{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T05:13:57Z","timestamp":1762060437305,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:00:00Z","timestamp":1659657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bingtuan Science and Technology Program","award":["2019BC008","2022DB005"],"award-info":[{"award-number":["2019BC008","2022DB005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Shadow removal is a fundamental task that aims at restoring dark areas in an image where the light source is blocked by an opaque object, to improve the visibility of shadowed areas. Existing shadow removal methods have developed for decades and yielded many promising results, but most of them are poor at maintaining consistency between shadowed regions and shadow-free regions, resulting in obvious artifacts in restored areas. In this paper, we propose a two-stage (i.e., shadow detection and shadow removal) method based on the Generative Adversarial Network (GAN) to remove shadows. In the shadow detection stage, a Recurrent Neural Network (RNN) is trained to obtain the attention map of shadowed areas. Then the attention map is injected into both generator and discriminator to guide the shadow removal stage. The generator is a dual encoder-decoder that processes the shadowed regions and shadow-free regions separately to reduce inconsistency. The whole network is trained with a spatial variant reconstruction loss along with the GAN loss to make the recovered images more natural. In addition, a novel feature-level perceptual loss is proposed to ensure enhanced images more similar to ground truths. Quantitative metrics like PSNR and SSIM on the ISTD dataset demonstrate that our method outperforms other compared methods. In the meantime, the qualitative comparison shows our approach can effectively avoid artifacts in the restored shadowed areas while keeping structural consistency between shadowed regions and shadow-free regions.<\/jats:p>","DOI":"10.3390\/info13080377","type":"journal-article","created":{"date-parts":[[2022,8,7]],"date-time":"2022-08-07T22:51:46Z","timestamp":1659912706000},"page":"377","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Attentive Generative Adversarial Network with Dual Encoder-Decoder for Shadow Removal"],"prefix":"10.3390","volume":"13","author":[{"given":"He","family":"Wang","sequence":"first","affiliation":[{"name":"Information Science Academy of China Electronics Technology Group Corporation, Beijing 100086, China"},{"name":"School of Computer Sciences, Wuhan University, Wuhan 430010, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3641-2686","authenticated-orcid":false,"given":"Hua","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Sciences, Wuhan University, Wuhan 430010, China"}]},{"given":"Dengyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Sciences, Wuhan University, Wuhan 430010, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1109\/TPAMI.2020.3025077","article-title":"Disentangling Monocular 3D Object Detection: From Single to Multi-Class Recognition","volume":"44","author":"Simonelli","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2246","DOI":"10.1109\/TPAMI.2020.3034435","article-title":"A Bayesian Filter for Multi-View 3D Multi-Object Tracking With Occlusion Handling","volume":"44","author":"Ong","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2732407","article-title":"Learning to remove soft shadows","volume":"34","author":"Gryka","year":"2015","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1109\/TPAMI.2012.214","article-title":"Paired regions for shadow detection and removal","volume":"35","author":"Guo","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1109\/TPAMI.2015.2462355","article-title":"Automatic shadow detection and removal from a single image","volume":"38","author":"Khan","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1109\/TPAMI.2017.2691703","article-title":"Leave-one-out kernel optimization for shadow detection and removal","volume":"40","author":"Vicente","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhu, L., Fu, C.-W., Qin, J., and Heng, P.-A. (2018, January 19\u201321). Direction-aware spatial context features for shadow detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00778"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4187","DOI":"10.1109\/TCSVT.2020.3047977","article-title":"Deshadownet: Learning from Synthetic Shadows for Shadow Detection and Removal","volume":"31","author":"Inoue","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, X., and Yang, J. (2018, January 19\u201321). Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00192"},{"key":"ref_10","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_11","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-C. (2015, January 7\u201310). Convolutional lstm network: A machine learning approach for precipitation nowcasting. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_12","unstructured":"Wang, Y., Tao, X., Qi, X., Shen, X., and Jia, J. (2018, January 3\u20138). Image inpainting via generative multi-column convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TPAMI.2006.18","article-title":"On the removal of shadows from images","volume":"28","author":"Finlayson","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s11263-009-0243-z","article-title":"Entropy minimization for shadow removal","volume":"85","author":"Finlayson","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.patcog.2015.09.006","article-title":"New spectrum ratio properties and features for shadow detection","volume":"51","author":"Tian","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lalonde, J.