{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:17:45Z","timestamp":1753885065694,"version":"3.41.2"},"reference-count":43,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T00:00:00Z","timestamp":1610409600000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906097"],"award-info":[{"award-number":["61906097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Inspired by the application of CycleGAN networks to the image style conversion problem Zhu et al. (2017), this paper proposes an end\u2010to\u2010end network, DefogNet, for solving the single\u2010image dehazing problem, treating the image dehazing problem as a style conversion problem from a fogged image to a nonfogged image, without the need to estimate a priori information from an atmospheric scattering model. DefogNet improves on CycleGAN by adding a cross\u2010layer connection structure in the generator to enhance the network\u2019s multiscale feature extraction capability. The loss function was redesigned to add detail perception loss and color perception loss to improve the quality of texture information recovery and produce better fog\u2010free images. In this paper, the novel Defog\u2010SN algorithm is presented. This algorithm adds a spectral normalization layer to the discriminator\u2019s convolution layer to make the discriminant network conform to a 1\u2010Lipschitz continuum and further improve the model\u2019s stability. In this study, the experimental process is completed based on the O\u2010HAZE, I\u2010HAZE, and RESIDE datasets. The dehazing results show that the method outperforms traditional methods in terms of PSNR and SSIM on synthetic datasets and Avegrad and Entropy on naturalistic images.<\/jats:p>","DOI":"10.1155\/2021\/2352185","type":"journal-article","created":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T23:12:20Z","timestamp":1610493140000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DefogNet: A Single\u2010Image Dehazing Algorithm with Cyclic Structure and Cross\u2010Layer Connections"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0673-7754","authenticated-orcid":false,"given":"Suting","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-7332","authenticated-orcid":false,"given":"Wenhao","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Shaw","family":"Peter","sequence":"additional","affiliation":[]},{"given":"Chuang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Kui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Huang","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,1,12]]},"reference":[{"key":"e_1_2_8_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2776239"},{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/ecj.12092"},{"key":"e_1_2_8_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2015.02.018"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.597272"},{"key":"e_1_2_8_5_2","doi-asserted-by":"crossref","unstructured":"TanR. T. Visibility in bad weather from a single image Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition June 2008 Anchorage AK USA IEEE 1\u20138.","DOI":"10.1109\/CVPR.2008.4587643"},{"key":"e_1_2_8_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/30.580378"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-336156-1.50061-6"},{"key":"e_1_2_8_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409069"},{"key":"e_1_2_8_9_2","unstructured":"SchechnerY. Y. NarasimhanS. G. andNayarS. K. Instant dehazing of images using polarization Proceedings of the 2001 IEEE computer Society Conference on computer vision and Pattern recognition CVPR 2001 December 2001 Kauai HI USA IEEE."},{"key":"e_1_2_8_10_2","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He K.","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_8_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2446191"},{"key":"e_1_2_8_12_2","doi-asserted-by":"crossref","unstructured":"AncutiC. O. AncutiC. andHermansC. A fast semi-inverse approach to detect and remove the haze from a single image Proceedings of the Asian Conference on Computer Vision December 2010 Berlin Heidelberg Springer 501\u2013514.","DOI":"10.1007\/978-3-642-19309-5_39"},{"key":"e_1_2_8_13_2","doi-asserted-by":"crossref","unstructured":"BermanD.andAvidanS. Non-local Image dehazing Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA IEEE 1674\u20131682.","DOI":"10.1109\/CVPR.2016.185"},{"key":"e_1_2_8_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/JQE.1978.1069864"},{"key":"e_1_2_8_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.660994"},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.1364\/ao.42.000511"},{"key":"e_1_2_8_17_2","unstructured":"NarasimhanS. G.andNayarS. K. Interactive (de) weathering of an image using physical models Proceedings of the Methods in Computer IEEE Workshop on Color and Photometric Vision October 2003 Nice France IEEE."