本論文旨在解決於單一影像去反射 (SIRR) 的問題。在日常生活中，當我們隔著具有反射和透明度屬性的介質如窗戶、玻璃等物品拍照 時，所拍攝到的影像通常具有多餘的反射現象，這些反射的區域會遮 擋到或模糊了我們實際想要拍攝的背景，除了會影響視覺品質外，還可能降低下游電腦視覺任務的性能。單一影像去反射的目的為移除不 想要的反射部分，並還原至乾淨的背景。現今已有基於深度學習為的 方法透過在模型中加入VGG 特徵、邊緣先驗和語言資訊的方式順利 得將反射去除。然而，這些方法卻有所限制，因為它們直接使用繁複 的模型將反射影像輸入映射回乾淨的背景，而沒有正視根本原因。為了解決這個問題，我們利用從輸入產生的多曝光值 (EVs) 影像中萃取 的多尺度特徵，進而提出一個多尺度、多曝光的去反射網路。由於降低曝光值後影像含有較弱的反射，有利於反射與背景層的解耦，因此 多曝光值、多尺度的設計可利用這些特徵來解決問題，經實驗表明， 本論文提出的模型即使在反射型態千變萬化的真實世界場景中也能將之去除，其表現也優於最先進的去反射方法。

This thesis focuses on the problem of Single image reflection removal (SIRR). When taking photographs through reflective materials, there is often an unwanted reflection area in the image. The purpose of SIRR is to remove the undesired reflection part and restore the original scene. Existing deep learning-based methods have achieved success by incorporating VGG features, edge priors and linguistic information into the model. However, these methods often have limitations, as they directly map inputs to clean background using sophisticated models without confronting the root cause. To address the ill-posedness of this problem, we propose a multi-scale, multi-exposure reflection removal network to leverages hierarchical multi-scale features extracted from images at multiple exposure values (EVs) generated from the input. As low EV images contain weaker reflections, the multi-EVs, multi-scale design can leverage these features to simplify the ill-posed problem and remove reflection even in real-world scenarios where reflection patterns random and complex.

[1] Nikolaos Arvanitopoulos, Radhakrishna Achanta, and Sabine Susstrunk. Single image reflection suppression. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4498–4506, 2017.
[2] Yakun Chang, Cheolkon Jung, and Jun Sun. Joint reflection removal and depth estimation from a single image. IEEE Transactions on Cybernetics, 51(12):5836– 5849, 2020.
[3] Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, and Jian Sun. Simple baselines for image restoration. In European conference on computer vision, pages 17–33. Springer, 2022.
[4] Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu, Min-Hung Chen, Hou-Ning Hu, Wen- Hsiao Peng, and Yen-Yu Lin. Learning continuous exposure value representations for single-image hdr reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12990–13000, 2023.
[5] Sung-Jin Cho, Seo-Won Ji, Jun-Pyo Hong, Seung-Won Jung, and Sung-Jea Ko. Rethinking coarse-to-fine approach in single image deblurring. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4641–4650, 2021.
[6] Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, and Rynson WH Lau. Location-aware single image reflection removal. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5017–5026, 2021.
[7] Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. The pascal visual object classes (voc) challenge. International journal of computer vision, 88:303–338, 2010.
[8] Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, and David Wipf. A generic deep architecture for single image reflection removal and image smoothing. In Proceedings of the IEEE International Conference on Computer Vision, pages 3238–3247, 2017.
[9] Xin Feng, Wenjie Pei, Zihui Jia, Fanglin Chen, David Zhang, and Guangming Lu. Deep-masking generative network: A unified framework for background restoration from superimposed images. IEEE Transactions on Image Processing, 30:4867-4882, 2021.
[10] Xiaojie Guo, Xiaochun Cao, and Yi Ma. Robust separation of reflection from multiple images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2187–2194, 2014.
[11] Byeong-Ju Han and Jae-Young Sim. Reflection removal using low-rank matrix completion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5438–5446, 2017.