-F., Efros, A.A., and Narasimhan, S.G. (2010, January 5\u201311). Detecting ground shadows in outdoor consumer photographs. Proceedings of the European Conference on Computer Vision, Crete, Greece.","DOI":"10.1007\/978-3-642-15552-9_24"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Guo, R., Dai, Q., and Hoiem, D. (2011, January 21\u201323). Single-image shadow detection and removal using paired regions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995725"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Vicente, Y., Tomas, F., Hoai, M., and Samaras, D. (2015, January 13\u201316). Leave-one-out kernel optimization for shadow detection. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.387"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhu, J., Samuel, K.G., Masood, S.Z., and Tappen, M.F. (2010, January 13\u201318). Learning to recognize shadows in monochromatic natural images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540209"},{"key":"ref_20","unstructured":"Huang, X., Hua, G., Tumblin, J., and Williams, L. (2011, January 6\u201313). What characterizes a shadow boundary under the sun and sky?. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Le, H., Vicente, Y., Tomas, F., Nguyen, V., Hoai, M., and Samaras, D. (2018, January 8\u201314). A+d net: Training a shadow detector with adversarial shadow attenuation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_41"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Qiao, X., Cao, Y., and Lau, R. (2019, January 15\u201320). Distraction-Aware Shadow Detection. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00531"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhu, L., Deng, Z., Hu, X., Fu, C.-W., Xu, X., Qin, J., and Heng, P.-A. (2018, January 8\u201314). Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01231-1_8"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nguyen, V., Vicente, T.F.Y., Zhao, M., Hoai, M., and Samaras, D. (2017, January 22\u201329). Shadow detection with conditional generative adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.483"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhao, X., Li, Y., Hu, X., Huang, K., and Cripac, N. (2018, January 13\u201319). Densely cascaded shadow detection network via deeply supervised parallel fusion. Proceedings of the IJCAI, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/140"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Khan, S.H., Bennamoun, M., Sohel, F., and Togneri, R. (2014, January 23\u201328). Automatic feature learning for robust shadow detection. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.249"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Vicente, T.F.Y., Hou, L., Yu, C.-P., Hoai, M., and Samaras, D. (2016, January 11\u201314). Large-scale training of shadow detectors with noisily-annotated shadow examples. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46466-4_49"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2795","DOI":"10.1109\/TPAMI.2019.2919616","article-title":"Direction-Aware Spatial Context Features for Shadow Detection and Removal","volume":"42","author":"Hu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1109\/TCSVT.2021.3074143","article-title":"Adaptive Feature Fusion and Spatio-Temporal Background Modeling in KDE Framework for Object Detection and Shadow Removal","volume":"32","author":"Sahoo","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1109\/TIP.2020.3048677","article-title":"Shadow Removal by a Lightness-Guided Network With Training on Unpaired Data","volume":"30","author":"Liu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Fu, L., Zhou, C., Guo, Q., Xu, F., Yu, H., Feng, W., Liu, Y., and Wang, S. (2021, January 19\u201325). Auto-Exposure Fusion for Single-Image Shadow Removal. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01043"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, Z., Long, C., Zhang, L., and Xiao, C. (2021, January 10\u201317). CANet: A Context-Aware Network for Shadow Removal. Proceedings of the IEEE International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00470"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MSP.2008.930649","article-title":"Mean squared error: Love it or leave it? A new look at signal fidelity measures","volume":"26","author":"Wang","year":"2009","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_34","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large scale image recognition. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.-F. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gong, H., and Cosker, D. (2014, January 1\u20135). Interactive shadow removal and ground truth for vari-able scene categories. Proceedings of the BMVC, Nottingham, UK.","DOI":"10.5244\/C.28.36"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/8\/377\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:04:54Z","timestamp":1760141094000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/8\/377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,5]]},"references-count":37,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["info13080377"],"URL":"https:\/\/doi.org\/10.3390\/info13080377","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2022,8,5]]}}}