},{"key":"e_1_2_8_18_2","doi-asserted-by":"crossref","unstructured":"TarelJ. P.andHautiereN. Fast visibility restoration from a single color or gray level image Proceedings of the 2009 IEEE 12th International Conference on Computer Vision September 2009 Kyoto Japan IEEE 2201\u20132208.","DOI":"10.1109\/ICCV.2009.5459251"},{"key":"e_1_2_8_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360671"},{"key":"e_1_2_8_20_2","doi-asserted-by":"crossref","unstructured":"PeiS. C.andLeeT. Y. Nighttime haze removal using color transfer pre-processing and dark channel prior Proceedings of the 2012 19th IEEE International Conference on Image Processing September 2012 Orlando FL USA IEEE 957\u2013960.","DOI":"10.1109\/ICIP.2012.6467020"},{"key":"e_1_2_8_21_2","doi-asserted-by":"crossref","unstructured":"ShuaiY. LiuR. andHeW. Image haze removal of wiener filtering based on dark channel prior Proceedings of the 2012 Eighth International Conference on Computational Intelligence and Security November 2012 Guangzhou China IEEE 318\u2013322.","DOI":"10.1109\/CIS.2012.78"},{"key":"e_1_2_8_22_2","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/6835367"},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2016.2598681"},{"key":"e_1_2_8_24_2","doi-asserted-by":"crossref","unstructured":"RenW. LiuS. andZhangH. Single image dehazing via multiscale convolutional neural networks Proceedings of the European Conference on Computer Vision October 2016 Amsterdam The Netherlands Springer 154\u2013169.","DOI":"10.1007\/978-3-319-46475-6_10"},{"key":"e_1_2_8_25_2","unstructured":"ZhangX. DongH. andHuZ. Gated fusion network for joint image deblurring and super-resolution 2018 https:\/\/arxiv.org\/abs\/1807.10806."},{"key":"e_1_2_8_26_2","unstructured":"GoodfellowI. Pouget-AbadieJ. andMirzaM. Generative adversarial nets Proceedings of the Advances in Neural Information Processing Systems December 2014 Montreal Canada 2672\u20132680."},{"key":"e_1_2_8_27_2","unstructured":"RadfordA. MetzL. andChintalaS. Unsupervised representation learning with deep convolutional generative adversarial networks 2015 https:\/\/arxiv.org\/abs\/1511.06434."},{"key":"e_1_2_8_28_2","unstructured":"MirzaM.andOsinderoS. Conditional generative adversarial nets 2014 https:\/\/arxiv.org\/abs\/1411.1784."},{"key":"e_1_2_8_29_2","doi-asserted-by":"crossref","unstructured":"IsolaP. ZhuJ. Y. andZhouT. Image-to-image translation with conditional adversarial networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA IEEE 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_8_30_2","doi-asserted-by":"crossref","unstructured":"ZhuJ. Y. ParkT. andIsolaP. Unpaired image-to-image translation using cycle-consistent adversarial networks Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy IEEE 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_8_31_2","unstructured":"SimonyanK.andZissermanA. Very deep convolutional networks for large-scale image recognition 2014 https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_8_32_2","unstructured":"KlambauerG. UnterthinerT. andMayrA. Self-normalizing neural networks Proceedings of the Advances in neural Information Processing Systems December 2017 Long Beach CA USA IEEE 971\u2013980."},{"key":"e_1_2_8_33_2","unstructured":"MiyatoT. KataokaT. andKoyamaM. Spectral normalization for generative adversarial networks 2018 https:\/\/arxiv.org\/abs\/1802.05957."},{"key":"e_1_2_8_34_2","unstructured":"Martin ArjovskyS. C.andBottouL. Wasserstein generative adversarial networks Proceedings of the 34 th International Conference on Machine Learning August 2017 Sydney Australia."},{"key":"e_1_2_8_35_2","unstructured":"MaasA. L. HannunA. Y. andNgA. Y. Rectifier nonlinearities improve neural network acoustic models Proceedings of the International Conference on Machine Learning June 2013 Atlanta GA USA."},{"key":"e_1_2_8_36_2","unstructured":"YoshidaY.andMiyatoT. Spectral norm regularization for improving the generalizability of deep learning Proceedings of the International Conference on Neural Information Processing Systems December 2018 Montreal Canada 1539\u20131550."},{"key":"e_1_2_8_37_2","unstructured":"SedghiH. GuptaV. andLongP. M. The singular values of convolutional layers 2018 https:\/\/arxiv.org\/abs\/1805.10408."},{"key":"e_1_2_8_38_2","unstructured":"GulrajaniI. AhmedF. andArjovskyM. Improved training of wasserstein gans Proceedings of the Advances in neural Information Processing Systems December 2017 Long Beach CA USA 5767\u20135777."},{"key":"e_1_2_8_39_2","unstructured":"AbadiM. BarhamP. andChenJ. Tensorflow: a system for large-scale machine learning Proceedings of the 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16) July 2016 Carlsbad CA USA 265\u2013283."},{"key":"e_1_2_8_40_2","unstructured":"ZeilerM. D. Adadelta: an adaptive learning rate method 2012 https:\/\/arxiv.org\/abs\/1212.5701."},{"key":"e_1_2_8_41_2","doi-asserted-by":"crossref","unstructured":"AncutiC. O. AncutiC. TimofteR. andDe VleeschouwerC. I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images 2018 https:\/\/arxiv.org\/abs\/1804.05091.","DOI":"10.1109\/CVPRW.2018.00119"},{"key":"e_1_2_8_42_2","doi-asserted-by":"crossref","unstructured":"AncutiC. O. AncutiC. andTimofteR. O-haze: a dehazing benchmark with real hazy and haze-free outdoor images in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops June 2018 Salt Lake City UT USA IEEE 754\u2013762.","DOI":"10.1109\/CVPRW.2018.00119"},{"key":"e_1_2_8_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867951"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/2352185.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/2352185.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/2352185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T21:52:22Z","timestamp":1723240342000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/2352185"}},"subtitle":[],"editor":[{"given":"Zhijie","family":"Wang","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/2352185"],"URL":"https:\/\/doi.org\/10.1155\/2021\/2352185","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-07-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2352185"}}