{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T03:43:49Z","timestamp":1775101429813,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Research and Development Plan Projects of Shaanxi Province","award":["2022ZDLGY01-05"],"award-info":[{"award-number":["2022ZDLGY01-05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Images obtained in an unfavorable environment may be affected by haze or fog, leading to fuzzy image details, low contrast, and loss of important information. Recently, significant progress has been achieved in the realm of image dehazing, largely due to the adoption of deep learning techniques. Owing to the lack of modules specifically designed to learn the unique characteristics of haze, existing deep neural network-based methods are impractical for processing images containing haze. In addition, most networks primarily focus on learning clear image information while disregarding potential features in hazy images. To address these limitations, we propose an innovative method called contrastive multiscale transformer for image dehazing (CMT-Net). This method uses the multiscale transformer to enable the network to learn global hazy features at multiple scales. Furthermore, we introduce feature combination attention and a haze-aware module to enhance the network\u2019s ability to handle varying concentrations of haze by assigning more weight to regions containing haze. Finally, we design a multistage contrastive learning loss incorporating different positive and negative samples at various stages to guide the network\u2019s learning process to restore real and non-hazy images. The experimental findings demonstrate that CMT-Net provides exceptional performance on established datasets and exhibits superior visual outcomes.<\/jats:p>","DOI":"10.3390\/s24072041","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T12:32:36Z","timestamp":1711369956000},"page":"2041","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Contrastive Multiscale Transformer for Image Dehazing"],"prefix":"10.3390","volume":"24","author":[{"given":"Jiawei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2348-0532","authenticated-orcid":false,"given":"Guanghui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Hecker, S., and Van Gool, L. (2018, January 8\u201314). Model adaptation with synthetic and real data for semantic dense foggy scene understanding. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01261-8_42"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1016\/j.ijleo.2015.10.080","article-title":"Real time image and video deweathering: The future prospects and possibilities","volume":"127","author":"Kumari","year":"2016","journal-title":"Optik"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., and Geiger, A. (2021, January 25). Multi-modal fusion transformer for end-to-end autonomous driving. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref_5","unstructured":"McCartney, E.J. (1976). Optics of the Atmosphere: Scattering by Molecules and Particles, John Wiley and Sons, Inc. ."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nayar, S.K., and Narasimhan, S.G. (1999, January 25). Vision in bad weather. Proceedings of the Seventh IEEE International Conference on Computer Vision, Corfu, Greece.","DOI":"10.1109\/ICCV.1999.790306"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1016328200723","article-title":"Vision and the atmosphere","volume":"48","author":"Narasimhan","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref_8","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1109\/TPAMI.2018.2882478","article-title":"Single image dehazing using haze-lines","volume":"42","author":"Berman","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9043","DOI":"10.1109\/TIP.2021.3122088","article-title":"IDRLP: Image dehazing using region line prior","volume":"30","author":"Ju","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhao, X. (2021, January 25). Single image dehazing using bounded channel difference prior. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPRW53098.2021.00082"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9270","DOI":"10.1109\/TIP.2021.3123551","article-title":"Multi-scale single image dehazing using Laplacian and Gaussian pyramids","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5187","DOI":"10.1109\/TIP.2016.2598681","article-title":"Dehazenet: An end-to-end system for single image haze removal","volume":"25","author":"Cai","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"17081","DOI":"10.1007\/s11042-015-2977-7","article-title":"Single image dehazing through improved atmospheric light estimation","volume":"75","author":"Lu","year":"2016","journal-title":"Multimed. Tools Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Patel, V.M. (2018, January 18\u201323). Densely connected pyramid dehazing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00337"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017, January 22\u201329). Aod-net: All-in-one dehazing network. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.511"},{"key":"ref_17","first-page":"11487","article-title":"Learning to dehaze with polarization","volume":"34","author":"Zhou","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dong, J., and Pan, J. (2020, January 23\u201328). Physics-based feature dehazing networks. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK.","DOI":"10.1007\/978-3-030-58577-8_12"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, R., Pan, J., Li, Z., and Tang, J. (2018, January 18\u201323). Single image dehazing via conditional generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00856"},{"key":"ref_20","unstructured":"Liu, X., Ma, Y., Shi, Z., and Chen, J. (November, January 27). Griddehazenet: Attention-based multi-scale network for image dehazing. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_21","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.1109\/TIP.2023.3256763","article-title":"Vision transformers for single image dehazing","volume":"32","author":"Song","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3888","DOI":"10.1109\/TIP.2015.2456502","article-title":"Referenceless prediction of perceptual fog density and perceptual image defogging","volume":"24","author":"Choi","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2651362","article-title":"Dehazing using color-lines","volume":"34","author":"Fattal","year":"2014","journal-title":"ACM Trans. Graph."