自然影像和影片通常含有陰影，但是陰影可能會影響演算法的效能。當處理含有陰影的輸入影像時，為了避免產生錯誤，進行陰影移除是必要的。
本論文提出了一種基於Lab色彩空間特性的陰影去除網路架構。此方法有兩個階段，第一個階段是一個雙層的注意力機制網路架構，用來去除陰影，而第二階段的網路則是負責陰影去除後圖像的色彩修正。所提出的方法，僅需要陰影影像進行訓練，並不需要陰影遮罩和無陰影圖像作為輸入，在測試時也只需要陰影影像即可生成無陰影圖像。實驗結果顯示，在比較方法當中，本論文所提出的方法，得到了很好的成績。

Real images and videos often contain shadows, but shadows may affect the performance of the algorithm. When processing input images that contain shadows, shadow removal is necessary to avoid errors.
In this Thesis, a shadow removal network architecture based on the Lab color space is proposed. This method has two stages, the first stage is a dual hierarchical attention network architecture for shadow removal, and the second stage network is responsible for color correction of the image after shadow removal. And the proposed method requires only shadow images for training and does not require shadow masks or non-shadow images, and only shadow images are needed to generate shade-free images for testing. The experimental results show that the proposed method achieves good results in the comparative methods.

[1] Graham D Finlayson, Steven D Hordley, Cheng Lu, and Mark S Drew. On the removal of shadows from images. IEEE transactions on pattern analysis and machine intelligence ( Volume: 28), 2005.
[2] Graham D Finlayson, Mark S Drew, and Cheng Lu. Entropy minimization for shadow removal. International Journal of Computer Vision ( Volume: 85), 2009.
[3] Hieu Le, Dimitris Samaras. Shadow Removal via Shadow Image Decomposition. In Proceedings of the International Conference on Computer Vision (ICCV), 2019.
[4] X. Hu, Y. Jiang, C.-W. Fu, and P.-A. Heng, Mask-shadowgan: learning to remove shadows from unpaired data. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019.
[5] Yeying Jin; Aashish Sharma; Robby T. Tan. DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network. In Proceedings of the International Conference on Computer Vision (ICCV), 2021.
[6] J. Zhu, T. Park, P. Isola, and A. A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the International Conference on Computer Vision (ICCV), 2017.
[7] Zhihao Liu, Hui Yin, Yang Mi, Mengyang Pu, Song Wang. Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data. IEEE transaction on image processing ( Volume: 30).
[8] Xin-An Jiang. A Cycle Generative Adversarial Networks Based Shadow Removal Algorithm.
[9] Shengfeng He; Bing Peng; Junyu Dong; Yong Du. Mask-ShadowNet: Toward Shadow Removal via Masked Adaptive Instance Normalization. IEEE Signal Processing Letters ( Volume: 28).
[10] Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Jing Qin, Pheng-Ann Heng. Direction-aware Spatial Context Features for Shadow Detection and Removal. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[11] Xiaodong Cun, Chi-Man Pun, Cheng Shi1. Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), 2019.
[12] Yu, F., and Koltun, V. Multiscale context aggregation by dilated convolutions. In Proceedings of the International Conference on Learning Representations (ICLR), 2016.
[13] Ryo Abiko; Masaaki Ikehara. Channel Attention GAN Trained With Enhanced Dataset for Single-Image Shadow Removal. IEEE Access ( Volume: 10).
[14] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations (ICLR), 2015.
[15] Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon. CBAM: Convolutional Block Attention Module. In Proceedings of the European Conference on Computer Vision (ECCV), 2018.
[16] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[17] Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger. Densely Connected Convolutional Networks. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[18] Yu, F.; Wang, D.; Shelhamer, E.; and Darrell, T. Deep Layer Aggregation. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[19] Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu. Squeeze-and-Excitation Networks. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[20] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
[21] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. In Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.
[22] Zhang, R. Isola, P. Efros, A. A. Shechtman, E., and Wang, O. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[23] J. Wang, X. Li, and J. Yang. Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[24] A. Shrivastava, T. Pfister, O. Tuzel, J. Susskind, W. Wang, and R. Webb. Learning from simulated and unsupervised images through adversarial training. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[25] J. Johnson, A. Alahi, and L. Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In Proceedings of the European Conference on Computer Vision (ECCV), 2016.
[26] Mahendran, A., Vedaldi, A. Understanding deep image representations by inverting them. In Proceedings of the IEEE Conf. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), 2015.
[27] L. Qu, J. Tian, S. He, Y. Tang, and R. W. Lau. Deshadownet: A multi-context embedding deep network for shadow removal. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[28] J. Wang, X. Li, and J. Yang. Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018.
[29] Q. Yang, K.-H. Tan, and N. Ahuja. Shadow removal using bilateral filtering. In Proceedings of the IEEE Transactions on Image Processing (TIP), 2012.
[30] R. Guo, Q. Dai, and D. Hoiem. Paired regions for shadow detection and removal. In Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2013.
[31] H. Gong and D. Cosker. Interactive shadow removal and ground truth for variable scene categories. In Proceedings of the British Machine Vision Conference (BMVC).
[32] Ling Zhang, Chengjiang Long, Xiaolong Zhang, Chunxia Xiao. RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), 2020.
[33] Hu, X.; Jiang, Y.; Fu, C.-W.; and Heng, P.- A. Mask-shadowgan: Learning to remove shadows from unpaired data. In Proceedings of the International Conference on Computer Vision (ICCV), 2019.
[34] Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia. Limited Pyramid Scene Parsing Network. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), 2017.