{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:22:37Z","timestamp":1784564557021,"version":"3.55.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11633-024-1522-4","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T21:58:12Z","timestamp":1742594292000},"page":"452-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DDSR-Net: Direct Document Shadow Removal Leveraging Multi-scale Attention"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2603-8328","authenticated-orcid":false,"given":"Bingshu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7865-5555","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,21]]},"reference":[{"key":"1522_CR1","unstructured":"C. W. Liu, J. C. Li, Y. H. Teng, C. Q. Wang, N. Xu, J. H. Wu, D. D. Tu. DocStormer: Revitalizing multi-degraded colored document images to pristine PDF, [Online], Available: https:\/\/arxiv.org\/abs\/2310.17910, 2023."},{"key":"1522_CR2","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/978-3-030-86334-0_16","volume-title":"Proceedings of the 16th International Conference on Document Analysis and Recognition","author":"S Dey","year":"2021","unstructured":"S. Dey, P. Jawanpuria. Light-weight document image cleanup using perceptual loss. In Proceedings of the 16th International Conference on Document Analysis and Recognition, Lausanne, Switzerland, pp. 238\u2013253, 2021. DOI: https:\/\/doi.org\/10.1007\/978-3-030-86334-0_16."},{"key":"1522_CR3","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-031-41734-4_13","volume-title":"Proceedings of the 17th International Conference on Document Analysis and Recognition","author":"S Saifullah","year":"2023","unstructured":"S. Saifullah, S. Agne, A. Dengel, S. Ahmed. ColDBin: Cold diffusion for document image binarization. In Proceedings of the 17th International Conference on Document Analysis and Recognition, San Jose, USA, pp.207\u2013226, 2023. DOI: https:\/\/doi.org\/10.1007\/978-3-031-41734-4_13."},{"key":"1522_CR4","unstructured":"Z. Anvari, V. Athitsos. A survey on deep learning based document image enhancement, [Online], Available: https:\/\/arxiv.org\/abs\/2112.02719, 2021."},{"key":"1522_CR5","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1145\/3581783.3611730","volume-title":"Proceedings of the 31st ACM International Conference on Multimedia","author":"Z Y Yang","year":"2023","unstructured":"Z. Y. Yang, B. L. Liu, Y. Xxiong, L. Yi, G. B. Wu, X. J. Tang, Z. Q. Liu, J. J. Zhou, X. Zhang. DocDiff: Document enhancement via residual diffusion models. In Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, Canada, pp. 2795\u20132806, 2023. DOI: https:\/\/doi.org\/10.1145\/3581783.3611730."},{"issue":"5","key":"1522_CR6","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1109\/TAI.2023.3321257","volume":"5","author":"J X Zhang","year":"2024","unstructured":"J. X. Zhang, L. Y. Liang, K. Ding, F. J. Guo, L. W. Jin. Appearance enhancement for camera-captured document images in the wild. IEEE Transactions on Artificial Intelligence, vol. 5, no. 5, pp. 2319\u20132330, 2024. DOI: https:\/\/doi.org\/10.1109\/TAI.2023.3321257.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"issue":"2","key":"1522_CR7","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1111\/j.1467-8659.2008.01155.x","volume":"27","author":"Y Shor","year":"2008","unstructured":"Y. Shor, D. Lischinski. The shadow meets the mask: Pyramid-based shadow removal. Computer Graphics Forum, vol. 27, no. 2, pp. 577\u2013586, 2008. DOI: https:\/\/doi.org\/10.1111\/j.1467-8659.2008.01155.x.","journal-title":"Computer Graphics Forum"},{"key":"1522_CR8","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1007\/978-3-642-39094-4_35","volume-title":"Proceedings of the 10th International Conference Image Analysis and Recognition","author":"D M Oliveira","year":"2013","unstructured":"D. M. Oliveira, R. D. Lins, G. de Fran\u00e7a Pereira e Silva. Shading removal of illustrated documents. In Proceedings of the 10th International Conference Image Analysis and Recognition, Aveiro, Portugal, pp. 308\u2013317, 2013. DOI: https:\/\/doi.org\/10.1007\/978-3-642-39094-4_35."