隨著科技的高速發展，深度學習在工業、軍事、民生科技處處都有大量的應用，現今運用在影像處理上的深度學習技術不斷進步，影像的去除如影像除霧、去反光、去陰影等都是電腦視覺領域中具挑戰性的任務。本論文研究目的為針對影像陰影去除提出了迭代推進生成對抗網路，首先我們輸入陰影圖藉由兩個生成器網路分別生成出無陰影的圖及殘差陰影圖，將兩者合成得到陰影圖，與輸入進行比對，最後將合成的圖再次輸入至網路重複上述步驟直到收斂，透過迭代推進的方式提升陰影移除的效果。此外為了使結果更加優異，我們的生成器網路加入了注意力機制，讓模型更專注於影子的部分，以及長短期記憶，使我們在長序列訓練過程中有更好的表現，最後是修復網路，以進一步改善生成的結果。我們與傳統方法以及近年來基於深度學習所提出的陰影去除方法比較，實驗結果表明本論文所提出的迭代推進方法有更優異的結果。

With the rapid development of technology. Deep learning used in image processing is constantly advancing. Image removal such as image haze removal, reflection removal and shadow removal are all challenging tasks in the field of computer vision. The purpose of this paper is to propose an iterative advance generative adversarial network for image shadow removal. First, we input the shadow image through two generator networks to produce shadow-free image and residual shadow. The outputs of the two networks are combined to compare the input image. Through an iteratively advance manner, the effect of shadow removal has a great improvement. In order to make the results more excellent. The generators networks contain attention mechanism so models can more focus on the shadow portion and the Long Short-Term Memory to improve training through long sequence training. Then an inpainting network is applied to further improve the results.

[1] R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti, “Improving shadow suppression in moving object detection with HSV color information,” Intelligent Transportation Systems, pp.334–339, 2002.
[2] C. Long, and G. Hua, “Multi-class multi-annotator active learning with robust gaussian process for visual recognition,” in Proceedings of IEEE International Conference on Computer Vision, pp. 2839–2847, 2015.
[3] G. Hua, C. Long, M. Yang, and Y. Gao, “Collaborative active visual recognition from crowds: A distributed ensemble approach,” IEEE transactions on pattern analysis and machine intelligence, pp. 582–594, 2018.
[4] G. Hua, C. Long, M. Yang, and Y. Gao, “Collaborative active learning of a kernel machine ensemble for recognition,” in Proceedings of IEEE International Conference on Computer Vision, pp. 1209–1216, 2013.
[5] C. Long and G. Hua, “Correlational gaussian processes for cross-domain visual recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 118–126, 2017.
[6] I. Miki, P. C. Cosman, G. T. Kogut, and M. M. Trivedi, “Moving shadow and object detection in traffic scenes,” in Proceedings of International Conference on Pattern Recognition, pp. 321–324, 2000.
[7] W. Luo, P. Sun, F. Zhong, W. Liu, T. Zhang, and Y. Wang, “End-to-end active object tracking and its real-world deployment via reinforcement learning,” IEEE Transactions on Pattern Analysis Machine Intelligence, pp. 1317–1332, 2019.
[8] C. Long, X. Wang, G. Hua, M. Yang, and Y. Lin, “Accurate object detection with location relaxation and regionlets re-localization,” Asian Conference on Computer Vision, pp. 260–275, 2014.
[9] G. Maciej, T. Michael, and J. B. Gabriel, “Learning to remove soft shadows,” ACM Transactions on Graphics. pp. 1–15, 2015.
[10] Q. Yang, K. H. Tan, and N. Ahuja, “Shadow removal using bilateral filtering,” IEEE Transactions on Image Processing, pp. 4361–4368, 2012.
[11] V. T. Yago, H. Minh, and S. Dimitris, “Leave-one-out kernel optimization for shadow detection and removal,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 682–695, 2017.
[12] X. Hu, C. W. Fu, L. Zhu, J. Qin, and P. A. Heng, “Direction-aware spatial context features for shadow detection and removal,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.2795–2808, 2019.
[13] L. Qu, J. Tian, S. He, Y. Tang, and R. W. H. Lau, “DeshadowNet: A multi-context embedding deep network for shadow removal,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 4067–4075, 2017.
[14] D. Bin, L. C. Jiang, Z. Ling, and X. C. Xia, “Argan: Attentive recurrent generative adversarial network for shadow detection and removal,” in Proceedings of IEEE International Conference on Computer Vision, pp. 10213–10222, 2019.
[15] K. He, Y. Li, S. Soundarajan, and J. E. Hopcroft, “Hidden community detection in social networks,” Information Sciences, pp. 92–106, 2018.
[16] X. Shi, Z. Chen, H. Wang, D. Y. Yeung, W. K. Wong, and W. c. Woo, “Convolutional lstm network: A machine learning approach for precipitation nowcasting,” Advances in neural information processing systems, pp. 802–810, 2015.
[17] Y. Y. Chuang, D. B. Goldman, B. Curless, D. H. Salesin, and R. Szeliski, “Shadow matting and compositing,” ACM Transactions on Graphics, pp.494–500, 2003.

