{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:52:15Z","timestamp":1785603135951,"version":"3.56.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T00:00:00Z","timestamp":1621036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T00:00:00Z","timestamp":1621036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["15\/RP\/2776"],"award-info":[{"award-number":["15\/RP\/2776"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions<jats:italic>in the wild<\/jats:italic>. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct choice of thresholds and frequency estimates. On the other hand, traditional deep networks are trained end to end in the RGB space by formulating this task as an image translation problem. However, that is done without any<jats:italic>explicit<\/jats:italic>constraints on the inherent noise of the dark images and thus produces noisy and blurry outputs. To this end, we propose a DCT\/FFT-based multi-scale loss function, which when combined with traditional losses, trains a network to translate the important features for visually pleasing output. Our loss function is end to end differentiable, scale-agnostic and generic; i.e., it can be applied to both RAW and JPEG images in most existing frameworks without additional overhead. Using this loss function, we report significant improvements over the state of the art using quantitative metrics and subjective tests.<\/jats:p>","DOI":"10.1007\/s11760-021-01915-4","type":"journal-article","created":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T13:02:44Z","timestamp":1621083764000},"page":"1829-1836","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Frequency-domain loss function for deep exposure correction of dark images"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4781-5517","authenticated-orcid":false,"given":"Ojasvi","family":"Yadav","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koustav","family":"Ghosal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Lutz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aljosa","family":"Smolic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,15]]},"reference":[{"issue":"3","key":"1915_CR1","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","volume":"39","author":"SM Pizer","year":"1987","unstructured":"Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R., Geselowitz, A., Greer, T., ter Haar Romeny, B., Zimmerman, J.B., Zuiderveld, K.: Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 39(3), 355\u2013368 (1987)","journal-title":"Comput. Vis. Graph. Image Process."},{"issue":"3","key":"1915_CR2","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1109\/TIP.2012.2226047","volume":"22","author":"S-C Huang","year":"2012","unstructured":"Huang, S.-C., Cheng, F.-C., Chiu, Y.-S.: Efficient contrast enhancement using adaptive gamma correction with weighting distribution. IEEE Trans. Image Process. 22(3), 1032\u20131041 (2012)","journal-title":"IEEE Trans. Image Process."},{"key":"1915_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., Chen, Q., Xu, J., Koltun, V.: Learning to see in the dark. In: Proceedings of the CVPR, pp.\u00a03291\u20133300 (2018)","DOI":"10.1109\/CVPR.2018.00347"},{"key":"1915_CR4","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.cviu.2018.10.010","volume":"178","author":"YP Loh","year":"2019","unstructured":"Loh, Y.P., Chan, C.S.: Getting to know low-light images with the exclusively dark dataset. Comput. Vis. Image Underst. 178, 30\u201342 (2019)","journal-title":"Comput. Vis. Image Underst."},{"key":"1915_CR5","unstructured":"Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: British Machine Vision Conference (2018)"},{"key":"1915_CR6","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the CVPR, pp.\u00a01125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"1915_CR7","unstructured":"Dong, X., Wang, G., Pang, Y., Li, W., Wen, J., Meng, W., Lu, Y.: Fast efficient algorithm for enhancement of low lighting video. In: 2011 IEEE International Conference on Multimedia and Expo, pp.\u00a01\u20136. IEEE (2011)"},{"key":"1915_CR8","doi-asserted-by":"crossref","unstructured":"Malm, H., Oskarsson, M., Warrant, E., Clarberg, P., Hasselgren, J., Lejdfors, C.: Adaptive enhancement and noise reduction in very low light-level video. In: 2007 IEEE 11th International Conference on Computer Vision, pp.