拍攝照片過程中的反光現象不僅會降低圖片的品質，當利用這些圖片來做一些電腦視覺的任務像是物件偵測、語意分割以及圖像分類的時候，也會影響它們所得到的表現。本論文提出了一個基於生成對抗網路的影像去反光演算法。
此方法包含了一個生成器和一個判別器，其中生成器使用了高效的殘差密集模塊以及注意力模塊來產生乾淨的圖片，而判別器則用來判別真實的圖片相對於生成的圖片更真實的機率。
實驗結果顯示，本論文提出的方法，相較於其他方法，在客觀影像評估標
準以及主觀的影像品質上皆有較好的表現。

Reflection when taking photos not only degrades the quality of images, but also influences the performance of some computer vision tasks like object detection, semantic segmentation, and image classification when using these images. In this Thesis, an image reflection removal algorithm based on the generative adversarial network is proposed. It contains a generator and a discriminator. The generator utilizes efficient residual dense blocks and attention modules to generate clean images for output. The discriminator is used to estimate the probability that the real image is relatively more realistic than the image generated from the generator.
The experimental results show that the proposed approach has better performance than other methods on subjective visual quality and objective measurement.

[1] Y. Y. Schechner, N. Kiryati, and R. Basri. Separation of transparent layers using focus. IJCV, 2000.
[2] N. Kong, Y.-W. Tai, and J. S. Shin. A physically-based approach to reflection separation: from physical modeling to constrained optimization. PAMI, 2014.
[3] A. Levin and Y. Weiss. User assisted separation of reflections from a single image using a sparsity prior. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 29(9):1647–1654, 2007.
[4] B.-J. Han and J.-Y. Sim. Reflection removal using low-rank matrix completion. In CVPR, 2017.
[5] Yu Li and Michael S Brown. Single image layer separation using relative smoothness. In CVPR, pages 2752–2759, 2014.
[6] R. Wan, B. Shi, T. A. Hwee, and A. C. Kot. Depth of field guided reflection removal. In ICIP, 2016.
[7] Y. Shih, D. Krishnan, F. Durand, and W. T. Freeman, “Reflection removal using ghosting cues,” in Proc. Computer Vision and Pattern Recognition (CVPR), 2015.
[8] Q. Fan, J. Yang, G. Hua, B. Chen, and D. Wipf. A generic deep architecture for single image reflection removal and image smoothing. In IEEE International Conference on Computer Vision (ICCV), pages 3238–3247, 2017.
[9] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
[10] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C Kot. Crrn: multi-scale guided concurrent reflection removal network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4777– 4785, 2018.
[11] Xuaner Zhang, Ren Ng, and Qifeng Chen. Single image reflection separation with perceptual losses. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4786–4794, 2018.
[12] J. Johnson, A. Alahi, and L. Feifei. Perceptual losses for real-time style transfer and super-resolution. European Conference on Computer Vision (ECCV), pages 694–711, 2016.
[13] Jie Yang, Dong Gong, Lingqiao Liu, and Qinfeng Shi. Seeing deeply and bidirectionally: A deep learning approach for single image reflection removal. In Proceedings of the European Conference on Computer Vision (ECCV), pages 654– 669, 2018.
[14] Qiang Wen, Yinjie Tan, Jing Qin, Wenxi Liu, Guoqiang Han, and Shengfeng He. Single image reflection removal beyond linearity. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3771– 3779, 2019.
[15] Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, and Hua Huang. Single image reflection removal exploiting misaligned training data and network enhancements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8178–8187, 2019.
[16] Ryo Abiko and Masaaki Ikehara Single Image Reflection Removal based on GAN with Gradient Constraint, in IEEE Access, Vol. 7, pp. 148790-148799 Oct. 2019.
[17] Chao Li, Yixiao Yang, Kun He, Stephen Lin, and John E Hopcroft. Single image reflection removal through cascaded refinement. In CVPR, 2020.
[18] Xingjian SHI, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-Kin Wong, and WangChun Woo. Convolutional lstm network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems, pages 802–810, 2015.
[19] Soomin Kim, Yuchi Huo, and Sung-Eui Yoon. Single image reflection removal with physically-based training images. In IEEE Conf. Comput. Vis. Pattern Recog., pages 5164–5173, 2020.
[20] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In International Conference on Machine Learning (ICLR), 2015.
[21] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV), 115(3):211– 252, 2015.
[22] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.
[23] J. Hu, L. Shen, and G. Sun. Squeeze-and-excitation networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
[24] K. He, X. Zhang, S. Ren, and J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(9):1904–1916, 2015.
[25] B. Hariharan, P. Arbelaez, R. Girshick, and J. Malik. Hypercolumns for object
segmentation and fine-grained localization. In The IEEE Conference on Computer
Vision and Pattern Recognition (CVPR), June 2015.
[26] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In NeurIPS, pages 2672–2680, 2014.
[27] Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard gan. arXiv preprint arXiv:1807.00734, 2018
[28] Yuxin Wu, Kaiming He, “Group Normalization”, in ECCV, 2018.
[29] Vinod Nair and Geoffrey E Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), pages 807–814, 2010.
[30] Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. Rectifier nonlinearities improve neural network acoustic models. In Proc. icml, volume 30, page 3, 2013.
[31] Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289, 2015.
[32] Günter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter.
Selfnormalizing neural networks. In Advances in neural information processing
systems, pages 971–980, 2017.
[33] Prajit Ramachandran, Barret Zoph, and Quoc V Le. Searching for activation functions. arXiv preprint arXiv:1710.05941, 2017.
[34] Diganta Misra. Mish: A self regularized nonmonotonic neural activation function. arXiv preprint arXiv:1908.08681, 2019.
[35] Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. Residual dense network for image super-resolution. In CVPR, pages 2472–2481, 2018.
[36] Dehua Song, Chang Xu, Xu Jia, Yiyi Chen, Chunjing Xu, Yunhe Wang. Efficient Residual Dense Block Search for Image Super-Resolution. In AAAI, pages 12007–12014, 2020.
[37] Zhang, X.; Zhou, X.; Lin, M.; and Sun, J. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6848–6856, 2018.
[38] F. Chollet. Xception: Deep learning with depthwise separable convolutions. arXiv preprint arXiv:1610.02357, 2016.
[39] S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. arXiv preprint arXiv:1611.05431, 2016.
[40] S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, ‘‘CBAM: Convolutional block attention module,’’ in Proc. Eur. Conf. Comput. Vis., 2018, pp. 3–19.
[41] Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image superresolution using very deep residual channel attention networks. In ECCV, pages 286–301, 2018.
[42] Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C Kot. Benchmarking single-image reflection removal algorithms. In Proceedings of the IEEE International Conference on Computer Vision, pages 3922–3930, 2017.