[18] L. Zhang, Q. Zhang, and C. Xiao, “Shadow remover: Image shadow removal based on illumination recovering optimization,” IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 4623–4636 2015.
[19] H. Le, and D. Samaras, “Shadow removal via shadow image decomposition,” in Proceedings of IEEE International Conference on Computer Vision, pp. 8578–8587, 2019.
[20] T. Porter, and T. Duff, “Compositing digital images,” in Proceedings of Computer graphics and interactive techniques, vol. 18, no. 3, pp. 253–259, 1984.
[21] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, “Self-attention generative adversarial networks,” International Conference on machine learning, pp. 7354–7363, 2018.
[22] T. P. Wu, C. K. Tang, M. S. Brown, and H. Y. Shum, “Natural shadow matting,” ACM Transactions on Graphics, pp.8–es, 2007.
[23] C. Xiao, R. She, D. Xiao, and K. L. Ma, “Fast shadow removal using adaptive multi-scale illumination transfer,” Computer Graphics Forum, volume 32, pp. 207–218 , 2013.
[24] A. Mohan, J. Tumblin, and P. Choudhury, “Editing soft shadows in a digital photograph,” IEEE Computer Graphics and Applications, pp. 23–31, 2007.
[25] G. Ruiqi, D. Qieyun, and H. Derek, “Paired regions for shadow detection and removal,” IEEE transactions on pattern analysis and machine intelligence, pp. 2956–2967, 2012.
[26] S. H. Khan, M. Bennamoun, F. Sohel, and R. Togneri, “Automatic feature learning for robust shadow detection,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1939–1946, 2014.
[27] W. Jifeng, L. Xiang, and Y. Jian, “Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1788–1797, 2018.
[28] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” Advances in Neural Information Processing Systems, 2014.
[29] C. Li, and M. Wand. “Precomputed real-time texture synthesis with markovian generative adversarial networks,” in Proceedings of European Conference on Computer Vision, pp. 702–716, 2016.
[30] C. Ledig, L. Theis, F. Husz´ar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang and W. Shi, ”Photo-realistic single image super-resolution using a generative adversarial network,” in Proceedings of IEEE Conference on computer vision and pattern recognition, pp. 702–716, 2017.
[31] P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, “Image to-image translation with conditional adversarial networks,” in Proceedings of IEEE Conference on computer vision and pattern recognition, pp. 1125–1134, 2017.
[32] D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, and A. A. Efros, “Context encoders: Feature learning by inpainting,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536–2544, 2016.
[33] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate.” arXiv preprint arXiv: 1409.0473, 2014.
[34] J. K. Chorowski, D. Bahdanau, D. Serdyuk, K. Cho, and Y. Bengio, “Attention-based models for speech recognition,” Advances in neural information processing systems, 2015.
[35] L. Gao, X. Li, J. Song, and H. T. Shen, “Hierarchical lstms with adaptive attention for visual captioning,” IEEE Transactions on Pattern Analysis Machine Intelligence, pp. 2482–2491, 2019.
[36] D. Kiela, C. Wang, and K. Cho, “Dynamic meta-embeddings for improved sentence representations,” arXiv preprint arXiv:1804.07983, 2018.
[37] R. Guo, Q. Dai, and D. Hoiem, “Single-image shadow detection and removal using paired regions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.2033–2040, 2011.
[38] X. Hu, Y. Jiang, C.W. Fu, and P.A. Heng, “Mask-ShadowGAN: Learning to remove shadows from unpaired data,” in Proceedings of IEEE International Conference on Computer Vision, pp.2472–2481, 2019.
[39] X. Cun, C. M. Pun, and C. Shi, “Towards ghost-free shadow removal via dual hierarchical aggregation network and shadow matting gan,” in Proceedings of AAAI, pp. 10680–10687, 2020.