{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:13:21Z","timestamp":1774541601654,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:00:00Z","timestamp":1667865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:00:00Z","timestamp":1667865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Ministry of Land, Infrastructure and Transport of the Korean government","award":["21DRMSB147287-04"],"award-info":[{"award-number":["21DRMSB147287-04"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recent advances in deep learning technology, and the availability of public shadow image datasets, have enabled significant performance improvements of shadow removal tasks in computer vision. However, most deep learning-based shadow removal methods are usually trained in a supervised manner, in which paired shadow and shadow-free data are required. We developed a weakly supervised generative adversarial network with a cycle-in-cycle structure for shadow removal using unpaired data. In addition, we introduced new loss functions to reduce unnecessary transformations for non-shadow areas and to enable smooth transformations for shadow boundary areas. We conducted extensive experiments using the ISTD and Video Shadow Removal datasets to assess the effectiveness of our methods. The experimental results show that our method is superior to other state-of-the-art methods trained on unpaired data.<\/jats:p>","DOI":"10.1007\/s10489-022-04269-7","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T04:30:44Z","timestamp":1667881844000},"page":"15067-15079","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["C2ShadowGAN: cycle-in-cycle generative adversarial network for shadow removal using unpaired data"],"prefix":"10.1007","volume":"53","author":[{"given":"Sunwon","family":"Kang","sequence":"first","affiliation":[]},{"given":"Juwan","family":"Kim","sequence":"additional","affiliation":[]},{"given":"In Sung","family":"Jang","sequence":"additional","affiliation":[]},{"given":"Byoung-Dai","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,8]]},"reference":[{"key":"4269_CR1","doi-asserted-by":"publisher","first-page":"111945","DOI":"10.1016\/j.rse.2020.111945","volume":"247","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Chen G, Vukomanovic J, Singh KK, Liu Y, Holden S, Meetemeyer RK (2020) Recurrent shadow attention model (RSAM) for shadow removal in high-resolution urban land-cover mapping. Remote Sens Environ 247:111945\u2013111959","journal-title":"Remote Sens Environ"},{"key":"4269_CR2","doi-asserted-by":"crossref","unstructured":"Qu L, Tian J, He S, Tang Y, Lau R (2017) DeshadowNet: a multi-context embedding deep network for shadow removal. In: Proc. CVPR, Honolulu, Hawaii, USA, pp 2308\u20132316","DOI":"10.1109\/CVPR.2017.248"},{"issue":"7","key":"4269_CR3","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1111\/cgf.13845","volume":"38","author":"J Wei","year":"2019","unstructured":"Wei J, Long C, Zou H, Xiao C (2019) Shadow inpainting and removal using generative adversarial networks with slice convolutions. Comput Graph Forum 38(7):381\u2013392","journal-title":"Comput Graph Forum"},{"key":"4269_CR4","doi-asserted-by":"crossref","unstructured":"Cun X, Pun C, Shi C (2020) Towards ghost-free shadow removal via dual hierarchical aggregation network and shadow matting GAN. In: Proc. AAAI Conf. Artif. Intell., New York, NY, USA, pp 10680\u201310687","DOI":"10.1609\/aaai.v34i07.6695"},{"key":"4269_CR5","doi-asserted-by":"crossref","unstructured":"Le H, Samaras D (2019) Shadow removal via shadow image decomposition. In: Proc. ICCV, Seoul, South Korea, pp. 8578\u20138587","DOI":"10.1109\/ICCV.2019.00867"},{"key":"4269_CR6","doi-asserted-by":"crossref","unstructured":"Hu X, Jiang Y, Fu C, Heng P (2019) Mask-ShadowGAN: learning to remove shadows from unpaired data. In: Proc. ICCV, Seoul, South Korea, pp 2472\u20132481","DOI":"10.1109\/ICCV.2019.00256"},{"key":"4269_CR7","unstructured":"Vasluianu F, Romero A, Gool L, Timofte R (2021) Self-supervised shadow removal. In: Proc. CVPRW, pp 826\u2013835"},{"issue":"11","key":"4269_CR8","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1109\/TPAMI.2019.2919616","volume":"42","author":"X Hu","year":"2020","unstructured":"Hu X, Fu C, Zhu L, Qin J, Heng P (2020) Direction-aware spatial context features for shadow detection and removal. IEEE Trans Pattern Anal Mach Intell 42(11):2795\u20132808","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4269_CR9","doi-asserted-by":"crossref","unstructured":"Zheng Q, Qian X, Cao Y, Lau R (2019) Distraction-aware shadow detection. In: Proc. CVPR, Long Beach, LA, USA, pp 5167\u20135176","DOI":"10.1109\/CVPR.2019.00531"},{"issue":"3","key":"4269_CR10","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1109\/TPAMI.2015.2462355","volume":"38","author":"SH Khan","year":"2016","unstructured":"Khan SH, Bennamoun M, Sohel F, Togneri R (2016) Automatic shadow detection and removal from a single image. IEEE Trans Pattern Anal Mach Intell 38(3):431\u2013446","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4269_CR11","doi-asserted-by":"crossref","unstructured":"Wang J, Li X, Yang J (2018) Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In: Proc. CVPR, Salt Lake City, UT, USA, pp 1788\u20131797","DOI":"10.1109\/CVPR.2018.00192"},{"key":"4269_CR12","doi-asserted-by":"crossref","unstructured":"Vincente TF, Hou L, Yu C, Hoai M, Samaras D (2016) Large-scale training of shadow detectors with noisily-annotated shadow examples. In: Proc. ECCV, Amsterdam, Netherlands, pp 816\u2013832","DOI":"10.1007\/978-3-319-46466-4_49"},{"key":"4269_CR13","doi-asserted-by":"crossref","unstructured":"Le H, Samaras