{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:05:44Z","timestamp":1753891544534,"version":"3.41.2"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The seriously degraded fogging image affects the further visual tasks. How to obtain a fog-free image is not only challenging, but also important in computer vision. Recently, the vision transformer (ViT) architecture has achieved very efficient performance in several vision areas.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this paper, we propose a new transformer-based progressive residual network. Different from the existing single-stage ViT architecture, we recursively call the progressive residual network with the introduction of swin transformer. Specifically, our progressive residual network consists of three main components: the recurrent block, the transformer codecs and the supervise fusion module. First, the recursive block learns the features of the input image, while connecting the original image features of the original iteration. Then, the encoder introduces the swin transformer block to encode the feature representation of the decomposed block, and continuously reduces the feature mapping resolution to extract remote context features. The decoder recursively selects and fuses image features by combining attention mechanism and dense residual blocks. In addition, we add a channel attention mechanism between codecs to focus on the importance of different features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results and discussion<\/jats:title><jats:p>The experimental results show that the performance of this method outperforms state-of-the-art handcrafted and learning-based methods.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2022.1084543","type":"journal-article","created":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T16:58:18Z","timestamp":1670345898000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Transformer-based progressive residual network for single image dehazing"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhe","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,12,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1016\/j.patrec.2020.09.010","article-title":"COVID-caps: a capsule network-based framework for identification of COVID-19 cases from x-ray images","volume":"138","author":"Afshar","year":"2020","journal-title":"Pattern Recognit Lett"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.11178","article-title":"Vatt: transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021","journal-title":"arXiv preprint arXiv:2104.11178"},{"key":"B3","first-page":"754","article-title":"\u201cO-haze: a dehazing benchmark with real hazy and haze-free outdoor images,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Ancuti","year":"2018"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.06632","article-title":"Dehaze-glcgan: unpaired single image de-hazing via adversarial training","author":"Anvari","year":"2020","journal-title":"arXiv preprint arXiv:2008.06632"},{"key":"B5","first-page":"1674","article-title":"\u201cNon-local image dehazing,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Berman","year":"2016"},{"key":"B6","doi-asserted-by":"publisher","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":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-021-01173-x","article-title":"Dcnet: dark channel network for single-image dehazing","volume":"32","author":"Bhola","year":"2021","journal-title":"Mach. Vis. Appl"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.05537","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv preprint arXiv:2105.05537"},{"key":"B9","first-page":"213","article-title":"\u201cEnd-to-end object detection with transformers,\u201d","volume-title":"European Conference on Computer Vision","author":"Carion","year":"2020"},{"key":"B10","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/ICIP.1994.413553","article-title":"\u201cTwo deterministic half-quadratic regularization algorithms for computed imaging,\u201d","volume-title":"Proceedings of 1st International Conference on Image Processing, Vol. 2","author":"Charbonnier","year":"1994"},{"key":"B11","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1109\/WACV.2019.00151","article-title":"\u201cGated context aggregation network for image dehazing and deraining,\u201d","volume-title":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Chen","year":"2019"},{"key":"B12","first-page":"12299","article-title":"\u201cPre-trained image processing transformer,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":""},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306","article-title":"Transunet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"","journal-title":"arXiv preprint arXiv:2102.04306"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6773","DOI":"10.1109\/TIP.2020.2993407","article-title":"Pmhld: patch map-based hybrid learning dehazenet for single image haze removal","volume":"29","author":"Chen","year":"2020","journal-title":"IEEE Trans. Image Process"},{"key":"B15","doi-asserted-by":"publisher","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":"B16","first-page":"2157","article-title":"\u201cMulti-scale boosted dehazing network with dense feature fusion,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Dong","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4885","DOI":"10.1109\/TIP.2020.2976814","article-title":"Blind universal bayesian image denoising with gaussian noise level learning","volume":"29","author":"El Helou","year":"2020","journal-title":"IEEE Trans. Image Process"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.113","article-title":"Congested crowd instance localization with dilated convolutional swin transformer","author":"Gao","year":"2021","journal-title":"arXiv preprint arXiv:2108.00584"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","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":"B21","first-page":"17","article-title":"\u201cHand-transformer: non-autoregressive structured modeling for 3D hand pose estimation,\u201d","volume-title":"European Conference on Computer Vision","author":"Huang","year":""},{"key":"B22","first-page":"3136","article-title":"\u201cHot-net: non-autoregressive transformer for 3D hand-object pose estimation,\u201d","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia","author":"Huang","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.neucom.2020.11.039","article-title":"Self-filtering image dehazing with self-supporting module","volume":"432","author":"Huang","year":"2021","journal-title":"Neurocomputing"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3189630","article-title":"Underwater image enhancement via adaptive group attention-based multiscale cascade