RETRACTED: Advanced Unpaired Shadow Manipulation via Adversarial Generation and Image Partitioning
Keywords:
Deep Learning, Shadow Generation, Shadow Removal, Adversarial Networks, Weakly Supervised LearningAbstract
RETRACTED
This article was retracted on September 12, 2026, at the request of the author. Following publication, the author and the research group identified issues concerning the data and experimental results that may affect the reliability of the findings.
Readers are advised not to rely on or cite the findings of this article as valid research results.
For further information, please see the Retraction Notice: http://www.dawnclarity.press/index.php/ijaaa/announcement/view/4
Retraction date: [September 12, 2026]
Accurate shadow processing is critical for perceptual realism in image synthesis, yet current methods often rely heavily on paired data. We propose two adversarial frameworks for shadow manipulation using unpaired data. For generation, a two-stage CycleGAN with attention predicts masks and synthesizes high-fidelity shadows without paired images. For removal, a weakly-supervised method uses patch extraction to construct intra-image training pairs and cycle-consistency to eliminate shadows without ground-truth unshaded images. Experiments on DESOBA and ISTD datasets demonstrate our methods achieve superior or competitive performance.
References
I. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., "Generative adversarial nets," in Advances in Neural Information Processing Systems, 2014, pp. 2672–2680.
J. Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 2242–2251.
P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, "Image-to-image translation with conditional adversarial networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 1125–1134.
X. Hu, Y. Jiang, C. W. Fu, and P. A. Heng, "Mask-ShadowGAN: Learning to remove shadows from unpaired data," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 2472–2481.
D. Liu, C. Long, H. Zhang, et al., "ARShadowGAN: Shadow generative adversarial network for augmented reality in single light scenes," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 8139–8148.
S. Zhang, R. Liang, and M. Wang, "ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networks," Comput. Visual Media, vol. 5, no. 1, pp. 105–115, 2019.
Z. Liu, H. Yin, Y. Mi, et al., "Shadow removal by a lightness-guided network with training on unpaired data," IEEE Trans. Image Process., vol. 30, pp. 1853–1865, 2021.
Y. Jin, A. Sharma, and R. T. Tan, "DC-ShadowNet: Single-image hard and soft shadow removal using unsupervised domain-classifier guided network," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2021, pp. 5027–5036.
H. Le and D. Samaras, "Shadow removal via shadow image decomposition," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 8578–8587.
J. Wang, X. Li, and J. Yang, "Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 1788–1797.
L. Qu, J. Tian, S. He, et al., "Deshadownet: A multi-context embedding deep network for shadow removal," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4067–4075.
H. Le and D. Samaras, "From shadow segmentation to shadow removal," in Computer Vision – ECCV 2020, 2020, pp. 264–281.
Z. Liu, H. Yin, X. Wu, et al., "From shadow generation to shadow removal," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 4927–4936.
Y. Hong, L. Niu, and J. Zhang, "Shadow generation for composite image in real-world scenes," in Proc. AAAI Conf. Artif. Intell., vol. 36, no. 1, 2022, pp. 914–922.
Q. Liu, J. Wang, and L. Niu, "DESOBAv2: Towards large-scale real-world dataset for shadow generation," arXiv preprint arXiv:2308.09972, 2023.
H. Le, T. F. Y. Vicente, V. Nguyen, et al., "A+D Net: Training a shadow detector with adversarial shadow attenuation," in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 662–678.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
C. Li and M. Wand, "Precomputed real-time texture synthesis with markovian generative adversarial networks," in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 702–716.
M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein generative adversarial networks," in Int. Conf. Mach. Learn. (ICML), 2017, pp. 214–223.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.
G. Huang, Z. Liu, L. Van Der Maaten, et al., "Densely connected convolutional networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700–4708.
L. C. Chen, G. Papandreou, I. Kokkinos, et al., "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs," IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834–848, 2017.
V. Badrinarayanan, A. Kendall, and R. Cipolla, "Segnet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, 2017.
H. Zhao, J. Shi, X. Qi, et al., "Pyramid scene parsing network," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 2881–2890.