[12] Jie Hu, Li Shen, and Gang Sun. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7132–7141, 2018.
[13] Qiming Hu and Xiaojie Guo. Trash or treasure? an interactive dual-stream strategy for single image reflection separation. Advances in Neural Information Processing Systems, 34:24683–24694, 2021.
[14] Qiming Hu and Xiaojie Guo. Single image reflection separation via component synergy. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13138–13147, 2023.
[15] Diederik P Kingma. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
[16] Chenyang Lei and Qifeng Chen. Robust reflection removal with reflection-free flash-only cues. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14811–14820, 2021.
[17] Anat Levin and Yair Weiss. User assisted separation of reflections from a single image using a sparsity prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(9):1647–1654, 2007.
[18] Anat Levin, Assaf Zomet, and Yair Weiss. Learning to perceive transparency from the statistics of natural scenes. Advances in Neural Information Processing Systems, 15, 2002.
[19] Chao Li, Yixiao Yang, Kun He, Stephen Lin, and John E Hopcroft. Single image reflection removal through cascaded refinement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3565–3574, 2020.
[20] Xiang Li, Wenhai Wang, Xiaolin Hu, and Jian Yang. Selective kernel networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 510–519, 2019.
[21] Yu Li and Michael S Brown. Exploiting reflection change for automatic reflection removal. In Proceedings of the IEEE international conference on computer vision, pages 2432–2439, 2013.
[22] Yu Li and Michael S Brown. Single image layer separation using relative smoothness. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2752–2759, 2014.
[23] Yu Li, Ming Liu, Yaling Yi, Qince Li, Dongwei Ren, and Wangmeng Zuo. Two- stage single image reflection removal with reflection-aware guidance. Applied Intelligence, 53(16):19433–19448, 2023.
[24] Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang. Learning to see through obstructions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14215–14224, 2020.
[25] Youwei Lyu, Zhaopeng Cui, Si Li, Marc Pollefeys, and Boxin Shi. Reflection separation using a pair of unpolarized and polarized images. Advances in neural infor- mation processing systems, 32, 2019.
[26] Simon Niklaus, Xuaner Cecilia Zhang, Jonathan T Barron, Neal Wadhwa, Rahul Garg, Feng Liu, and Tianfan Xue. Learned dual-view reflection removal. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3713–3722, 2021.
[27] YiChang Shih, Dilip Krishnan, Fredo Durand, and William T Freeman. Reflection removal using ghosting cues. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3193–3201, 2015.
[28] Karen Simonyan. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
[29] 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.
[30] Renjie Wan, Boxin Shi, Tan Ah Hwee, and Alex C Kot. Depth of field guided reflection removal. In 2016 IEEE International Conference on Image Processing (ICIP), pages 21–25. IEEE, 2016.
[31] Renjie Wan, Boxin Shi, Haoliang Li, Ling-Yu Duan, and Alex C Kot. Face image reflection removal. International Journal of Computer Vision, 129:385–399, 2021.
[32] 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/CVF Conference on Computer Vision and Pattern Recognition, pages 8178–8187, 2019.
[33] Patrick Wieschollek, Orazio Gallo, Jinwei Gu, and Jan Kautz. Separating reflection and transmission images in the wild. In Proceedings of the European Conference on Computer Vision (ECCV), pages 89–104, 2018.
[34] 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.
[35] 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.
[36] Haofeng Zhong, Yuchen Hong, Shuchen Weng, Jinxiu Liang, and Boxin Shi. Language-guided image reflection separation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24913–24922, 2024.
[37] Yurui Zhu, Xueyang Fu, Peng-Tao Jiang, Hao Zhang, Qibin Sun, Jinwei Chen, Zheng-Jun Zha, and Bo Li. Revisiting single image reflection removal in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 25468–25478, 2024.
[38] Daniel Zoran and Yair Weiss. From learning models of natural image patches to whole image restoration. In 2011 international conference on computer vision, pages 479–486. IEEE, 2011.