跳到主要內容

臺灣博碩士論文加值系統

(34.204.198.73) 您好!臺灣時間:2024/07/21 16:52
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:楊騏瑄
研究生(外文):Ci-Syuan Yang
論文名稱:使用生成對抗式網路模擬五官置換
論文名稱(外文):Face Features Replacement Using Generative AdversarialNetwork
指導教授:歐陽明歐陽明引用關係
指導教授(外文):Ming Ouhyoung
口試委員:傅楸善梁容輝
口試委員(外文):Chiou-Shann FuhRung-Huei Liang
口試日期:2018-06-22
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:英文
論文頁數:31
中文關鍵詞:生成對抗式網路影像處理
相關次數:
  • 被引用被引用:0
  • 點閱點閱:143
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文的目標是讓使用者模擬將自己的五官之一整形成理想人物的五官,並且使得被置換後的五官可以與使用者其餘未整形之五官恰當地融合。在先前的研究當中,五官置換(face features replacement)的方法通常為先進行五官特徵的偵測(feature detection)接以取代置換並輔以阿爾法混合(alpha blending)為主。然而,當使用者的照片中頭部姿勢與理想人物照片中的頭部姿勢有相當程度的不同之時或是光照情況差異較大之時,即便使用良好的混成方法(blending techniques),其合成的結果照片也往往不令人滿意。因此在過往五官的整形置換模擬必須限制在使用正臉的照片。本論文採用生成對抗式網路(generative adversarial network, GAN)的架構,並在損失函數(loss function)中加入重建損失(reconstruction loss)以及引導損失(guiding loss),以得到我們的結果。
Our goal is to replace an individual''s facial features with corresponding features of another individual and then fuse the replaced features with the original face. In previous studies, face features replacement can be done by face feature detection and simple replacement. However, when the pose of two faces are quite different, the synthesized image become barely plausible even with good blending techniques. Therefore, current face feature replacement techniques are limited to frontal face only. Our approach leverages the GAN to handle this limitation. Our proposed framework is automatic and does not need any markers on input image. Furthermore, by the introduction of reconstruction loss and guiding loss in GAN, the output image of our approach can preserve the content in source image.
口試委員會審定書iii
誌謝v
摘要vii
Abstract ix
1 Introduction 1
2 Related Work 3
2.1 Face Feature Detection and replacement . . . . . . . . . . . . . . . . . . 3
2.2 Generative Adversarial Networks . . . . . . . . . . . . . . . . . . . . . . 3
2.3 Image-to-Image Translation . . . . . . . . . . . . . . . . . . . . . . . . 4
3 Overall System 5
3.1 Adversarial Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
3.2 Modified Reconstruction Loss . . . . . . . . . . . . . . . . . . . . . . . 6
3.3 Guiding Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.4 Full Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
4 Guiding Function 11
4.1 Facial Landmark Detection . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2 Locate Lips Bounding Rectangle . . . . . . . . . . . . . . . . . . . . . . 12
4.3 Replacement and Blending . . . . . . . . . . . . . . . . . . . . . . . . . 13
5 Implementation 17
5.1 Generator Network Architecture . . . . . . . . . . . . . . . . . . . . . . 17
5.2 Discriminator Network Architecture . . . . . . . . . . . . . . . . . . . . 17
6 Experiment 19
6.1 Baseline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.2 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
6.3 Training Configuration . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
6.4 Experiment Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
7 Conclusion 27
Bibliography 29
[1] M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein generative adversarial networks. In D. Precup and Y. W. Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 214–223, International Convention Centre, Sydney, Australia, 06–11 Aug 2017. PMLR.
[2] Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. arXiv preprint arXiv:1711.09020, 2017.
[3] M. Goin and T. Rees. A prospective study of patients’ psychological reactions to rhinoplasty. Annals of plastic surgery, 27 3:210–5, 1991.
[4] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 27, pages 2672–2680. Curran Associates, Inc., 2014.
[5] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville. Improved training of wasserstein gans. CoRR, abs/1704.00028, 2017.
[6] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015.
[7] X. Huang, Y. Li, O. Poursaeed, J. E. Hopcroft, and S. J. Belongie. Stacked generative adversarial networks. CoRR, abs/1612.04357, 2016.
[8] P. Isola, J. Zhu, T. Zhou, and A. A. Efros. Image-to-image translation with conditional adversarial networks. CoRR, abs/1611.07004, 2016.
[9] V. Kazemi and J. Sullivan. One millisecond face alignment with an ensemble of regression trees. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 1867–1874, June 2014.
[10] T. Kim, M. Cha, H. Kim, J. K. Lee, and J. Kim. Learning to discover cross-domain relations with generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70, pages 1857–1865, 06–11 Aug 2017.
[11] D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014.
[12] I. Korshunova, W. Shi, J. Dambre, and L. Theis. Fast face-swap using convolutional neural networks. CoRR, abs/1611.09577, 2016.
[13] C. Ledig, L. Theis, F. Huszar, J. Caballero, A. P. Aitken, A. Tejani, J. Totz, Z. Wang, and W. Shi. Photo-realistic single image super-resolution using a generative adversarial network. CoRR, abs/1609.04802, 2016.
[14] M. Li, W. Zuo, and D. Zhang. Deep identity-aware transfer of facial attributes. CoRR, abs/1610.05586, 2016.
[15] Z. Liu, P. Luo, X. Wang, and X. Tang. Deep learning face attributes in the wild. CoRR, abs/1411.7766, 2014.
[16] S. A. Rabi and P. Aarabi. Face fusion: An automatic method for virtual plastic surgery. In 2006 9th International Conference on Information Fusion, pages 1–7, July 2006.
[17] A. Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR, abs/1511.06434, 2015.
[18] W. Shen and R. Liu. Learning residual images for face attribute manipulation. CoRR, abs/1612.05363, 2016.
[19] D. Ulyanov, A. Vedaldi, and V. S. Lempitsky. Instance normalization: The missing ingredient for fast stylization. CoRR, abs/1607.08022, 2016.
[20] T. Yamada, Y. Mori, K. Minami, K. Mishima, T. Sugahara, and M. Sakuda. Computer aided three-dimensional analysis of nostril forms: Application in normal and operated cleft lip patients. 27:345–53, 01 2000.
[21] Z. Zhang, Y. Song, and H. Qi. Age progression/regression by conditional adversarial autoencoder. CoRR, abs/1702.08423, 2017.
[22] J. J. Zhao, M. Mathieu, and Y. LeCun. Energy-based generative adversarial network. CoRR, abs/1609.03126, 2016.
[23] J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593, 2017.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top