heterogeneous-attributes enhancement deep framework for network embedding. Frontiers of Computer Science, 2021, 15( 6): 156616
40	J, Dong J Pan. Physics-based feature dehazing networks. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 188− 204
41	Z U, Khan D, Pi S, Yao A, Nawaz F, Ali S Ali . PiEnPred: a bi-layered discriminative model for enhancers and their subtypes via novel cascade multi-level subset feature selection algorithm. Frontiers of Computer Science, 2021, 15( 6): 156904
42	X, Meng W, Li X, Peng Y, Li M Li . Protein interaction networks: centrality, modularity, dynamics, and applications. Frontiers of Computer Science, 2021, 15( 6): 156902
43	C, Li Y, Mao R, Zhang J Huai . A revisit to mackay algorithm and its application to deep network compression. Frontiers of Computer Science, 2020, 14( 4): 144304
44	J, Luo F, He H, Li X T, Zeng Y Liang. A novel whale optimization algorithm with filtering disturbance and non-linear step. International Journal of Bio-Inspired Computation, DOI: https://doi.org/10.1504/IJBIC.2020. 10036562
45	L, Huang J, Peng R, Zhang G, Li L Lin . Learning deep representations for semantic image parsing: a comprehensive overview. Frontiers of Computer Science, 2018, 12( 5): 840– 857
46	R, Quan X, Yu Y, Liang Y Yang. Removing raindrops and rain streaks in one go. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 9143− 9152
47	Y, Du J, Xu X, Zhen M M, Cheng L Shao . Conditional variational image deraining. IEEE Transactions on Image Processing, 2020, 29: 6288– 6301
48	H, Zeng X, Xie J Ning . Hyperspectral image denoising via global spatial-spectral total variation regularized nonconvex local low-rank tensor approximation. Signal Processing, 2021, 178: 107805
49	A, Kumar A Jain . Image smog restoration using oblique gradient profile prior and energy minimization. Frontiers of Computer Science, 2021, 15( 6): 156706
50	Z, Zhu E, Albadawy A, Saha J, Zhang M R, Harowicz M A Mazurowski . Deep learning for identifying radiogenomic associations in breast cancer. Computers in Biology and Medicine, 2019, 109: 85– 90
51	M, Masood T, Nazir M, Nawaz A, Javed M, Iqbal A Mehmood . Brain tumor localization and segmentation using mask RCNN. Frontiers of Computer Science, 2021, 15( 6): 156338
52	X, Zhang W, Hu N, Xie H, Bao S Maybank . A robust tracking system for low frame rate video. International Journal of Computer Vision, 2015, 115( 3): 279– 304
53	X, Zhang W, Li W, Hu H, Ling S Maybank . Block covariance based l1 tracker with a subtle template dictionary. Pattern Recognition, 2013, 46( 7): 1750– 1761
54	H, Li F, He Y, Chen Y Pan . MLFS-CCDE: MULTI-objective large-scale feature selection by cooperative coevolutionary differential evolution. Memetic Computing, 2021, 13( 1): 1– 18
55	H, Men B, Wang G Wu . MITAR: a study on human activity recognition based on NLP with microscopic perspective. Frontiers of Computer Science, 2021, 15( 5): 155330

[1]

FCS-21523-OF-JZ_suppl_1

Download

[1]	Youming GE, Cong HUANG, Yubao LIU, Sen ZHANG, Weiyang KONG. Unsupervised social network embedding via adaptive specific mappings[J]. Front. Comput. Sci., 2024, 18(3): 183310-.
[2]	Wuxiu QUAN, Yu HU, Tingting DAN, Junyu LI, Yue ZHANG, Hongmin CAI. Weakly-supervised instance co-segmentation via tensor-based salient co-peak search[J]. Front. Comput. Sci., 2024, 18(2): 182305-.
[3]	Min HAO, Beihai TAN, Siming WANG, Rong YU, Ryan Wen LIU, Lisu YU. Exploiting blockchain for dependable services in zero-trust vehicular networks[J]. Front. Comput. Sci., 2024, 18(2): 182805-.
[4]	Qi LI, Xingli WANG, Luoyi FU, Xinde CAO, Xinbing WANG, Jing ZHANG, Chenghu ZHOU. VSAN: A new visualization method for super-large-scale academic networks[J]. Front. Comput. Sci., 2024, 18(1): 181701-.
[5]	Yanbin JIANG, Huifang MA, Xiaohui ZHANG, Zhixin LI, Liang CHANG. Incorporating metapath interaction on heterogeneous information network for social recommendation[J]. Front. Comput. Sci., 2024, 18(1): 181302-.
[6]	Miao ZHANG, Tingting HE, Ming DONG. Meta-path reasoning of knowledge graph for commonsense question answering[J]. Front. Comput. Sci., 2024, 18(1): 181303-.
[7]	Shuo TAN, Lei ZHANG, Xin SHU, Zizhou WANG. A feature-wise attention module based on the difference with surrounding features for convolutional neural networks[J]. Front. Comput. Sci., 2023, 17(6): 176338-.
[8]	Yongquan LIANG, Qiuyu SONG, Zhongying ZHAO, Hui ZHOU, Maoguo GONG. BA-GNN: Behavior-aware graph neural network for session-based recommendation[J]. Front. Comput. Sci., 2023, 17(6): 176613-.
[9]	Yufei ZENG, Zhixin LI, Zhenbin CHEN, Huifang MA. Aspect-level sentiment analysis based on semantic heterogeneous graph convolutional network[J]. Front. Comput. Sci., 2023, 17(6): 176340-.
[10]	Yamin HU, Hao JIANG, Zongyao HU. Measuring code maintainability with deep neural networks[J]. Front. Comput. Sci., 2023, 17(6): 176214-.
[11]	Jinwei LUO, Mingkai HE, Weike PAN, Zhong MING. BGNN: Behavior-aware graph neural network for heterogeneous session-based recommendation[J]. Front. Comput. Sci., 2023, 17(5): 175336-.
[12]	Di ZHANG, Dong ZHAO, Huadong MA. Robust load-balanced backbone-based multicast routing in mobile opportunistic networks[J]. Front. Comput. Sci., 2023, 17(4): 174502-.
[13]	Yuan GAO, Xiang WANG, Xiangnan HE, Huamin FENG, Yongdong ZHANG. Rumor detection with self-supervised learning on texts and social graph[J]. Front. Comput. Sci., 2023, 17(4): 174611-.
[14]	Xulun YE, Jieyu ZHAO. Heterogeneous clustering via adversarial deep Bayesian generative model[J]. Front. Comput. Sci., 2023, 17(3): 173322-.
[15]	Shuang LIU, Fan ZHANG, Baiyang ZHAO, Renjie GUO, Tao CHEN, Meishan ZHANG. APPCorp: a corpus for Android privacy policy document structure analysis[J]. Front. Comput. Sci., 2023, 17(3): 173320-.

Viewed

Full text

Abstract

Cited

Shared

Discussed