D (2020) From shadow segmentation to shadow removal. In: Proc. ECCV, pp 264\u2013281","DOI":"10.1007\/978-3-030-58621-8_16"},{"issue":"11","key":"4269_CR14","doi-asserted-by":"publisher","first-page":"4187","DOI":"10.1109\/TCSVT.2020.3047977","volume":"31","author":"N Inoue","year":"2020","unstructured":"Inoue N, Yamasaki T (2020) Learning from synthetic shadows for shadow detection and removal. IEEE Trans Circuits Syst Video Technol 31(11):4187\u20134197","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"2","key":"4269_CR15","first-page":"27","volume":"29","author":"J Kim","year":"2021","unstructured":"Kim J, Jang I (2021) Dual hierarchical aggregation network based enhanced shadow detection and removal. J Korean Soc Geospatial Info Sci 29(2):27\u201334","journal-title":"J Korean Soc Geospatial Info Sci"},{"key":"4269_CR16","doi-asserted-by":"crossref","unstructured":"Liu Z, Yin H, Wu X, Wu Z, Mi Y, Wang S (2021) From shadow generation to shadow removal. In: Proc. CVPR, pp 4927\u20134936","DOI":"10.1109\/CVPR46437.2021.00489"},{"key":"4269_CR17","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Couville A, Bengio Y (2014) Generative adversarial nets. Adv Neural Inf Process Syst:2672\u20132680"},{"key":"4269_CR18","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1109\/TIP.2020.3048677","volume":"30","author":"Z Liu","year":"2021","unstructured":"Liu Z, Yin H, Mi Y, Pu M, Wang S (2021) Shadow removal by a lightness-guided network with training on unpaired data. IEEE Trans Image Process 30:1853\u20131865","journal-title":"IEEE Trans Image Process"},{"key":"4269_CR19","doi-asserted-by":"publisher","first-page":"5881","DOI":"10.1109\/TIP.2019.2922854","volume":"28","author":"Y Li","year":"2019","unstructured":"Li Y, Tang S, Zhang R, Zhang Y, Li U, Yan S (2019) Asymmetric GAN for unpaired image-to-image translation. IEEE Trans Image Process 28:5881\u20135896","journal-title":"IEEE Trans Image Process"},{"key":"4269_CR20","doi-asserted-by":"crossref","unstructured":"Choi Y, Choi M, Kim M, Ha J, Kim S, Choo J (2018) StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proc. CVPR, Salt Lake City, UT, USA, pp 8789\u20138797","DOI":"10.1109\/CVPR.2018.00916"},{"key":"4269_CR21","doi-asserted-by":"crossref","unstructured":"Kumar PC (2019) A survey on various shadow detection and removal methods. In: Proc. ICCVBIC, Coimbatore, India, pp 395\u2013401","DOI":"10.1007\/978-3-030-37218-7_45"},{"key":"4269_CR22","doi-asserted-by":"crossref","unstructured":"Tiwari A, Singh PK, Amin S (2016) A survey on shadow detection and removal in images and video sequences. In: Proc. CONFLUENCE, Noida, India, pp 518\u2013523","DOI":"10.1109\/CONFLUENCE.2016.7508175"},{"key":"4269_CR23","doi-asserted-by":"publisher","first-page":"38","DOI":"10.5815\/ijigsp.2016.12.05","volume":"8","author":"S Murali","year":"2016","unstructured":"Murali S, Govindan V, Kalady S (2016) A survey on shadow removal techniques for single image. Int J Image Graph Signal Process 8:38\u201346","journal-title":"Int J Image Graph Signal Process"},{"issue":"13","key":"4269_CR24","doi-asserted-by":"publisher","first-page":"2998","DOI":"10.1049\/iet-ipr.2020.0001","volume":"14","author":"M Shilpa","year":"2020","unstructured":"Shilpa M, Gopalakrishnan MT, Naveena C (2020) Approach for shadow detection and removal using machine learning techniques. IET Image Process 14(13):2998\u20133005","journal-title":"IET Image Process"},{"key":"4269_CR25","doi-asserted-by":"crossref","unstructured":"Zhu J, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proc. ICCV, Venice, Italy, pp 1033\u20131038","DOI":"10.1109\/ICCV.2017.244"},{"key":"4269_CR26","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1109\/TPAMI.2010.157","volume":"33","author":"E Arbel","year":"2011","unstructured":"Arbel E, Helor H (2011) Shadow removal using intensity surfaces and texture anchor points. IEEE Trans Pattern Anal Mach Intell 33:1202\u20131216","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4269_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app9051009","volume":"9","author":"H Fan","year":"2019","unstructured":"Fan H, Han M, Li J (2019) Image shadow removal using end-to-end deep convolutional neural networks. Appl Sci 9:1\u201318","journal-title":"Appl Sci"},{"key":"4269_CR28","unstructured":"Ulyanov D, Vedaldai A, Lempitsky V (2016) Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1701.02096"},{"key":"4269_CR29","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J, Zhou T, Efros A (2017) Image-to-image translation with conditional adversarial networks. In: Proc. CVPR, Honolulu, Hawaii, USA, pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"4269_CR30","doi-asserted-by":"publisher","first-page":"33346","DOI":"10.1109\/ACCESS.2019.2903131","volume":"7","author":"S Son","year":"2019","unstructured":"Son S, Song Y, Kim N, Do Y, Kwak N, Lee M, Lee B (2019) TW3- based fully automated bone age assessment system using deep neural networks. IEEE Access 7:33346\u201333358","journal-title":"IEEE Access"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04269-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04269-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04269-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T03:49:42Z","timestamp":1685591382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04269-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,8]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["4269"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04269-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,8]]},"assertion":[{"value":"15 October 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}