{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:22:08Z","timestamp":1779888128932,"version":"3.53.1"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Aiming at the problems of traditional image super-resolution reconstruction algorithms in the image reconstruction process, such as small receptive field, insufficient multi-scale feature extraction, and easy loss of image feature information, a super-resolution reconstruction algorithm of multi-scale dilated convolution network based on dilated convolution is proposed in this paper. First, the algorithm extracts features from the same input image through the dilated convolution kernels of different receptive fields to obtain feature maps with different scales; then, through the residual attention dense block, further obtain the features of the original low resolution images, local residual connections are added to fuse multi-scale feature information between multiple channels, and residual nested networks and jump connections are used at the same time to speed up deep network convergence and avoid network degradation problems. Finally, deep network extraction features, and it is fused with input features to increase the nonlinear expression ability of the network to enhance the super-resolution reconstruction effect. Experimental results show that compared with Bicubic, SRCNN, ESPCN, VDSR, DRCN, LapSRN, MemNet, and DSRNet algorithms on the Set5, Set14, BSDS100, and Urban100 test sets, the proposed algorithm has improved peak signal-to-noise ratio and structural similarity, and reconstructed images. The visual effect is better.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1436052","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T12:55:20Z","timestamp":1723812920000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["The super-resolution reconstruction algorithm of multi-scale dilated convolution residual network"],"prefix":"10.3389","volume":"18","author":[{"given":"Shanqin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengjun","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","article-title":"Contour detection and hierarchical image segmentation","volume":"33","author":"Arbelaez","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Chao","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"184","DOI":"10.48550\/arXiv.1412.7062","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"Chen","year":"2014","journal-title":"arXiv"},{"key":"ref4","author":"Dong","year":"2014"},{"key":"ref5","author":"Fei","year":"2007"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10489-022-03625-x","article-title":"Image super-resolution reconstruction based on instance spatial feature modulation and feedback mechanism","volume":"53","author":"Fu","year":"2023","journal-title":"Appl. Intell."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TIP.2023.3240845","article-title":"Semi-cycled generative adversarial networks for real-world face super-resolution","volume":"32","author":"Hou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref8","author":"Huang","year":"2015"},{"key":"ref9","author":"Kim","year":"2016"},{"key":"ref10","author":"Kingma","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2150","DOI":"10.1109\/TIP.2019.2945835","article-title":"Face hallucination using cascaded super-resolution and identity priors","volume":"29","author":"Klemen","year":"2020","journal-title":"IEEE Trans. Image Proces. Publ. IEEE Signal Proces. Soc."},{"key":"ref12","author":"Lai","year":"2017"},{"key":"ref13","author":"Ledig","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2182487","DOI":"10.1080\/09540091.2023.2182487","article-title":"Image super-resolution reconstruction based on multi-scale dual-attention","volume":"35","author":"Li","year":"2023","journal-title":"Connect. Sci."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/978-3-030-01237-3_32","article-title":"Multi-scale residual network for image super-resolution","author":"Li","year":"2018","journal-title":"Proc. European Conf. Comp. Vision (ECCV)"},{"key":"ref17","author":"Lim","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"991","DOI":"10.11834\/jig.200265","article-title":"Lightweight image super-resolution network based on two-stage information distillation","volume":"26","author":"Li","year":"2021","journal-title":"J. Image Graph."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3264459","article-title":"D 2 UNet: dual decoder U-net for seismic image super-resolution reconstruction","volume":"61","author":"Min","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"107590","DOI":"10.1016\/j.cmpb.2023.107590","article-title":"Medical image super-resolution reconstruction algorithms based on deep learning: a survey","volume":"238","author":"Qiu","year":"2023","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref20","author":"Tai","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1049\/cit2.12297","article-title":"Image super-resolution via dynamic network","volume":"8","author":"Tian","year":"2023","journal-title":"CAAI Trans. Intel. Technol."},{"key":"ref22","author":"Timofte","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1364\/OL.479074","article-title":"Learning-based single-shot long-range synthetic aperture Fourier ptychographic imaging with a camera array","volume":"48","author":"Wang","year":"2023","journal-title":"Opt. Lett."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.ins.2022.11.140","article-title":"A novel fuzzy hierarchical fusion attention convolution neural network for medical image super-resolution reconstruction","volume":"622","author":"Wang","year":"2023","journal-title":"Inf. Sci."},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","first-page":"075403","DOI":"10.1088\/1361-6501\/accbdd","article-title":"Multi-image hybrid super-resolution reconstruction via interpolation and multi-scale residual networks","volume":"34","author":"Wu","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"3490","DOI":"10.3390\/rs15143490","article-title":"IESRGAN: enhanced U-net structured generative adversarial network for remote sensing image super-resolution reconstruction","volume":"15","author":"Yue","year":"2023","journal-title":"Remote Sens."},{"key":"ref28","author":"Zeyde","year":"2010"},{"key":"ref32","first-page":"1","article-title":"Multi morphological sparse regularized image super-resolution reconstruction based on machine learning algorithm","volume":"53","author":"Zhang","year":"2023","journal-title":"IAENG Int. J. Appl. Math."},{"key":"ref29","author":"Zhang","year":"2020"},{"key":"ref30","author":"Zhang","year":"2018"},{"key":"ref31","author":"Zhang","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.3390\/rs15051391","article-title":"SA-GAN: a second order attention generator adversarial network with region aware strategy for real satellite images super resolution reconstruction","volume":"15","author":"Zhao","year":"2023","journal-title":"Remote Sens."},{"key":"ref34","first-page":"1","article-title":"Image super-resolution reconstruction based on feature fusion attention network","volume":"42","author":"Zhou","year":"2021","journal-title":"Acta Automat. Sin."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1436052\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T12:55:25Z","timestamp":1723812925000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1436052\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":34,"alternative-id":["10.3389\/fnbot.2024.1436052"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1436052","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"article-number":"1436052"}}