\u00a01\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4409007"},{"issue":"6","key":"1915_CR9","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1016\/j.dsp.2013.06.002","volume":"23","author":"A \u0141oza","year":"2013","unstructured":"\u0141oza, A., Bull, D.R., Hill, P.R., Achim, A.M.: Automatic contrast enhancement of low-light images based on local statistics of wavelet coefficients. Digit. Signal Process. 23(6), 1856\u20131866 (2013)","journal-title":"Digit. Signal Process."},{"issue":"1\u20134","key":"1915_CR10","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","volume":"60","author":"LI Rudin","year":"1992","unstructured":"Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D Nonlinear Phenomena 60(1\u20134), 259\u2013268 (1992)","journal-title":"Physica D Nonlinear Phenomena"},{"issue":"11","key":"1915_CR11","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1109\/TIP.2003.818640","volume":"12","author":"J Portilla","year":"2003","unstructured":"Portilla, J., Strela, V., Wainwright, M.J., Simoncelli, E.P.: Image denoising using scale mixtures of gaussians in the wavelet domain. IEEE Trans. Image Process. 12(11), 1338\u20131351 (2003)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"1915_CR12","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TIP.2006.881969","volume":"15","author":"M Elad","year":"2006","unstructured":"Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 15(12), 3736\u20133745 (2006)","journal-title":"IEEE Trans. Image Process."},{"key":"1915_CR13","doi-asserted-by":"crossref","unstructured":"Zhuo, S., Guo, D., Sim, T.: Robust flash deblurring. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.\u00a02440\u20132447. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539941"},{"issue":"3","key":"1915_CR14","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1145\/1360612.1360672","volume":"27","author":"Q Shan","year":"2008","unstructured":"Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. (TOG) 27(3), 73 (2008)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"1915_CR15","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1088\/0266-5611\/22\/6\/008","volume":"22","author":"M Donatelli","year":"2006","unstructured":"Donatelli, M., Estatico, C., Martinelli, A., Serra-Capizzano, S.: Improved image deblurring with anti-reflective boundary conditions and re-blurring. Inverse Probl. 22(6), 2035 (2006)","journal-title":"Inverse Probl."},{"key":"1915_CR16","unstructured":"Yu, R., Liu, W., Zhang, Y., Qu, Z., Zhao, D., Zhang, B.: Deepexposure: learning to expose photos with asynchronously reinforced adversarial learning. In: Advances in Neural Information Processing Systems, vol. 31, pp.\u00a02149\u20132159. Curran Associates, Inc. (2018)"},{"issue":"2","key":"1915_CR17","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TIP.2016.2639450","volume":"26","author":"X Guo","year":"2016","unstructured":"Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982\u2013993 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"1915_CR18","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.patcog.2016.06.008","volume":"61","author":"KG Lore","year":"2017","unstructured":"Lore, K.G., Akintayo, A., Sarkar, S.: LLNet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recognit. 61, 650\u2013662 (2017)","journal-title":"Pattern Recognit."},{"key":"1915_CR19","unstructured":"Shen, L., Yue, Z., Feng, F., Chen, Q., Liu, S., Ma, J.: Msr-net: low-light image enhancement using deep convolutional network. CoRR, arXiv:1711.02488 (2017)"},{"key":"1915_CR20","doi-asserted-by":"publisher","first-page":"e22","DOI":"10.1017\/ATSIP.2018.26","volume":"7","author":"Y Kinoshita","year":"2018","unstructured":"Kinoshita, Y., Kiya, H.: Automatic exposure compensation using an image segmentation method for single-image-based multi-exposure fusion. APSIPA Trans. Signal Inf. Process. 7, e22 (2018)","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"1915_CR21","doi-asserted-by":"crossref","unstructured":"Huang, H., Tao, H., Wang, H.: A convolutional neural network based method for low-illumination image enhancement. In: Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition, AIPR \u201919 (New York, NY, USA), pp.\u00a072\u201377. ACM (2019)","DOI":"10.1145\/3357254.3357255"},{"key":"1915_CR22","unstructured":"Zamir, S.W., Arora, A., Khan, S., Khan, F.S., Shao, L.: Learning digital camera pipeline for extreme low-light imaging. arXiv preprint arXiv:1904.05939 (2019)"},{"key":"1915_CR23","doi-asserted-by":"publisher","first-page":"164:1","DOI":"10.1145\/3355089.3356508","volume":"38","author":"O Liba","year":"2019","unstructured":"Liba, O., Murthy, K., Tsai, Y.