簡易檢索 / 詳目顯示

回結果列表
研究生： 林家慶
Lin, Chia-Ching
論文名稱： 一個基於循環對抗網路的雨紋移除演算法
A Cycle Generative Adversarial Networks Based Rain Streaks Removal Algorithm
指導教授： 戴顯權
Tai, Shen-Chuan
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2019
畢業學年度： 107
語文別： 英文
論文頁數： 60
中文關鍵詞： 雨紋去除 、自然影像 、生成對抗網路 、卷積神經網路
外文關鍵詞： rain removal, natural images, generative adversarial network, convolutional neural networks
相關次數： 點閱：147  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 電腦視覺演算法像是物件偵測、影像辨識技術已經被導入許多日常生活的應用中，然而這些演算法通常沒有辦法在實際情形都運作的很完善，原因在於這些演算法大部分都是基於理想狀態下的數據去做訓練。在實際景象中，無法預測的影像品質損害情形時常會發生，例如：雜訊、曝光度，以及多變的氣候情況。常見的氣候情況像是下雨、下雪、沙塵暴都會嚴重地影響許多電腦視覺演算法的表現。本論文提出了一種基於循環生成對抗網絡的雨紋移除演算法。此網路包含兩個循環，每個循環各包含一個產生器與兩個鑑別器。產生器合成趨於真實的影像來欺騙鑑別器；鑑別器則判別產生器的輸出是否為真實影像。本論文提出的方法僅需要雨紋和無雨紋影像進行訓練，並不需要雨紋遮罩。實驗結果顯示，本論文的方法，在比較的方法當中，得到了更自然的紋理與細節。

    Computer vision algorithms like object detection, image classification have changed our life significantly in various applications. However, these algorithms usually cannot have good performance in practical applications, due to the fact that these algorithms are normally trained by images with ideal condition. Unpredictable degradations often occur in realistic scene, for instance, noise, illuminations, and severe weather conditions. Commonly seen weather conditions such as rain, snow, and sandstorm can adversely affect the performance of many computer vision tasks.
    In this thesis, a rain removal algorithm based on cycle generative adversarial network is proposed. It contains two cycles. Each cycle includes one generator and two discriminators. Generators synthesize outputs that can deceive discriminators with real images. Discriminators distinguish whether outputs from generators are real images.The proposed method only requires rainy and non-rain images for training, so it does not require rain streaks masks. Experimental results show that the proposed method gets more nature textures and details compared with available methods.

    Contents...........iv List of Tables..........vi List of Figures.........vii Chapter 1 Introduction............1 Chapter 2 Background and Related Works........4 2.1 Neural Networks.............4 2.2 Convolutional Neural Network............10 2.3 Learning Methods............17 2.4 Generative Adversarial Networks...........19 2.5 Cycle-Consistent Adversarial Network..........22 Chapter 3 The Proposed Algorithm...........24 3.1 Proposed Network Architecture.............27 3.2 Loss Function..............32 3.2.1 Cycle consistency loss.................32 3.2.2 Adversarial loss.......................32 3.2.3 Rain model adversarial loss............33 3.2.4 Gaussian gradient loss.................33 3.2.5 Total variation loss...................34 3.2.6 Total loss function....................34 3.3 Generator Network........................37 3.4 Discriminator Network....................39 Chapter 4 Experimental Results.........41 4.1 Experimental Dataset...........41 4.2 Parameter and Experimental Setting.........44 4.3 Experimental Results of Simulated Images.......45 4.4 Ablation Experimental Results...............53 Chapter 5 Conclusion and Future Work............55 5.1 Conclusion.................55 5.2 Future Work................55 References.....................56

