{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:25:10Z","timestamp":1771467910836,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T00:00:00Z","timestamp":1681344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Nature Science Foundation of Fujian Province","award":["2022J05113"],"award-info":[{"award-number":["2022J05113"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deployment of deep convolutional neural networks (CNNs) in single image super-resolution (SISR) for edge computing devices is mainly hampered by the huge computational cost. In this work, we propose a lightweight image super-resolution (SR) network based on a reparameterizable multibranch bottleneck module (RMBM). In the training phase, RMBM efficiently extracts high-frequency information by utilizing multibranch structures, including bottleneck residual block (BRB), inverted bottleneck residual block (IBRB), and expand\u2013squeeze convolution block (ESB). In the inference phase, the multibranch structures can be combined into a single 3 \u00d7 3 convolution to reduce the number of parameters without incurring any additional computational cost. Furthermore, a novel peak-structure-edge (PSE) loss is proposed to resolve the problem of oversmoothed reconstructed images while significantly improving image structure similarity. Finally, we optimize and deploy the algorithm on the edge devices equipped with the rockchip neural processor unit (RKNPU) to achieve real-time SR reconstruction. Extensive experiments on natural image datasets and remote sensing image datasets show that our network outperforms advanced lightweight SR networks regarding objective evaluation metrics and subjective vision quality. The reconstruction results demonstrate that the proposed network can achieve higher SR performance with a 98.1 K model size, which can be effectively deployed to edge computing devices.<\/jats:p>","DOI":"10.3390\/s23083963","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T02:03:38Z","timestamp":1681437818000},"page":"3963","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Reparameterizable Multibranch Bottleneck Network for Lightweight Image Super-Resolution"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1322-1753","authenticated-orcid":false,"given":"Ying","family":"Shen","sequence":"first","affiliation":[{"name":"College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihuang","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., and Lee, K.M. (2016, January 27\u201330). Deeply-recursive convolutional network for image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.181"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Tai, Y., Yang, J., Liu, X., and Xu, C. (2017, January 22\u201329). Memnet: A persistent memory network for image restoration. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.486"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ahn, N., Kang, B., and Sohn, K.A. (2018, January 8\u201314). Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01249-6_16"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, J., Liu, Z., Yang, X., Jeon, G., and Wu, W. (2019, January 16\u201320). Feedback Network for Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00399"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hui, Z., Gao, X., Yang, Y., and Wang, X. (2019, January 21\u201325). Lightweight Image Super-Resolution with Information Multi-distillation Network. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.","DOI":"10.1145\/3343031.3351084"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, J., Tang, J., and Wu, G. (2020, January 23\u201328). Residual Feature Distillation Network for Lightweight Image Super-Resolution. Proceedings of the European Conference on Computer Vision AIM Workshops, Glasgow, UK.","DOI":"10.1007\/978-3-030-67070-2_2"},{"key":"ref_9","unstructured":"Vasu PK, A., Gabriel, J., Zhu, J., Tuzel, O., and Ranjan, A. (2022). An improved one millisecond mobile backbone. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2021, January 19\u201325). Multi-stage progressive image restoration. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ding, X., Guo, Y., Ding, G., and Han, J. (2019, January 16\u201320). Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zeng, H., and Zhang, L. (2021, January 20\u201324). Edge-oriented convolution block for real-time super resolution on mobile devices. Proceedings of the 29th ACM International Conference on Multimedia, Chengdu, China.","DOI":"10.1145\/3474085.3475291"},{"key":"ref_13","first-page":"529","article-title":"Collapsible linear blocks for super-efficient super resolution","volume":"4","author":"Bhardwaj","year":"2022","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lai, W.S., Huang, J.B., Ahuja, N., and Yang, M.H. (2017, January 22\u201325). Deep laplacian pyramid networks for fast and accurate super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.618"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2017, January 21\u201326). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref_16","first-page":"2672","article-title":"Generative adversarial nets","volume":"2","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., He, K., and Tang, X. (2014, January 6\u201312). Learning a deep convolutional network for image super-resolution. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1646","DOI":"10.1109\/CVPR.2016.182","article-title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","volume":"Volume 60","author":"Kim","year":"2016","journal-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (July, January 26). Real-time single image and video super resolution using an efficient subpixel convolutional neural network. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., and Mu Lee, K. (2017, January 21\u201326). Enhanced Deep Residual Networks for Single Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., and Change Loy, C. (2018, January 8\u201314). Esrgan: Enhanced super-resolution generative adversarial networks. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Munich, Germany.","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2480","DOI":"10.1109\/TPAMI.2020.2968521","article-title":"Residual dense network for image restoration","volume":"43","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hui, Z., Wang, X., and Gao, X. (2018, January 18\u201323). Fast and Accurate Single Image Super-Resolution via Information Distillation Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00082"},{"key":"ref_24","first-page":"20343","article-title":"Lapar: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Luo, X., Xie, Y., Zhang, Y., Qu, Y., Li, C., and Fu, Y. (2020, January 23\u201328). LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58542-6_17"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 19\u201325). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref_27","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., and Ding, G. (2021, January 19\u201325). Diverse branch block: Building a convolution as an inception-like unit. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"ref_29","unstructured":"Justin, J., Alexandre, A., and Li, F.-F. (2016, January 11\u201314). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhao, L., Liu, L., Hu, H., and Tao, W. (2021). URNet: A U-Shaped Residual Network for Lightweight Image Super-Resolution. Remote Sens., 13.","DOI":"10.3390\/rs13193848"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 11\u201318). Delving deep into rectifiers: Surpassing human level performance on ImageNet classification. Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cai, Y., Gao, G., Jia, Z., and Lai, H. (2022). Image Reconstruction of Multibranch Feature Multiplexing Fusion Network with Mixed Multilayer Attention. Remote Sens., 14.","DOI":"10.3390\/rs14092029"},{"key":"ref_33","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, L., Lu, X., Zhang, J., Chu, X., and Chen, C. (2021, January 19\u201325). Hinet: Half instance normalization network for image restoration. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPRW53098.2021.00027"},{"key":"ref_35","unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1049\/el:20080522","article-title":"Scope of validity of PSNR in image\/video quality assessment","volume":"44","author":"Ghanbari","year":"2008","journal-title":"Electron. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Hore, A., and Ziou, D. (2010, January 23\u201326). Image quality metrics: PSNR vs. SSIM. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Jiang, K., Wang, Z., Yi, P., Chen, C., Huang, B., Luo, Y., and Jiang, J. (2020, January 14\u201319). Multi-scale progressive fusion network for single image deraining. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00837"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Timofte, R., Agustsson, E., Van Gool, L., Yang, M.H., and Zhang, L. (2017, January 21\u201326). Ntire 2017 challenge on single image super-resolution: Methods and results. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, J., Wang, J., Chen, Q., Cao, J., Deng, Z., and Tan, M. (2020, January 14\u201319). Closed-loop matters: Dual regression networks for single image super-resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00545"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Bevilacqua, M., Roumy, A., Guillemot, C., and Alberi-Morel, M.L. (2012, January 3\u20137). Low-complexity single-image super-resolution based on nonnegative neighbor embedding. Proceedings of the 2012 British Machine Vision Conference, Surrey, UK.","DOI":"10.5244\/C.26.135"},{"key":"ref_42","unstructured":"Zeyde, R., Elad, M., and Protter, M. (2010, January 23\u201324). On single image scale-up using sparse-representations. Proceedings of the International Conference on Curves and Surfaces, Avignon, France."},{"key":"ref_43","doi-asserted-by":"crossref","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":"ref_44","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1109\/TIP.2009.2018014","article-title":"Image quality assessment based on multiscale geometric analysis","volume":"18","author":"Gao","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"ref_45","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., and Tang, X. (2016, January 11\u201314). Accelerating the super-resolution convolutional neural network. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Chu, X., Zhang, B., Ma, H., Xu, R., and Li, Q. (2021, January 10\u201315). Fast, accurate and lightweight super-resolution with neural architecture search. Proceedings of the 2020 25th International Conference on Pattern Recognition, Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9413080"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhao, L., Li, J., Zhao, H., Liu, W., Li, Y., Wang, Y., Chen, H., and Cao, W. (2021). Saliency-Guided Remote Sensing Image Super-Resolution. Remote Sens., 13.","DOI":"10.3390\/rs13245144"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Yang, Y., and Newsam, S. (2010, January 2\u20135). Bag-of-visual-words and spatial extensions for land-use classification. Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose, CA, USA.","DOI":"10.1145\/1869790.1869829"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote sensing image scene classification: Benchmark and state of the art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","article-title":"AID: A benchmark data set for performance evaluation of aerial scene classification","volume":"55","author":"Xia","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3963\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:15:44Z","timestamp":1760123744000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3963"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,13]]},"references-count":51,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23083963"],"URL":"https:\/\/doi.org\/10.3390\/s23083963","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,13]]}}}