{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:14:39Z","timestamp":1773249279185,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T00:00:00Z","timestamp":1604448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T00:00:00Z","timestamp":1604448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["51775215"],"award-info":[{"award-number":["51775215"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, a novel multi-exposure image fusion method based on generative adversarial networks (termed as GANFuse) is presented. Conventional multi-exposure image fusion methods improve their fusion performance by designing sophisticated activity-level measurement and fusion rules. However, these methods have a limited success in complex fusion tasks. Inspired by the recent FusionGAN which firstly utilizes generative adversarial networks (GAN) to fuse infrared and visible images and achieves promising performance, we improve its architecture and customize it in the task of extreme exposure image fusion. To be specific, in order to keep content of extreme exposure image pairs in the fused image, we increase the number of discriminators differentiating between fused image and extreme exposure image pairs. While, a generator network is trained to generate fused images. Through the adversarial relationship between generator and discriminators, the fused image will contain more information from extreme exposure image pairs. Thus, this relationship can realize better performance of fusion. In addition, the method we proposed is an end-to-end and unsupervised learning model, which can avoid designing hand-crafted features and does not require a number of ground truth images for training. We conduct qualitative and quantitative experiments on a public dataset, and the experimental result shows that the proposed model demonstrates better fusion ability than existing multi-exposure image fusion methods in both visual effect and evaluation metrics.<\/jats:p>","DOI":"10.1007\/s00521-020-05387-4","type":"journal-article","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T07:02:46Z","timestamp":1604473366000},"page":"6133-6145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["GANFuse: a novel multi-exposure image fusion method based on generative adversarial networks"],"prefix":"10.1007","volume":"33","author":[{"given":"Zhiguang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3635-085X","authenticated-orcid":false,"given":"Youping","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuliang","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,4]]},"reference":[{"key":"5387_CR1","unstructured":"Wandell B (1995) Foundations of vision, vol 42, p 01"},{"issue":"11","key":"5387_CR2","doi-asserted-by":"publisher","first-page":"3345","DOI":"10.1109\/TIP.2015.2442920","volume":"24","author":"K Ma","year":"2015","unstructured":"Ma K, Zeng K, Wang Z (2015) Perceptual quality assessment for multi-exposure image fusion. IEEE Trans Image Process 24(11):3345\u20133356","journal-title":"IEEE Trans Image Process"},{"key":"5387_CR3","doi-asserted-by":"crossref","unstructured":"Burt PJ (1984) The pyramid as a structure for efficient computation. Springer Series in Information Sciences, vol 12, pp 6\u201335","DOI":"10.1007\/978-3-642-51590-3_2"},{"key":"5387_CR4","doi-asserted-by":"crossref","unstructured":"Vonikakis V, Bouzos O, Andreadis I (2011) Multi-exposure image fusion based on illumination estimation. Springer Series in Information Sciences, pp 135\u2013142","DOI":"10.2316\/P.2011.738-051"},{"issue":"1","key":"5387_CR5","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/TIP.2011.2157514","volume":"21","author":"M Song","year":"2012","unstructured":"Song M, Tao D, Chen C, Bu J, Luo J, Zhang C (2012) Probabilistic exposure fusion. IEEE Trans Image Process A Publ IEEE Signal Process Soc 21(1):341","journal-title":"IEEE Trans Image Process A Publ IEEE Signal Process Soc"},{"issue":"10","key":"5387_CR6","doi-asserted-by":"publisher","first-page":"4372","DOI":"10.1109\/TIP.2014.2349432","volume":"23","author":"Z Li","year":"2014","unstructured":"Li Z, Zheng J, Zhu Z, Wu S (2014) Selectively detail-enhanced fusion of differently exposed images with moving objects. IEEE Trans Image Process 23(10):4372\u20134382","journal-title":"IEEE Trans Image Process"},{"key":"5387_CR7","doi-asserted-by":"crossref","unstructured":"Lee S, Sung PJ, Ik CN (2018) A multi-exposure image fusion based on the adaptive weights reflecting the relative pixel intensity and global gradient, pp 1737\u20131741","DOI":"10.1109\/ICIP.2018.8451153"},{"key":"5387_CR8","doi-asserted-by":"crossref","unstructured":"Wang J, Xu G, Lou H (2015) Exposure fusion based on sparse coding in pyramid transform