{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T18:11:29Z","timestamp":1781115089738,"version":"3.54.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:00:00Z","timestamp":1690416000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:00:00Z","timestamp":1690416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2023,11]]},"abstract":"Abstract<\/jats:title>\n \n Aiming at the problems of color bias and noise enhancement on the output image by the traditional low-light image enhancement algorithm, we propose a deep multi-scale pyramid hybrid network (DMPH-Net) algorithm that fuses attention mechanism and multi-scale pyramid is proposed in this paper. The algorithm uses DecomNet to decompose reflectance and light components, and uses multi-scale illumination attention module to fuse light and reflectance for the decomposed low-light reflectance to improve the realism and details of reflectance; by using five-layer feature pyramid and kernel selection in PRID-net module to achieve the fusion of contextual information between different scale feature layers, while effectively removing the enhanced of noise, and the added color loss effectively suppresses the color bias of the output image; using multi-scale cascading and channel attention mechanisms to adjust the illumination and fuse the illumination ratios, effectively enhancing the brightness, texture, and other feature information in the image. The DMPH-Net algorithm is experimentally validated on LOL and no-reference LIME, MEF, and NPE datasets, and the objective evaluation metrics PSNR\n \n \n $$\\uparrow $$<\/jats:tex-math>\n \n \u2191<\/mml:mo>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , SSIM\n \n \n $$\\uparrow $$<\/jats:tex-math>\n \n \u2191<\/mml:mo>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , LIPIPS\n \n \n $$\\downarrow $$<\/jats:tex-math>\n \n \u2193<\/mml:mo>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , and NIQE\n \n \n $$\\downarrow $$<\/jats:tex-math>\n \n \u2193<\/mml:mo>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n are 23.3772, 0.8442, 0.1386, and 3.5966 on LOL dataset. The objective evaluation metrics NIQE on the reference-free datasets LIME, NPE, and MEF are 3.0735, 3.1711, and 2.9464, respectively. The experiments show that the DMPH-Net algorithm maintains high image details and textures in image enhancement and denoising, effectively enhances low-light images, and reduces noise and color bias of images. Compared with RUAS, UnRetinex-Net, and other enhancement algorithms, it improves in objective evaluation metrics PSNR, SSIM, LIPIPS, and NIQE.\n <\/jats:p>","DOI":"10.1007\/s11760-023-02687-9","type":"journal-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:01:20Z","timestamp":1690416080000},"page":"4533-4542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["DMPH-Net: a deep multi-scale pyramid hybrid network for low-light image enhancement with attention mechanism and noise reduction"],"prefix":"10.1007","volume":"17","author":[{"given":"Min","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rugang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naihong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,27]]},"reference":[{"key":"2687_CR1","doi-asserted-by":"publisher","DOI":"10.13272\/j.issn.1671-251x.2022080047","author":"ZL Li","year":"2023","unstructured":"Li, Z.L., Cao, W., Hw, Wang: A method for enhancing low light images in coal mines based on noisy retinex model. J. Mine Autom. (2023). https:\/\/doi.org\/10.13272\/j.issn.1671-251x.2022080047","journal-title":"J. Mine Autom."},{"key":"2687_CR2","doi-asserted-by":"publisher","DOI":"10.13199\/j.cnki.cst.2022-1626","author":"ML Wang","year":"2023","unstructured":"Wang, M.L., Zhang, H.: Deep neural network-based image enhancement algorithm for low-illumination images underground mines. Coal Sci. Technol. (2023). https:\/\/doi.org\/10.13199\/j.cnki.cst.2022-1626","journal-title":"Coal Sci. Technol."},{"key":"2687_CR3","unstructured":"Ying, Z., Li, G., Gao, W.: A bio-inspired multi-exposure fusion framework for low-light image enhancement. arXiv:1711.00591. (2017)"},{"issue":"2","key":"2687_CR4","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TIP.2016.2639450","volume":"26","author":"X Guo","year":"2017","unstructured":"Guo, X., Ling, H., Li, Y.: Lime: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982\u2013993 (2017). https:\/\/doi.org\/10.1109\/TIP.2016.2639450","journal-title":"IEEE Trans. Image Process."},{"key":"2687_CR5","doi-asserted-by":"publisher","unstructured":"Fu, X., Huang, Y., Zeng, D.: A weighted variational model for simultaneous reflectance and illumination estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2782\u20132790 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.304","DOI":"10.1109\/CVPR.2016.304"},{"key":"2687_CR6","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patrec.2018.01.010","volume":"104","author":"C Li","year":"2018","unstructured":"Li, C., Porikli, F., Guo, J.: Lightennet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recognit. Lett. 104, 15\u201322 (2018). https:\/\/doi.org\/10.1016\/j.patrec.2018.01.010","journal-title":"Pattern Recognit. Lett."