C. Szegedy, W. Liu, Y. Jia, et al., "Going deeper with convolutions," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2015, pp. 1–9.
S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in Int. Conf. Mach. Learn. (ICML), 2015, pp. 448–456.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
R. Guo, Q. Dai, and D. Hoiem, "Paired regions for shadow detection and removal," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 12, pp. 2956–2967, 2012.
M. Gryka, M. Terry, and G. J. Brostow, "Learning to remove soft shadows," ACM Trans. Graph. (TOG), vol. 34, no. 5, pp. 1–15, 2015.
C. Xiao, R. She, D. Xiao, and K. L. Ma, "Fast shadow removal using adaptive multiscale illumination transfer," Comput. Graph. Forum, vol. 32, no. 8, pp. 207–218, 2013.
S. H. Khan, M. Bennamoun, F. Sohel, and R. Togneri, "Automatic shadow detection and removal from a single image," IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 3, pp. 431–446, 2015.
G. D. Finlayson, M. S. Drew, and C. Lu, "Entropy minimization for shadow removal," Int. J. Comput. Vis., vol. 85, no. 1, pp. 35–57, 2009.
I. Sato, Y. Sato, and K. Ikeuchi, "Illumination from shadows," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 3, pp. 290–300, 2003.
A. Panagopoulos, C. Wang, D. Samaras, and N. Paragios, "Illumination estimation and cast shadow detection through a higher-order graphical model," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2011, pp. 673–680.
T. Kim, M. Cha, H. Kim, et al., "Learning to discover cross-domain relations with generative adversarial networks," in Int. Conf. Mach. Learn. (ICML), 2017, pp. 1857–1865.
Z. Yi, H. Zhang, P. Tan, and M. Gong, "Dualgan: Unsupervised dual learning for image-to-image translation," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 2849–2857.
Y. Choi, M. Choi, M. Kim, et al., "Stargan: Unified generative adversarial networks for multi-domain image-to-image translation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 8789–8797.
S. Tulyakov, M. Y. Liu, X. Yang, and J. Kautz, "Mocogan: Decomposing motion and content for video generation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 1526–1535.
V. Nguyen, T. F. Yago Vicente, M. Zhao, et al., "Shadow detection with conditional generative adversarial networks," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 4510–4518.
X. Hu, L. Zhu, C. W. Fu, et al., "Direction-aware spatial context features for shadow detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7454–7462.
L. Zhu, Z. Deng, X. Hu, et al., "Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection," in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 121–136.
K. Zhou, J. L. Fang, W. Wu, et al., "Semantic-aware Transformer for shadow detection," Comput. Vis. Image Underst., vol. 240, art. no. 103941, 2024.
I. Arief, S. McCallum, and J. Y. Hardeberg, "Realtime estimation of illumination direction for augmented reality on mobile devices," in Color and Imaging Conf., 2012, pp. 111–116.
K. Karsch, V. Hedau, D. Forsyth, and D. Hoiem, "Rendering synthetic objects into legacy photographs," ACM Trans. Graph. (TOG), vol. 30, no. 6, pp. 1–12, 2011.
B. Liao, Y. Zhu, C. Liang, et al., "Illumination animating and editing in a single picture using scene structure estimation," Comput. Graph., vol. 82, pp. 53–64, 2019.
P. P. Srinivasan, B. Deng, X. Zhang, et al., "Nerv: Neural reflectance and visibility fields for relighting and view synthesis," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 7495–7504.
H. Gong and D. Cosker, "Interactive removal and ground truth for difficult shadow scenes," J. Opt. Soc. Am. A, vol. 33, no. 9, pp. 1798–1811, 2016.
N. Su, Y. Zhang, S. Tian, et al., "Shadow detection and removal for occluded object information recovery in urban high-resolution panchromatic satellite images," IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 9, no. 6, pp. 2568–2582, 2016.
H. M. Le, B. C. Goncalves, D. Samaras, et al., "Weakly labeling the Antarctic: The penguin colony case," in CVPR Workshops, 2019, pp. 18–25.