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tan, R.T. (2008, January 24\u201326). Visibility in bad weather from a single image. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587643"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1360612.1360671","article-title":"Single image dehazing","volume":"27","author":"Fattal","year":"2008","journal-title":"ACM Trans. Graph."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhou, J., and Zhou, F. (2013, January 23\u201324). Single image dehazing motivated by Retinex theory. Proceedings of the 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA), Toronto, ON, Canada.","DOI":"10.1109\/IMSNA.2013.6743260"},{"key":"ref_28","unstructured":"Zhang, Q., and Li, X. (2015, January 18\u201321). Fast image dehazing using guided filter. Proceedings of the 2015 IEEE 16th International Conference on Communication Technology (ICCT), Hangzhou, China."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.1109\/TCSVT.2017.2728822","article-title":"Single image dehazing based on the physical model and MSRCR algorithm","volume":"28","author":"Wang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3927","DOI":"10.1109\/TIP.2020.2965294","article-title":"Efficient and fast real-world noisy image denoising by combining pyramid neural network and two-pathway unscented Kalman filter","volume":"29","author":"Ma","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., and Yang, M.-H. (2016, January 11\u201314). Single image dehazing via multi-scale convolutional neural networks. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_10"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, D., He, M., Fan, Q., Liao, J., Zhang, L., Hou, D., Yuan, L., and Hua, G. (2019, January 7\u201311). Gated context aggregation network for image dehazing and deraining. Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA.","DOI":"10.1109\/WACV.2019.00151"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, January 7\u201312). FFA-Net: Feature Fusion Attention Network for Single Image Dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., and Li, Y. (2022, January 24). Maxim: Multi-axis mlp for image processing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00568"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, Y., Pan, J., Ren, J., and Su, Z. (2019, January 28). Learning deep priors for image dehazing. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00258"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shao, Y., Li, L., Ren, W., Gao, C., and Sang, N. (2020, January 13\u201319). Domain adaptation for image dehazing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00288"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"11187","DOI":"10.1109\/TCYB.2021.3070310","article-title":"Hierarchical density-aware dehazing network","volume":"52","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/TCYB.2021.3124231","article-title":"Semantic-aware dehazing network with adaptive feature fusion","volume":"53","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., and Yang, M.-H. (2020, January 13\u201319). Multi-scale boosted dehazing network with dense feature fusion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, Y., Yang, Y., and Liu, D. (2021, January 20\u201325). PSD: Principled synthetic-to-real dehazing guided by physical priors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00710"},{"key":"ref_41","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhan, J., He, S., Dong, J., and Du, Y. (2023, January 17\u201324). Curricular contrastive regularization for physics-aware single image dehazing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00560"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3391","DOI":"10.1109\/TIP.2021.3060873","article-title":"RefineDNet: A weakly supervised refinement framework for single image dehazing","volume":"30","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/TIP.2019.2952032","article-title":"Unsupervised single image dehazing using dark channel prior loss","volume":"29","author":"Golts","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., and Li, H. (2022, January 18\u201324). Uformer: A general u-shaped transformer for image restoration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_47","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., and Unterthiner, T. (2020). Transformers for image recognition at scale. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wu, H., Qu, Y., Lin, S., Zhou, J., Qiao, R., Zhang, Z., Xie, Y., and Ma, L. (2021, January 19\u201325). Contrastive learning for compact single image dehazing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 14\u201319). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_52","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1109\/TIP.2018.2867951","article-title":"Benchmarking single-image dehazing and beyond","volume":"28","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Ancuti, C.O., Ancuti, C., and Timofte, R. (2020, January 14\u201319). NH-HAZE: An image dehazing benchmark with non-homogeneous hazy and haze-free images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00230"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"2879","DOI":"10.1109\/TITS.2018.2868771","article-title":"Objective quality evaluation of dehazed images","volume":"20","author":"Min","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind\u201d image quality analyzer","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/7\/2041\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:18:20Z","timestamp":1760105900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/7\/2041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":57,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["s24072041"],"URL":"https:\/\/doi.org\/10.3390\/s24072041","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,22]]}}}