},{"key":"2687_CR7","doi-asserted-by":"publisher","unstructured":"Wang, W., Yang, W., Chen, W.: Gladnet: low-light enhancement network with global awareness. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 751\u2013755 (2018). https:\/\/doi.org\/10.1109\/FG.2018.00118","DOI":"10.1109\/FG.2018.00118"},{"key":"2687_CR8","unstructured":"Chen, W., Yang, W.H., Wang, W.J.: Deep retinex decomposition for low-light enhancement. In: Proceedings of British Machine Vision Conference. arXiv:1808.04560"},{"key":"2687_CR9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350926","volume-title":"Kindling the Darkness: a Practical Low-Light Image Enhancer","author":"YH Zhang","year":"2019","unstructured":"Zhang, Y.H., Zhang, J.W., Guo, X.: Kindling the Darkness: a Practical Low-Light Image Enhancer. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3343031.3350926"},{"issue":"2","key":"2687_CR10","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s11263-020-01407-x","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Ma, J., Guo, X.: Beyond brightening low-light images. Int. J. Comput. Vis. 129(2), 1013\u20131037 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"2687_CR11","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhang, P., Weng, J.: Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5901\u20135910 (2022)","DOI":"10.1109\/CVPR52688.2022.00581"},{"key":"2687_CR12","doi-asserted-by":"crossref","unstructured":"Ronneberger, O, Brox, T., Fischer, P.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, pp. 234\u2013241. Springer, Cham (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2687_CR13","doi-asserted-by":"publisher","first-page":"8339","DOI":"10.1109\/TIP.2020.3014721","volume":"29","author":"Y Makinen","year":"2020","unstructured":"Makinen, Y., Foi, A., Azzari, L.: Collaborative filtering of correlated noise: exact transform-domain variance for improved shrinkage and patch matching. IEEE Trans. Image Process. 29, 8339\u20138354 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"2687_CR14","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Men, A., Jiang, Z.: Pyramid real image denoising network. In: 2019 IEEE Visual Communications and Image Processing (VCIP), pp. 1\u20134 (2019). https:\/\/doi.org\/10.1109\/VCIP47243.2019.8965754","DOI":"10.1109\/VCIP47243.2019.8965754"},{"key":"2687_CR15","doi-asserted-by":"publisher","first-page":"2340","DOI":"10.1109\/TIP.2021.3051462","volume":"30","author":"Y Jiang","year":"2021","unstructured":"Jiang, Y., Liu, D., Gong, X.: Enlightengan: deep light enhancement without paired supervision. IEEE Trans. Image Process. 30, 2340\u20132349 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3051462","journal-title":"IEEE Trans. Image Process."},{"key":"2687_CR16","doi-asserted-by":"publisher","unstructured":"Guo, C., Guo, J., Li, C.: Zero-reference deep curve estimation for low-light image enhancement. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1777\u20131786 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00185","DOI":"10.1109\/CVPR42600.2020.00185"},{"key":"2687_CR17","unstructured":"Zhang, Y., Zhang, B., Di, X.: Self-supervised image enhancement network: training with low light images only. arXiv:2002.11300 (2020)"},{"key":"2687_CR18","doi-asserted-by":"publisher","unstructured":"Liu, R., Zhang, J., Ma, L.: Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10556\u201310565 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01042","DOI":"10.1109\/CVPR46437.2021.01042"},{"key":"2687_CR19","doi-asserted-by":"publisher","unstructured":"Ma, L., Liu, R., Ma, T.: Toward fast, flexible, and robust low-light image enhancement. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5627\u20135636 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00555","DOI":"10.1109\/CVPR52688.2022.00555"},{"key":"2687_CR20","doi-asserted-by":"publisher","unstructured":"Rahman, Z., Pu, Y.F., Aamir, M.: A smart system for low-light image enhancement with color constancy and detail manipulation in complex light environments. Symmetry-Basel (2018). https:\/\/doi.org\/10.3390\/sym10120718","DOI":"10.3390\/sym10120718"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02687-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-023-02687-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02687-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T14:20:35Z","timestamp":1694528435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-023-02687-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,27]]},"references-count":20,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["2687"],"URL":"https:\/\/doi.org\/10.1007\/s11760-023-02687-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2946470\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,27]]},"assertion":[{"value":"17 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaratons"}},{"value":"There is no conflict of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}