-T., Brooks, T., Xue, T., Karnad, N., He, Q., Barron, J.T., Sharlet, D., Geiss, R., Hasinoff, S.W., Pritch, Y., Levoy, M.: Handheld mobile photography in very low light. ACM Trans. Graph. 38, 164:1\u2013164:16 (2019)","journal-title":"ACM Trans. Graph."},{"key":"1915_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, L., Liu, X., Shen, Y., Zhang, S., Zhao, S.: Zero-shot restoration of back-lit images using deep internal learning. In: Proceedings of the 27th ACM International Conference on Multimedia, MM\u201919 (New York), pp.\u00a01623\u20131631. ACM (2019)","DOI":"10.1145\/3343031.3351069"},{"key":"1915_CR25","unstructured":"Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., Yang, J., Zhou, P., Wang, Z.: Enlightengan: deep light enhancement without paired supervision. arXiv preprint arXiv:1906.06972 (2019)"},{"key":"1915_CR26","doi-asserted-by":"crossref","unstructured":"Atoum, Y., Ye, M., Ren, L., Tai, Y., Liu, X.: Color-wise attention network for low-light image enhancement. arXiv preprint arXiv:1911.08681 (2019)","DOI":"10.1109\/CVPRW50498.2020.00261"},{"key":"1915_CR27","unstructured":"Lv, F., Lu, F.: Attention-guided low-light image enhancement. arXiv preprint arXiv:1908.00682 (2019)"},{"key":"1915_CR28","doi-asserted-by":"crossref","unstructured":"Malik, S., Soundararajan, R.: Llrnet: a multiscale subband learning approach for low light image restoration. In: 2019 IEEE International Conference on Image Processing (ICIP), pp.\u00a0779\u2013783. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803765"},{"key":"1915_CR29","doi-asserted-by":"publisher","first-page":"13737","DOI":"10.1109\/ACCESS.2019.2891957","volume":"7","author":"Y Guo","year":"2019","unstructured":"Guo, Y., Ke, X., Ma, J., Zhang, J.: A pipeline neural network for low-light image enhancement. IEEE Access 7, 13737\u201313744 (2019)","journal-title":"IEEE Access"},{"key":"1915_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp.\u00a02223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"1915_CR31","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv (2016)","DOI":"10.1109\/CVPR.2017.632"},{"key":"1915_CR32","unstructured":"Perez-Ortiz, M., Mantiuk, R.K.: A practical guide and software for analysing pairwise comparison experiments. arXiv preprint arXiv:1712.03686 (2017)"},{"key":"1915_CR33","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. CoRR, arXiv:1501.00092 (2015)"},{"key":"1915_CR34","unstructured":"Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., Aila, T.: Noise2noise: learning image restoration without clean data. CoRR, arXiv:1803.04189 (2018)"},{"key":"1915_CR35","doi-asserted-by":"crossref","unstructured":"Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: Deblurgan-v2: deblurring (orders-of-magnitude) faster and better. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp.\u00a08877\u20138886 (2019)","DOI":"10.1109\/ICCV.2019.00897"},{"key":"1915_CR36","doi-asserted-by":"crossref","unstructured":"Xie, C., Liu, S., Li, C., Cheng, M.-M., Zuo, W., Liu, X., Wen, S., Ding, E.: Image inpainting with learnable bidirectional attention maps (2019)","DOI":"10.1109\/ICCV.2019.00895"},{"key":"1915_CR37","doi-asserted-by":"crossref","unstructured":"Claus , M., van Gemert, J.: Videnn: deep blind video denoising. CoRR, arXiv:1904.10898 (2019)","DOI":"10.1109\/CVPRW.2019.00235"},{"key":"1915_CR38","doi-asserted-by":"crossref","unstructured":"Nah, S., Kim, T.H., Lee, K.M.: Deep multi-scale convolutional neural network for dynamic scene deblurring. CoRR, arXiv:1612.02177 (2016)","DOI":"10.1109\/CVPR.2017.35"},{"issue":"12","key":"1915_CR39","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/2830541","volume":"58","author":"C Doersch","year":"2015","unstructured":"Doersch, C., Singh, S., Gupta, A., Sivic, J., Efros, A.A.: What makes Paris look like Paris? Commun. ACM 58(12), 103\u2013110 (2015)","journal-title":"Commun. ACM"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01915-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-01915-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01915-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T13:17:16Z","timestamp":1672147036000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-01915-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,15]]},"references-count":39,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1915"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-01915-4","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,15]]},"assertion":[{"value":"17 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}