},{"key":"1522_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2015.7761529","volume-title":"Proceedings of International Conference on Image and Vision Computing New Zealand","author":"B Jiang","year":"2015","unstructured":"B. Jiang, S. J. Liu, S. Y. Xia, X. Yu, M. M. Ding, X. D. Hou, Y. Gao. Video-based document image scanning using a mobile device. In Proceedings of International Conference on Image and Vision Computing New Zealand, Auckland, New Zealand, 2015. DOI: https:\/\/doi.org\/10.1109\/IVCNZ.2015.7761529."},{"issue":"3","key":"1522_CR10","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/s41095-019-0148-x","volume":"5","author":"S Murali","year":"2019","unstructured":"S. Murali, V. K. Govindan, S. Kalady. Single image shadow removal by optimization using non-shadow anchor values. Computational Visual Media, vol. 5, no. 3, pp. 311\u2013324, 2019. DOI: https:\/\/doi.org\/10.1007\/s41095-019-0148-x.","journal-title":"Computational Visual Media"},{"key":"1522_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095307","volume-title":"Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing","author":"P Mondal","year":"2023","unstructured":"P. Mondal, A. Pant, S. Soni. Dewarping documents using C2 continuous boundary estimation. In Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023. DOI: https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095307."},{"key":"1522_CR12","doi-asserted-by":"publisher","first-page":"1818","DOI":"10.1109\/CV-PR52729.2023.00181","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Zhang","year":"2023","unstructured":"L. Zhang, Y. H. He, Q. Zhang, Z. Liu, X. L. Zhang, C. X. Xiao. Document image shadow removal guided by color-aware background. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, pp. 1818\u20131827, 2023. DOI: https:\/\/doi.org\/10.1109\/CV-PR52729.2023.00181."},{"key":"1522_CR13","doi-asserted-by":"publisher","first-page":"12902","DOI":"10.1109\/CVPR42600.2020.01292","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y H Lin","year":"2020","unstructured":"Y. H. Lin, W. C. Chen, Y. Y. Chuang. BEDSR-Net: A deep shadow removal network from a single document image. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 12902\u201312911, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01292."},{"key":"1522_CR14","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/ICIP46576.2022.9897217","volume-title":"Proceedings of IEEE International Conference on Image Processing","author":"Y Matsuo","year":"2022","unstructured":"Y. Matsuo, N. Akimoto, Y. Aoki. Document shadow removal with foreground detection learning from fully synthetic images. In Proceedings of IEEE International Conference on Image Processing, Bordeaux, France, pp. 1656\u20131660, 2022. DOI: https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897217."},{"key":"1522_CR15","doi-asserted-by":"publisher","first-page":"5967","DOI":"10.1109\/CVPR.2017.632","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"P Isola","year":"2017","unstructured":"P. Isola, J. Y. Zhu, T. H. Zhou, A. A. Efros. Image-to-image translation with conditional adversarial networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 5967\u20135976, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.632."},{"issue":"7","key":"1522_CR16","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.1109\/TPAMI.2012.251","volume":"35","author":"G F Meng","year":"2013","unstructured":"G. F. Meng, S. M. Xiang, N. N. Zheng, C. H. Pan. Non-parametric illumination correction for scanned document images via convex hulls. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 7, pp. 1730\u20131743, 2013. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2012.251.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1522_CR17","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-319-54187-7_12","volume-title":"Proceedings of the 13th Asian Conference on Computer Vision","author":"S Bako","year":"2017","unstructured":"S. Bako, S. Darabi, E. Shechtman, J. Wang, K. Sunkavalli, P. Sen. Removing shadows from images of documents. In Proceedings of the 13th Asian Conference on Computer Vision, Taipei, China, pp. 173\u2013183, 2017. DOI: https:\/\/doi.org\/10.1007\/978-3-319-54187-7_12."