多深度自适应融合去雾生成网络

doi:10.13229/j.cnki.jdxbgxb.20230813

Abstract

Abstract:

To address issues such as incomplete dehazing and distortion in image dehazing， a multi-depth adaptive fusion dehazing generation network is proposed using generative adversarial training. Firitly， the network utilizes U-Net++ architecture and haze perception units to learn the haze features. Secondly， a vector mixed attention module is proposed to expand the bottom-layer information and supplement details in the dehazed image. Thirdly， adaptive weights are constructed from partial and global dimensions to select features at different depths and improve the utilization of effective information in the network. Finally， a mixed loss is employed to ensure the quality of the generated image， and Wasserstein distance is introduced into the adversarial loss. To validate the effectiveness of the proposed algorithm， objective quantitative comparisons are conducted with 10 popular dehazing algorithms on the RESIDE and Haze4k datasets， followed by subjective evaluations on real images. The experimental results demonstrate that the proposed algorithm achieves a PSNR of 36.20 dB and SSIM of 0.988 4 on the SOTS Outdoor validation set， showing superior dehazing performance.

Key words: information processing technology, image dehazing, generate adversarial network, multiple depth feature, adaptive feature fusion

CLC Number:

TP391.4

Bin WEN,Shun PENG,Chao YANG,Yan-jun SHEN,Hui LI. Multi⁃depth adaptive fusion dehazing generation network[J].Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2103-2113.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

Fig.10

Fig.11

Table 2

Table 3

References 20

[1]	Yao D N L, Bade A, Zolkifly I A, et al. A naive but effective post-processing approach for dark channel prior (DCP)[C]∥Data Science and Emerging Technologies: Proceedings of DaSET 2022, Petaling Jaya, Malaysia, 2022: 67-76.
[2]	He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[3]	Raanan F. Dehazing using color-lines[J]. ACM Transactions on Graphics, 2014, 34(1): 1-14.
[4]	Tan R T. Visibility in bad weather from a single image[C]∥Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), Anchorage, USA, 2008: 1-8.
[5]	Zhu Q S, Mai J M, Shao L. A fast single image haze removal algorithm using color attenuation prior[J]. 2015, 24(11): 3522-3533.
[6]	Cai B, Xu X, Jia K, et al. Dehazenet: an end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.
[7]	Li B, Peng X, Wang Z, et al. Aod-net: all-in-One dehazing network[C]∥proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017: 4780-4788.
[8]	Liu X, Ma Y, Shi Z, et al. Grid dehaze net: attention-based multi-scale network for image dehazing[C]∥Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 2019: 7313-7322.
[9]	Qu Y, Chen Y, Huang J, et al. Enhanced pix2pix dehazing network[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 2019: 8152-8160.
[10]	Dong Y, Liu Y, Zhang H, et al. Fd-gan: generative adversarial networks with fusion-discriminator for single image dehazing[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 10729-10736.
[11]	Mehta A, Sinha H, Narang P, et al. HIDeGan: a hyperspectral-guided image dehazing GAN[J]. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, USA, 2020: 846-856.
[12]	Qin X, Wang Z L, Bai Y C, et al. FFA-Net: feature fusion attention network for single image dehazing[J/OL]. [2023-07-22].
[13]	Yang X, Yan J C, Ming Q, et al. Rethinking rotated object detection with gaussian wasserstein distance loss[J/OL]. [2023-07-23].
[14]	Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 5967-5976.
[15]	Zhao C, Shuai R, Ma L, et al. Segmentation of skin lesions image based on U-Net++[J]. Multimedia Tools and Applications, 2022, 81(6): 8691-8717.
[16]	Fu H X, Song G Q, Wang Y C. Improved YOLOv4 marine target detection combined with CBAM[J]. Symmetry, 2021, 13(4): No.623.
[17]	Li B, Ren W, Fu D, et al. Benchmarking single-image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505.
[18]	Liu Y, Zhu L, Pei S D, et al. From synthetic to real: image dehazing collaborating with unlabeled real data[J/OL]. [2023-07-23].
[19]	Sun Z, Zhang Y, Bao F, et al. SADnet: semi-supervised single image dehazing method based on an attention mechanism[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2022, 18(2): 1-23.
[20]	Manu C M, Sreeni K G. GANID: a novel generative adversarial network for image dehazing[J]. The Visual Computer, 2022, 39: 2923-3936.