transformer","volume":"71","author":"Huang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.01701","article-title":"Transmission map and atmospheric light guided iterative updater network for single image dehazing","author":"Kar","year":"2020","journal-title":"arXiv preprint arXiv:2008.01701"},{"key":"B26","first-page":"1637","article-title":"\u201cDeeply-recursive convolutional network for image super-resolution,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kim","year":"2016"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"B28","doi-asserted-by":"publisher","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":"B29","doi-asserted-by":"publisher","first-page":"4227","DOI":"10.1109\/TCSVT.2021.3049940","article-title":"Low-light image enhancement via progressive-recursive network","volume":"31","author":"Li","year":"2021","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210","article-title":"Swinir: image restoration using swin transformer","author":"Liang","year":"2021","journal-title":"arXiv preprint arXiv:2108.10257"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3178991","article-title":"Ds-transunet: dual swin transformer u-net for medical image segmentation","author":"Lin","year":"","journal-title":"arXiv preprint arXiv:2106.06716"},{"key":"B32","first-page":"1954","article-title":"\u201cEnd-to-end human pose and mesh reconstruction with transformers,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lin","year":""},{"key":"B33","first-page":"430","article-title":"\u201cTrident dehazing network,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Liu","year":""},{"key":"B34","doi-asserted-by":"publisher","first-page":"6204","DOI":"10.3390\/s20216204","article-title":"An efficient residual-based method for railway image dehazing","volume":"20","author":"Liu","year":"","journal-title":"Sensors"},{"key":"B35","first-page":"7314","article-title":"\u201cGriddehazenet: Attention-based multi-scale network for image dehazing,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Liu","year":"2019"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"arXiv preprint arXiv:2103.14030"},{"volume-title":"Vision Through the Atmosphere","year":"2019","author":"Middleton","key":"B37"},{"key":"B38","doi-asserted-by":"publisher","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"},{"key":"B39","first-page":"4055","article-title":"\u201cImage transformer,\u201d","volume-title":"International Conference on Machine Learning","author":"Parmar","year":"2018"},{"key":"B40","first-page":"11908","article-title":"\u201cFfa-net: Feature fusion attention network for single image dehazing,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34","author":"Qin","year":"2020"},{"key":"B41","first-page":"3937","article-title":"\u201cProgressive image deraining networks: a better and simpler baseline,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ren","year":"2019"},{"key":"B42","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/s11263-019-01235-8","article-title":"Single image dehazing via multi-scale convolutional neural networks with holistic edges","volume":"128","author":"Ren","year":"2020","journal-title":"Int. J. Comput. Vis"},{"key":"B43","first-page":"5998","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B44","doi-asserted-by":"crossref","first-page":"2517","DOI":"10.1145\/3394171.3413559","article-title":"\u201cJoint self-attention and scale-aggregation for self-calibrated deraining network,\u201d","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia","author":"Wang","year":"2020"},{"key":"B45","doi-asserted-by":"publisher","first-page":"033026","DOI":"10.1117\/1.JEI.30.3.033026","article-title":"Rgnam: recurrent grid network with an attention mechanism for single-image dehazing","volume":"30","author":"Wang","year":"2021","journal-title":"J. Electron. Imaging"},{"key":"B46","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.03677","article-title":"Visual transformers: token-based image representation and processing for computer vision","author":"Wu","year":"2020","journal-title":"arXiv preprint arXiv:2006.03677"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.04553","article-title":"Self-supervised learning with swin transformers","author":"Xie","year":"2021","journal-title":"arXiv preprint arXiv:2105.04553"},{"key":"B49","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1145\/3377713.3377722","article-title":"\u201cA comparison between arima, lstm, and gru for time series forecasting,\u201d","volume-title":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","author":"Yamak","year":"2019"},{"key":"B50","doi-asserted-by":"publisher","first-page":"25431","DOI":"10.1109\/ACCESS.2020.2971092","article-title":"Mmp-net: a multi-scale feature multiple parallel fusion network for single image haze removal","volume":"8","author":"Yan","year":"2020","journal-title":"IEEE Access"},{"key":"B51","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.1109\/TIP.2019.2957929","article-title":"Multi-scale deep residual learning-based single image haze removal via image decomposition","volume":"29","author":"Yeh","year":"2019","journal-title":"IEEE Trans. Image Process"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044","article-title":"Vision transformer with progressive sampling","author":"Yue","year":"2021","journal-title":"arXiv preprint arXiv:2108.01684"},{"key":"B53","first-page":"14821","article-title":"\u201cMulti-stage progressive image restoration,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zamir","year":"2021"},{"key":"B54","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s41095-021-0246-4","article-title":"Progressive edge-sensing dynamic scene deblurring","volume":"8","author":"Zhang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"B55","first-page":"6881","article-title":"\u201cRethinking semantic segmentation from a sequence-to-sequence perspective with transformers,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheng","year":"2021"},{"key":"B56","doi-asserted-by":"publisher","first-page":"3522","DOI":"10.1109\/TIP.2015.2446191","article-title":"A fast single image haze removal algorithm using color attenuation prior","volume":"24","author":"Zhu","year":"2015","journal-title":"IEEE Trans. Image Process"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.04159","article-title":"Deformable detr: deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv:2010.04159"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1084543\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T16:58:45Z","timestamp":1670345925000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1084543\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":57,"alternative-id":["10.3389\/fnbot.2022.1084543"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2022.1084543","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2022,12,6]]},"article-number":"1084543"}}