},{"key":"1522_CR18","doi-asserted-by":"publisher","first-page":"3611","DOI":"10.1109\/ICIP.2019.8803486","volume-title":"Proceedings of IEEE International Conference on Image Processing","author":"B S Wang","year":"2019","unstructured":"B. S. Wang, C. L. P. Chen. An effective background estimation method for shadows removal of document images. In Proceedings of IEEE International Conference on Image Processing, Taipei, China, pp. 3611\u20133615, 2019. DOI: https:\/\/doi.org\/10.1109\/ICIP.2019.8803486."},{"key":"1522_CR19","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1109\/ICAS-SP40776.2020.9053378","volume-title":"Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing","author":"J R Wang","year":"2020","unstructured":"J. R. Wang, Y. Y. Chuang. Shadow removal of text document images by estimating local and global background colors. In Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, pp. 1534\u20131538, 2020. DOI: https:\/\/doi.org\/10.1109\/ICAS-SP40776.2020.9053378."},{"key":"1522_CR20","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-030-88010-1_8","volume-title":"Proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision","author":"J H Li","year":"2021","unstructured":"J. H. Li, Y. Chen, S. L. Liu. Document image binarization using visibility detection and point cloud segmentation. In Proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision, Beijing, China, pp. 92\u2013104, 2021. DOI: https:\/\/doi.org\/10.1007\/978-3-030-88010-1_8."},{"key":"1522_CR21","doi-asserted-by":"publisher","first-page":"2882","DOI":"10.1109\/SMC53654.2022.9945183","volume-title":"Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics","author":"Z Wang","year":"2022","unstructured":"Z. Wang, B. S. Wang, J. B. Zheng, C. L. P. Chen. Joint water-filling algorithm with adaptive chroma adjustment for shadow removal from text document images. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Prague, Czech Republic, pp. 2882\u20132887, 2022. DOI: https:\/\/doi.org\/10.1109\/SMC53654.2022.9945183."},{"key":"1522_CR22","doi-asserted-by":"publisher","first-page":"508","DOI":"10.23919\/EUSIPCO55093.2022.9909975","volume-title":"Proceedings of the 30th European Signal Processing Conference","author":"P Mondal","year":"2022","unstructured":"P. Mondal, A. Bal. A statistical approach for multi-frame shadow movement detection and shadow removal for document capture. In Proceedings of the 30th European Signal Processing Conference, Belgrade, Serbia, pp. 508\u2013512, 2022. DOI: https:\/\/doi.org\/10.23919\/EUSIPCO55093.2022.9909975."},{"issue":"3","key":"1522_CR23","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s10043-023-00806-y","volume":"30","author":"S Imahayashi","year":"2023","unstructured":"S. Imahayashi, M. Mukaida, S. Takeda, N. Suetake. Shadow removal from document image based on background estimation employing selective median filter and black-top-hat transform. Optical Review, vol. 30, no. 3, pp.336\u2013340, 2023. DOI: https:\/\/doi.org\/10.1007\/s10043-023-00806-y.","journal-title":"Optical Review"},{"issue":"11","key":"1522_CR24","doi-asserted-by":"publisher","first-page":"3072","DOI":"10.16208\/j.issn1000-7024.2017.11.033","volume":"38","author":"F F Zeng","year":"2017","unstructured":"F. F. Zeng, S. P. Liu. Research on Retinex in uneven illumination document images. Computer Engineering and Design, vol. 38, no. 11, pp. 3072\u20133079, 2017. DOI: https:\/\/doi.org\/10.16208\/j.issn1000-7024.2017.11.033.","journal-title":"Computer Engineering and Design"},{"key":"1522_CR25","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-319-64698-5_26","volume-title":"Proceedings of the 17th International Conference on Computer Analysis of Images and Patterns","author":"X M Yu","year":"2017","unstructured":"X. M. Yu, G. Li, Z. Q. Ying, X. Q. Guo. A new shadow removal method using color-lines. In Proceedings of the 17th International Conference on Computer Analysis of Images and Patterns, Ystad, Sweden, pp.307\u2013319, 2017. DOI: https:\/\/doi.org\/10.1007\/978-3-319-64698-5_26."},{"key":"1522_CR26","doi-asserted-by":"publisher","first-page":"2374","DOI":"10.1109\/CV-PR.2018.00252","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"N Kligler","year":"2018","unstructured":"N. Kligler, S. Katz, A. Tal. Document enhancement using visibility detection. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 2374\u20132382, 2018. DOI: https:\/\/doi.org\/10.1109\/CV-PR.2018.00252."