Related Articles 15

[1]	Ru-bo ZHANG,Shi-qi CHANG,Tian-yi ZHANG. Review on image information hiding methods based on deep learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1497-1515.
[2]	Ya-li XUE,Tong-an YU,Shan CUI,Li-zun ZHOU. Infrared small target detection based on cascaded nested U-Net [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1714-1721.
[3]	Wei-zhi NIE,Fei YIN,Yi-shan SU. Review of task⁃driven imaging sonar for underwater target recognition approaches [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(4): 1163-1175.
[4]	De-qiang CHENG,Gui LIU,Qi-qi KOU,Jian-ying ZHANG,He JIANG. Lightweight image super⁃resolution network based on adaptive large kernel attention fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(3): 1015-1027.
[5]	Xi ZHANG,Shao-ping KU. Facial super-resolution reconstruction method based on generative adversarial networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 333-338.
[6]	Jin DUAN,An-ni YAO,Zhen WANG,Lin-tao YU. Improved sparrow search algorithm optimizes coverage in wireless sensor networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(3): 761-770.
[7]	Jian XIAO,Jing-wei LIU,Xin HU,Xiao-gang QI. TDOA⁃AOA location based on improved african vulture algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(12): 3558-3567.
[8]	Yong WANG,Yu-xiao BIAN,Xin-chao LI,Chun-ming XU,Gang PENG,Ji-kui WANG. Image dehazing algorithm based on multiscale encoding decoding neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(12): 3626-3636.
[9]	Mian-shu CHEN,Lu-lu YU,Xiao-ni LI,Hong-yu ZHENG. Loop detection based on uniform ORB [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2666-2675.
[10]	Yu-ting SU,Ji WANG,Wei ZHAO,Pei-guang JING. Dynamic graph convolutional neural network for image sentiment distribution prediction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2601-2610.
[11]	Qiang GUO,Guo-hui ZHU,Wan-chen LI. TDOA/FDOA localization based on chaotic sparrow search algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 593-600.
[12]	Hou⁃jie LI,Fa⁃sheng WANG,Jian⁃jun HE,Yu ZHOU,Wei LI,Yu⁃xuan DOU. Pseudo sample regularization Faster R⁃CNN for traffic sign detection [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1251-1260.
[13]	Hua-wei JIANG,Zhen YANG,Xin ZHANG,Qian-lin DONG. Research progress of image dehazing algorithms [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1169-1181.
[14]	De-xing WANG,Ruo-you WU,Hong-chun YUAN,Peng GONG,Yue WANG. Underwater image restoration based on multi-scale attention fusion and convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1396-1404.
[15]	Jing JIN,Jian-wu DANG,Yang-ping WANG,Dong SHEN. Multi⁃cue particle filter tracking based on fuzzy statistical texture features [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(3): 1111-1120.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 10

[1]	Li Jie, Zhuang Ji-de, Wei Dong, Wan Yi-qiang. Comparative traction performance tests between bionic camel foot tire and common tire[J]. 吉林大学学报(工学版), 2006, 36(04): 510 -513 .
[2]	Yang Jiewei,,Wu Yihui,Liu Bo,, Wang Shurong, Zhang Ping, Zhang Tao,. Torque and minimum dimension of axialmagnetized permanent magnet micromotor[J]. 吉林大学学报(工学版), 2006, 36(增刊1): 105 -0109 .
[3]	Zhang Peng，Li Yuan-chun . Modeling and control for the system of two manipulators in handling flexible payload based on hinge configuration[J]. 吉林大学学报(工学版), 2008, 38(02): 444 -0448 .
[4]	Zou Jun，Fu Xin，Yang Hua-yong . Numerical simulation and experimental investigation into tension control system for the hot strip finishing mill[J]. 吉林大学学报(工学版), 2008, 38(02): 354 -0359 .
[5]	Yao Zhi-sheng, Shao Chun-fu, Xiong Zhi-hua, Yue Hao . Short-term traffic volumes forecasting of road network based on principal component analysis and support vector machine[J]. 吉林大学学报(工学版), 2008, 38(01): 48 -52 .
[6]	Wang Liya，Meng Guangwei，Chen Jiezhong. Method for Identifying Local Stiffness of Linear Structures Under Random Excitations[J]. 吉林大学学报(工学版), 2006, 36(01): 1 -0004 .
[7]	Yang Chun-sheng;Zhang Tao;Cheng Jun-kang;Liu Guo-dong. Influence of nonlinearity on measuring precision of dualfrequency laser interferometer with two longitudinal modes[J]. 吉林大学学报(工学版), 2008, 38(03): 561 -0564 .
[8]	Wang De-hui，Shang Guang-rui，Ren Lu-quan . Nonlinear math′s model on Cu-Zn alloy bionic coupling hydrophilic surface [J]. 吉林大学学报(工学版), 2008, 38(01): 105 -109 .
[9]	XU Yue, WANG Tai-yong, ZHAO Yan-ju, DONG Jing-chuan, LI Bo . Reconfigurable CNC system based on ARM and DSP[J]. 吉林大学学报(工学版), 2008, 38(04): 848 -851 .
[10]	Yu Fan-hua,Liu Han-bing . Structural damage identification by support vector machine and particle swarm algorithm[J]. 吉林大学学报(工学版), 2008, 38(02): 434 -0438 .

Method	SOTS（indoor）		SOTS（outdoor）		Haze4k
Method	PSNR /dB	SSIM /%	PSNR /dB	SSIM /%	PSNR /dB	SSIM /%
DCP	16.62	0.817 9	19.13	0.814 8	14.01	0.767 9
CAP	19.05	0.843 1	15.93	0.815 0	14.46	0.672 4
AOD-Net	19.06	0.850 4	20.29	0.876 5	17.15	0.833 9
Dehazed	21.14	0.847 2	22.46	0.851 4	19.12	0.846 7
FD-GAN	23.45	0.925 8	23.68	0.901 7	20.39	0.894 3
HIDE-GAN	25.01	0.871 2	26.64	0.892 3	21.72	0.915 2
GridDehazed	32.16	0.983 6	30.86	0.981 9	23.29	0.931 2
FFA-Net	36.39	0.988 6	33.57	0.984 0	26.96	0.957 3
SADNet	23.85	0.902 3	26.97	0.927 4	21.40	0.907 8
GANID	32.52	0.936 7	33.96	0.949 1	-	-
本文	34.20	0.985 1	36.20	0.988 4	27.67	0.968 9

模型	VMAM	AWM	HPB	PSNR/dB	SSIM/%
模型 a	√	√	√	36.20	0.988 4
模型 b		√	√	35.04	0.985 3
模型 c			√	33.22	0.984 3
模型 d				32.41	0.983 9

Method	PSNR/dB	SSIM/%
Baseline	27.98	0.938 2
Wloss	30.04	0.960 1
L_PM+Wloss	30.89	0.969 8
L_P+L_PM+Wloss	32.41	0.983 9

Multi⁃depth adaptive fusion dehazing generation network

RICH HTML

PDF (PC)