domain. In: ACM Press the 7th international conference, pp 1\u20134","DOI":"10.1145\/2808492.2808496"},{"key":"5387_CR9","doi-asserted-by":"crossref","unstructured":"Xu J, Huang Y (2013) Multi-exposure images of wavelet transform fusion. In: Proceedings of the SPIE, p 8878","DOI":"10.1117\/12.2030557"},{"key":"5387_CR10","doi-asserted-by":"crossref","unstructured":"Abdelkader A, Eldin MH, Ebrahim RS (2011) Performance measures for image fusion based on wavelet transform and curvelet transform, pp 1\u20137","DOI":"10.1109\/NRSC.2011.5873622"},{"issue":"6","key":"5387_CR11","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1016\/j.imavis.2005.02.004","volume":"23","author":"A Goshtasby","year":"2005","unstructured":"Goshtasby A (2005) Fusion of multi-exposure images. Image Vis Comput 23(6):611\u2013618","journal-title":"Image Vis Comput"},{"key":"5387_CR12","doi-asserted-by":"crossref","unstructured":"Ma K (2015) Multi-exposure image fusion: a patch-wise approach. In: IEEE International conference on image processing (ICIP), pp 1717\u20131721","DOI":"10.1109\/ICIP.2015.7351094"},{"key":"5387_CR13","doi-asserted-by":"crossref","unstructured":"Ram Prabhakar K, Sai Srikar V, Venkatesh Babu R (2017) Deepfuse: a deep unsupervised approach for exposure fusion with extreme exposure image pairs. In: IEEE international conference on computer vision, vol 505, pp 4724\u20134732","DOI":"10.1109\/ICCV.2017.505"},{"key":"5387_CR14","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.inffus.2016.12.001","volume":"36","author":"Y Liu","year":"2017","unstructured":"Liu Y, Chen X, Peng H, Wang Z (2017) Multi-focus image fusion with a deep convolutional neural network. Inf Fusion 36:191\u2013207","journal-title":"Inf Fusion"},{"key":"5387_CR15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","volume":"54","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Liu Y, Sun P, Yan H, Zhao X, Zhang L (2020) IFCNN: a general image fusion framework based on convolutional neural network. Inf Fusion 54:99\u2013118","journal-title":"Inf Fusion"},{"key":"5387_CR16","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","volume":"48","author":"J Ma","year":"2019","unstructured":"Ma J, Yu W, Liang P, Li C, Jiang J (2019) Fusiongan: a generative adversarial network for infrared and visible image fusion. Inf Fusion 48:11\u201326","journal-title":"Inf Fusion"},{"key":"5387_CR17","doi-asserted-by":"publisher","first-page":"7203","DOI":"10.1109\/TIP.2020.2999855","volume":"29","author":"H Xu","year":"2020","unstructured":"Xu H, Ma J, Zhang X-P (2020) MEF-GAN: multi-exposure image fusion via generative adversarial networks. IEEE Trans Image Process 29:7203\u20137216","journal-title":"IEEE Trans Image Process"},{"key":"5387_CR18","unstructured":"Han X, Ma J, Jiang J, Guo X, Ling H (2020) U2fusion: a unified unsupervised image fusion network. IEEE Trans Pattern Anal Mach Intell"},{"key":"5387_CR19","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.inffus.2016.05.004","volume":"33","author":"S Li","year":"2017","unstructured":"Li S, Kang X, Fang L, Hu J, Yin H (2017) Pixel-level image fusion: a survey of the state of the art. Inf Fusion 33:100\u2013112","journal-title":"Inf Fusion"},{"issue":"12","key":"5387_CR20","doi-asserted-by":"publisher","first-page":"1882","DOI":"10.1109\/LSP.2016.2618776","volume":"23","author":"Y Liu","year":"2016","unstructured":"Liu Y, Chen X, Ward RK, Wang ZJ (2016) Image fusion with convolutional sparse representation. IEEE Signal Process Lett 23(12):1882\u20131886","journal-title":"IEEE Signal Process Lett"},{"key":"5387_CR21","doi-asserted-by":"crossref","unstructured":"Li H, Wu X, Kittler J (2018) Infrared and visible image fusion using a deep learning framework. In: 2018 24th international conference on pattern recognition (ICPR), pp 2705\u20132710","DOI":"10.1109\/ICPR.2018.8546006"},{"key":"5387_CR22","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.inffus.2019.07.005","volume":"54","author":"J Ma","year":"2020","unstructured":"Ma J, Liang P, Yu W, Chen C, Guo X, Wu J, Jiang J (2020) Infrared and visible image fusion via detail preserving adversarial learning. Inf Fusion 54:85\u201398","journal-title":"Inf Fusion"},{"key":"5387_CR23","doi-asserted-by":"publisher","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","volume":"29","author":"J Ma","year":"2020","unstructured":"Ma J, Han X, Jiang J, Mei X, Zhang X (2020) DDCGAN: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans Image Process 29:4980\u20134995","journal-title":"IEEE Trans Image Process"},{"issue":"12","key":"5387_CR24","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1016\/j.aeue.2015.09.004","volume":"69","author":"V Aslantas","year":"2015","unstructured":"Aslantas