},{"key":"1522_CR27","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1109\/ICASSP.2018.8462476","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"V Shah","year":"2018","unstructured":"V. Shah, V. Gandhi. An iterative approach for shadow removal in document images. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, pp. 1892\u20131896, 2018. DOI: https:\/\/doi.org\/10.1109\/ICASSP.2018.8462476."},{"key":"1522_CR28","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/ICFHR-2018.2018.00066","volume-title":"Proceedings of the 16th International Conference on Frontiers in Handwriting Recognition","author":"J Y Zhao","year":"2018","unstructured":"J. Y. Zhao, C. Z. Shi, F. X. Jia, Y. N. Wang, B. H. Xiao. An effective binarization method for disturbed camera-captured document images. In Proceedings of the 16th International Conference on Frontiers in Handwriting Recognition, Niagara Falls, USA, pp. 339\u2013344, 2018. DOI: https:\/\/doi.org\/10.1109\/ICFHR-2018.2018.00066."},{"key":"1522_CR29","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-030-20887-5_25","volume-title":"Proceedings of the 14th Asian Conference on Computer Vision","author":"S Jung","year":"2018","unstructured":"S. Jung, M. A. Hasan, C. Kim. Water-filling: An efficient algorithm for digitized document shadow removal. In Proceedings of the 14th Asian Conference on Computer Vision, Perth, Australia, pp.398\u2013414, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-20887-5_25."},{"key":"1522_CR30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096115","volume-title":"Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing","author":"W J Liu","year":"2023","unstructured":"W. J. Liu, B. S. Wang, J. B. Zheng, W. M. Wang. Shadow removal of text document images using background estimation and adaptive text enhancement. In Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023. DOI: https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096115."},{"key":"1522_CR31","doi-asserted-by":"publisher","first-page":"7454","DOI":"10.1109\/CVPR.2018.00778","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X W Hu","year":"2018","unstructured":"X. W. Hu, L. Zhu, C. W. Fu, J. Qin, P. A. Heng. Direction-aware spatial context features for shadow detection. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 7454\u20137462, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00778."},{"key":"1522_CR32","doi-asserted-by":"publisher","first-page":"10680","DOI":"10.1609\/aaai.v34i07.6695","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence","author":"X D Cun","year":"2020","unstructured":"X. D. Cun, C. M. Pun, C. Shi. Towards ghost-free shadow removal via dual hierarchical aggregation network and shadow matting GAN. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, USA, pp. 10680\u201310687, 2020. DOI: https:\/\/doi.org\/10.1609\/aaai.v34i07.6695."},{"key":"1522_CR33","doi-asserted-by":"publisher","unstructured":"X. Zhang, J. T. Barron, Y. T. Tsai, R. Pandey, X. M. Zhang, R. Ng, D. E. Jacobs. Portrait shadow manipulation. ACM Transactions on Graphics, vol. 39, no. 4, Article number 78, 2020. DOI: https:\/\/doi.org\/10.1145\/3386569.3392390.","DOI":"10.1145\/3386569.3392390"},{"issue":"3","key":"1522_CR34","doi-asserted-by":"publisher","first-page":"3259","DOI":"10.1109\/TPAMI.2022.3185628","volume":"45","author":"T Y Wang","year":"2023","unstructured":"T. Y. Wang, X. W. Hu, P. A. Heng, C. W. Fu. Instance shadow detection with a single-stage detector. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 3, pp.3259\u20133273, 2023. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2022.3185628.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1522_CR35","unstructured":"L. P. Jie, H. Zhang. When SAM meets shadow detection, [Online], Available: https:\/\/arxiv.org\/abs\/2305.11513,2023."},{"key":"1522_CR36","doi-asserted-by":"publisher","first-page":"12641","DOI":"10.1109\/ICCV51070.2023.01165","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Yang","year":"2023","unstructured":"H. Yang, T. Y. Wang, X. W. Hu, C. W. Fu. SILT: Shadow-aware iterative label tuning for learning to detect shadows from noisy labels. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Paris, France, pp. 12641\u201312652, 2023. DOI: https:\/\/doi.org\/10.1109\/ICCV51070.2023.01165."},{"key":"1522_CR37","doi-asserted-by":"publisher","first-page":"2308","DOI":"10.1109\/CVPR.2017.248","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"L Q Qu","year":"2017","unstructured":"L. Q. Qu, J. D. Tian, S. F. He, Y. D. Tang, R. W. H. Lau. DeshadowNet: A multi-context embedding deep network for shadow removal. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 2308\u20132316, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.248."},{"key":"1522_CR38","doi-asserted-by":"publisher","first-page":"8577","DOI":"10.1109\/ICCV.2019.00867","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Le","year":"2019","unstructured":"H. Le, D. Samaras. Shadow removal via shadow image decomposition. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 8577\u20138586, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00867."},{"key":"1522_CR39","doi-asserted-by":"publisher","first-page":"12829","DOI":"10.1609\/aaai.v34i07.6979","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence","author":"L Zhang","year":"2020","unstructured":"L. Zhang, C. J. Long, X. L. Zhang, C. X. Xiao. RIS-GAN: Explore residual and illumination with generative adversarial networks for shadow removal. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, USA, pp.12829\u201312836, 2020. DOI: https:\/\/doi.org\/10.1609\/aaai.v34i07.6979."},{"key":"1522_CR40","doi-asserted-by":"publisher","first-page":"5074","DOI":"10.1145\/3503161.3547916","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia","author":"Y H Wang","year":"2022","unstructured":"Y. H. Wang, W. G. Zhou, Z. B. Lu, H. Q. Li. UDoc-GAN: Unpaired document illumination correction with back-ground light prior. In Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal, pp. 5074\u20135082, 2022. DOI: https:\/\/doi.org\/10.1145\/3503161.3547916."},{"key":"1522_CR41","unstructured":"Z. Y. Zhou, Y. T. Lei, X. H. Chen, S. H. Luo, W. J. Zhang, C. M. Pun, Z. Wang. DocDeshadower: Frequency-aware transformer for document shadow removal, [Online], Available: https:\/\/arxiv.org\/abs\/2307.15318, 2023."},{"key":"1522_CR42","doi-asserted-by":"crossref","unstructured":"W. W. Chen, Y. T. Lei, S. H. Luo, Z. Y. Zhou, M. X. Li, C. M. Pun. ShaDocFormer: A shadow-attentive threshold detector with cascaded fusion refiner for document shadow removal, [Online], Available: https:\/\/arxiv.org\/abs\/2309.06670, 2023.","DOI":"10.1109\/IJCNN60899.2024.10651298"},{"key":"1522_CR43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095920","volume-title":"Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing","author":"K Georgiadis","year":"2023","unstructured":"K. Georgiadis, M. K. Yucel, E. Skartados, V. Dimaridou, A. Drosou, A. Sa\u00e0-Garriga, B. Manganelli. LP-IOANet: Efficient high resolution document shadow removal. In Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023. DOI: https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095920."},{"key":"1522_CR44","doi-asserted-by":"publisher","first-page":"12415","DOI":"10.1109\/ICCV51070.2023.01144","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z N Li","year":"2023","unstructured":"Z. N. Li, X. H. Chen, C. M. Pun, X. D. Cun. High-resolution document shadow removal via a large-scale real-world dataset and a frequency-aware shadow erasing net. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Paris, France, pp. 12415\u201312424, 2023. DOI: https:\/\/doi.org\/10.1109\/ICCV51070.2023.01144."},{"key":"1522_CR45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095403","volume-title":"Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing","author":"X H Chen","year":"2023","unstructured":"X. H. Chen, X. D. Cun, C. M. Pun, S. Q. Wang. ShadocNet: Learning spatial-aware tokens in transformer for document shadow removal. In Proceedings of ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023. DOI: https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095403."},{"key":"1522_CR46","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"A Dosovitskiy","year":"2021","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. H. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby. An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. In Proceedings of the 9th International Conference on Learning Representations, 2021."},{"key":"1522_CR47","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"O Ronneberger","year":"2015","unstructured":"O. Ronneberger, P. Fischer, T. Brox. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, pp. 234\u2013241, 2015. DOI: https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28."},{"key":"1522_CR48","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","volume-title":"Proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis","author":"Z W Zhou","year":"2018","unstructured":"Z. W. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, J. M. Liang. UNet++: A nested u-net architecture for medical image segmentation. In Proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis, Granada, Spain, pp. 3\u201311, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1."},{"key":"1522_CR49","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Hu","year":"2018","unstructured":"J. Hu, L. Shen, G. Sun. Squeeze-and-excitation networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 7132\u20137141, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00745."},{"key":"1522_CR50","doi-asserted-by":"publisher","unstructured":"B. S. Wang, C. L. P. Chen. Local water-filling algorithm for shadow detection and removal of document images. Sensors, vol. 20, no. 23, Article number 6929, 2020. DOI: https:\/\/doi.org\/10.3390\/s20236929.","DOI":"10.3390\/s20236929"},{"key":"1522_CR51","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1109\/ICCV.2019.00256","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Visio","author":"X W Hu","year":"2019","unstructured":"X. W. Hu, Y. T. Jiang, C. W. Fu, P. A. Heng. Mask-shadowGAN: Learning to remove shadows from unpaired data. In Proceedings of IEEE\/CVF International Conference on Computer Visio, Seoul, Republic of Korea, pp. 2472\u20132481, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00256."},{"key":"1522_CR52","doi-asserted-by":"publisher","first-page":"5007","DOI":"10.1109\/IC-CV48922.2021.00498","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Y Y Jin","year":"2021","unstructured":"Y. Y. Jin, A. Sharma, R. T. Tan. DC-ShadowNet: Single-image hard and soft shadow removal using unsupervised domain-classifier guided network. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 5007\u20135016, 2021. DOI: https:\/\/doi.org\/10.1109\/IC-CV48922.2021.00498."},{"key":"1522_CR53","doi-asserted-by":"publisher","unstructured":"X. Y. Li, B. Zhang, J. Liao, P. V. Sander. Document rectification and illumination correction using a patch-based CNN. ACM Transactions on Graphics, vol. 38, no. 6, Article number 168, 2019. DOI: https:\/\/doi.org\/10.1145\/3355089.3356563.","DOI":"10.1145\/3355089.3356563"},{"key":"1522_CR54","volume-title":"Proceedings of the 31st British Machine Vision Conference","author":"S Das","year":"2020","unstructured":"S. Das, H. A. Sial, K. Ma, R. Baldrich, M. Vanrell, D. Samaras. Intrinsic decomposition of document images in-the-wild. In Proceedings of the 31st British Machine Vision Conference, 2020."},{"key":"1522_CR55","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1145\/3474085.3475388","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"H Feng","year":"2021","unstructured":"H. Feng, Y. C. Wang, W. G. Zhou, J. J. Deng, H. Q. Li. DocTr: Document image transformer for geometric un-warping and illumination correction. In Proceedings of the 29th ACM International Conference on Multimedia, pp. 273\u2013281, 2021. DOI: https:\/\/doi.org\/10.1145\/3474085.3475388."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1522-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-024-1522-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1522-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:03:36Z","timestamp":1779361416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-024-1522-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,21]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1522"],"URL":"https:\/\/doi.org\/10.1007\/s11633-024-1522-4","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,21]]},"assertion":[{"value":"29 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}