    [1] Qixing Huang and Leonidas Guibas. Consistent Shape Maps via Semidefinite Programming. In Computer Graphics Forum, vol. 32, no. 5, Proc. Eurographics Symposium on Geometry Processing (SGP), 2013.
    [2] J. Zhu, T. Park, P. Isola, and A. A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In International Conference on Computer Vision (ICCV), to appear, 2017.
    [3] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Neural Information Processing Systems (NIPS), 2014.
    [4] Y. Lecun, L. Bottou, Y. Bengio, P. Haffner. Gradient-based learning applied to document recognition. In Proceedings of the IEEE, vol. 86, no. 11, 1998.
    [5] Chuan Li and Michael Wand. Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks. arXiv preprint arXiv:1604.04382
    [6] Nicolas Dey, Laure Blanc‐Feraud, Christophe Zimmer, Pascal Roux, Zvi Kam, Jean‐Christophe Olivo‐Marin, Josiane Zerubia. Richardson-Lucy Algorithm with Total Variation Regularization for 3D Confocal Microscope Deconvolution. In Microscopy Research Technique, pages 260-266, 2006.
    [7] Thekke Madam Nimisha, Kumar Sunil, A. N. Rajagopalan. Unsupervised Class-Specific Deblurring. The European Conference on Computer Vision (ECCV), pages 353-369, Springer, 2018.
    [8] Matthew D. Zeiler and Rob Fergus. Visualizing and Understanding Convolutional Networks. In European Conference on Computer Vision (ECCV), pages 818–833. Springer, 2014.
    [9] M. Mirza and S. Osindero. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
    [10] A. Shrivastava, T. Pfister, O. Tuzel, J. Susskind, W. Wang, and R. Webb. Learning from simulated and unsupervised images through adversarial training. In IEEE
    Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [11] Andrew L. Maas, Awni Y. Hannum and Andrew Y. Ng. Rectifier Nonlinearities Improve Neural Network Acoustic Models. In ICML. 2013.
    [12] Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha. Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining. arXiv preprint arXiv:1807.05698, resca2018.
    [13] K. Fukushima. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 1980.
    [14] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Backpropagation applied to handwritten zip code recognition. Neural computation, 1989.
    [15] A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in Proc. ICML, 2013, vol. 30, no. 1.
    [16] O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pages 234–241. Springer, 2015.
    [17] C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, ´ A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint arXiv:1609.04802, 2016.
    [18] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros. Image-to-image translation with conditional adversarial networks. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [19] Z. Yi, H. Zhang, T. Gong, Tan, and M. Gong. Dualgan. Unsupervised dual learning for image-to-image translation. In IEEE International Conference on Computer Vision (ICCV), 2017.
    [20] J.-Y. Zhu, R. Zhang, D. Pathak, T. Darrell, A. A. Efros, O. Wang, and E. Shechtman. Toward multimodal image-to-image translation. In Advances in Neural Information Processing Systems (NIPS), 2017.
    [21] D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, and A. A. Efros. Context encoders: Feature learning by inpainting. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
    [22] Guilin Liu, Fitsum A Reda, Kevin J Shih, Ting-Chun Wang, Andrew Tao, and Bryan Catanzaro. Image inpainting for irregular holes using partial convolutions. arXiv
    preprint arXiv:1804.07723, 2018.
    [23] Yi-Lei Chen, Chiou-Ting Hsu. A Generalized Low-Rank Appearance Model for Spatio-Temporally Correlated Rain Streaks. In IEEE International Conference on
    Computer Vision (ICCV), 2013.
    [24] Li-Wei Kang, Chia-Wen Lin, Yu-Hsiang Fu. Automatic Single-Image-Based Rain Streaks Removal via Image Decomposition. In IEEE Transactions on Image Processing,
    vol. 21, no. 4, 2013.
    [25] Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, and John Paisley. Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal. In IEEE Transactions on Image Processing, vol. 26, no. 6, 2017.
    [26] Wenhan Yang, Robby T. Tan, Jiashi Feng, Jiaying Liu, Zongming Guo, Shuicheng Yan. Deep Joint Rain Detection and Removal from a Single Image. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [27] He Zhang, Vishal M. Patel. Density-aware Single Image De-raining using a Multi-stream Dense Network. In IEEE International Conference on Computer Vision and
    Pattern Recognition (CVPR), 2018.
    [28] H. Zhang, V. A. Sindagi, and V. M. Patel. Image de-raining using a conditional generative adversarial network. arXiv preprint arXiv:1701.05957, 2017.
    [29] Xueyang Fu, Jiabin Huang, Delu Zeng, Yue Huang, Xinghao Ding, John Paisley. Removing rain from single images via a deep detail network. In IEEE International
    Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [30] K. Garg and S. K. Nayar. Detection and removal of rain from videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pages I–I,2004.
    [31] Zhang, X., Li, H., Qi, Y., Leow, W.K., Ng, T.K. Rain removal in video by combining temporal and chromatic properties. In IEEE ICME, pages 461–464, 2006.
    [32] P. Barnum, S. Narasimhan, T. Kanade. Analysis of rain and snow in frequency space. International Journal of Computer Vision 86 (2-3) (2010) 256–274.
    [33] J. Bossu, N. Hautiere, and J.-P. Tarel. Rain or snow detection in image sequences through use of a histogram of orientation of streaks. IJCV, 93(3):348–367, 2011.
    [34] C. Stauffer, W. Grimson, Learning patterns of activity using realtime tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 747–757.
    [35] Yu Luo, Yong Xu, Hui Ji. Removing Rain from a Single Image via Discriminative Sparse Coding. In IEEE International Conference on Computer Vision (ICCV),2015.
    [36] Yinglong Wang, Shuaicheng Liu, Chen Chen, Bing Zeng.A Hierarchical Approach for Rain or Snow Removing in a Single Color Image. In IEEE Transactions on Image
    Processing,vol. 26, no. 8, 2017.
    [37] Siyuan Li, Wenqi Ren, Jiawan Zhang, Jinke Yu, Xiaojie Guo. Fast Single Image Rain Removal via a Deep Decomposition-Composition Network. arXiv preprint arXiv:
    1804.02688, 2018.
    [38] Santhaseelan, V., Asari, V.K.: Utilizing local phase information to remove rain from video. International Journal of Computer Vision 112(1) (2015) 71–89.
    [39] Y. Li, R. Tan, X. Guo, J. Lu, and M. Brown. 2016. Rain Streak Removal Using Layer Priors. In IEEE International Conference on Computer Vision and Pattern
    Recognition (CVPR), 2016.
    [40] Fisher Yu, Vladlen Koltun. Multi-scale context aggregation by dilated convolutions.
    arXiv preprint arXiv:1511.07122, 2015.
    [41] Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu. Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507, 2017.
    [42] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
    [43] 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, 2018.
    [44] D.-A. Huang, L.-W. Kang, M.-C. Yang, C.-W. Lin, and Y.-C. F. Wang. Context-aware single image rain removal. In IEEE Multimedia and Expo (ICME), 2012.

    下載圖示 校內：立即公開
    校外：立即公開
    QR CODE