V, Bendes E (2015) A new image quality metric for image fusion: the sum of the correlations of differences. AEU-Int J Electron Commun 69(12):1890\u20131896","journal-title":"AEU-Int J Electron Commun"},{"issue":"5","key":"5387_CR25","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2019","unstructured":"Li H, Wu X (2019) Densefuse: a fusion approach to infrared and visible images. IEEE Trans Image Process 28(5):2614\u20132623","journal-title":"IEEE Trans Image Process"},{"key":"5387_CR26","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"key":"5387_CR27","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. In: International conference on learning representation (ICLR), pp 1-16"},{"key":"5387_CR28","unstructured":"Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: Proceedings of the international conference on machine learning, pp 214\u2013223"},{"key":"5387_CR29","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RYK, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks, pp 2813\u20132821","DOI":"10.1109\/ICCV.2017.304"},{"key":"5387_CR30","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"5387_CR31","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:Learning"},{"issue":"9","key":"5387_CR32","doi-asserted-by":"publisher","first-page":"3540","DOI":"10.1109\/TNNLS.2019.2944979","volume":"31","author":"L Liu","year":"2019","unstructured":"Liu L, Zhang H, Xu X, Zhang Z (2019) Collocating clothes with generative adversarial networks cosupervised by categories and attributes: a multidiscriminator framework. IEEE Trans Neural Netw Learn Syst 31(9):3540\u20133554","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"5387_CR33","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1007\/s10489-017-0916-1","volume":"47","author":"KT Ahmed","year":"2017","unstructured":"Ahmed KT, Irtaza A, Iqbal MA (2017) Fusion of local and global features for effective image extraction. Appl Intell 47(2):526\u2013543","journal-title":"Appl Intell"},{"issue":"7","key":"5387_CR34","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1007\/s00521-018-3441-1","volume":"30","author":"H Hermessi","year":"2018","unstructured":"Hermessi H, Mourali O, Zagrouba E (2018) Convolutional neural network-based multimodal image fusion via similarity learning in the shearlet domain. Neural Comput Appl 30(7):2029\u20132045","journal-title":"Neural Comput Appl"},{"key":"5387_CR35","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"10","key":"5387_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0218126616501231","volume":"25","author":"S Paul","year":"2016","unstructured":"Paul S, Sevcenco IS, Agathoklis P (2016) Multi-exposure and multi-focus image fusion in gradient domain. J Circuits Syst Comput 25(10):1\u201318","journal-title":"J Circuits Syst Comput"},{"key":"5387_CR37","doi-asserted-by":"crossref","unstructured":"Ram Prabhakar K, Venkatesh Babu R (2016) Ghosting-free multi-exposure image fusion in gradient domain. In: IEEE International conference on acoustics, speech and signal processing, pp 1766\u20131770","DOI":"10.1109\/ICASSP.2016.7471980"},{"issue":"7","key":"5387_CR38","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1109\/TIP.2013.2253483","volume":"22","author":"S Li","year":"2013","unstructured":"Li S, Kang X, Jianwen H (2013) Image fusion with guided filtering. IEEE Trans Image Process 22(7):2864\u20132875","journal-title":"IEEE Trans Image Process"},{"key":"5387_CR39","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.jvcir.2015.06.021","volume":"31","author":"Y Liu","year":"2015","unstructured":"Liu Y, Wang Z (2015) Dense sift for ghost-free multi-exposure fusion. J Vis Commun Image Represent 31:208\u2013224","journal-title":"J Vis Commun Image Represent"},{"issue":"12","key":"5387_CR40","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1109\/LSP.2018.2877893","volume":"25","author":"Y Yang","year":"2018","unstructured":"Yang Y, Cao W, Shiqian W, Li Z (2018) Multi-scale fusion of two large-exposure-ratio images. IEEE Signal Process Lett 25(12):1885\u20131889","journal-title":"IEEE Signal Process Lett"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05387-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05387-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05387-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T07:38:56Z","timestamp":1621496336000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05387-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,4]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["5387"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05387-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,4]]},"assertion":[{"value":"14 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}