從相機出現直到彩色相機普及前，世上累積了大量的黑白照片，若能彩色化那些遺留下來的黑白紀錄，將為人類歷史增添一番風采。

本論文提出一個以Tensorflow作為軟體框架，卷積神經網路為基礎，利用生成對抗網路的架構，完成一個能自動彩色化灰階圖像，生成彩色圖片的系統，輸出結果的解析度能達到512x512。

本論文實作可應用的的資料集可分為鞋子(Zappos50K)、人臉(CelebA)、辛普森家庭(Simpsons)、自然風景與城市街景五種，在這些差異性高的資料中，測試本論文提出方法的泛用性，並利用序列式影像輸入驗證本系統的穩定性。

實驗結果說明本論文提出的彩色化方案的泛用性，可以應用於不同場景，因此亦有不錯的擴充性，可以適應不同的資料訓練及如此便可以增加泛用性；彩色化方法之穩定性，在序列式影像輸入的測試中，並不會突然彩色化成完全不同的顏色。

During the time from the invention of cameras to the diffusion of color photography, there had been a lot of black and white photos. If we can colorize those black and white photos and transform them into colorful ones, they would certainly mark a brilliant page in the history of mankind.

In this thesis, we present an auto colorization system implemented by tensorflow framework and the structure of generative adversarial network. The resolution of output can reach as high as 512 by 512.

The experiment was conducted on several datasets, including shoes(Zappos 50K), human faces(CelebA), cartoon(The Simpsons), natural landscapes and modern urban cityscapes. By testing these diverse datasets, it proves the multiusability of the technique we present. In addition, we test the sequential input to verify the stability of our system.

The results turned out that the multiusability of our colorization system can be used in different scenes. Therefore, our colorization system can be expanded to other applications with different datasets. The results of sequential input will not shift to different color all of a sudden, demonstrating the stability of our colorization system.

[1] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A.Davis, J. Dean, M.Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard,Y. Jia, R. Jozefowicz, L. Kaiser, M.Kudlur, J. Levenberg, D. Man´e, R. Monga, S.Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Vi´egas, O. Vinyals, P.Warden, M.Wattenberg, M. Wicke, Y. Yu, and X. Zheng, TensorFlow: Large-scale machine learning on heterogeneous systems, Software available from tensorflow.org, 2015. [Online]. Available: https://www.tensorflow.org/.
[2] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting”, Journal of computer and system sciences, vol. 55, no. 1, pp. 119–139, 1997.
[3] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector machines”, IEEE Intelligent Systems and their applications, vol. 13, no. 4, pp. 18–28, 1998.
[4] A. Levin, D. Lischinski, and Y. Weiss, “Colorization using optimization”, in ACM transactions on graphics (tog), ACM, vol. 23, 2004, pp. 689–694.
[5] Q. Luan, F. Wen, D. Cohen-Or, L. Liang, Y.-Q. Xu, and H.-Y. Shum, “Natural image colorization”, in Proceedings of the 18th Eurographics conference on Rendering
Techniques, Eurographics Association, 2007, pp. 309–320.
[6] G. Charpiat, M. Hofmann, and B. Sch¨olkopf, “Automatic image colorization via multimodal predictions”, in Proceedings of the 10th European Conference on Computer Vision: Part III, ser. ECCV ’08, Marseille, France: Springer-Verlag, 2008, pp. 126–139, isbn: 978-3-540-88689-1. doi: 10.1007/978- 3- 540- 88690- 7_10. [Online]. Available: http://dx.doi.org/10.1007/978-3-540-88690-7_10.
[7] X. Liu, L. Wan, Y. Qu, T.-T. Wong, S. Lin, C.-S. Leung, and P.-A. Heng, “Intrinsic colorization”, in ACM Transactions on Graphics (TOG), ACM, vol. 27, 2008, p. 152.
[8] R. Zhang, P. Isola, and A. A. Efros, “Colorful image colorization”, in European Conference on Computer Vision, Springer, 2016, pp. 649–666.
[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets”, in Advances in neural information processing systems, 2014, pp. 2672–2680.
[10] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks”, arXiv preprint, 2017.
[11] T.-C. Wang, M.-Y. Liu, J.-Y. Zhu, A. Tao, J. Kautz, and B. Catanzaro, “High resolution image synthesis and semantic manipulation with conditional gans”, arXiv preprint arXiv:1711.11585, 2017.
[12] 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, Springer, 2015, pp. 234–241.
[13] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation”, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431–3440.
[14] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization”, arXiv preprint arXiv:1412.6980, 2014.
[15] D. Ulyanov, A. Vedaldi, and V. S. Lempitsky, “Instance normalization: The missing ingredient for fast stylization”, CoRR, vol. abs/1607.08022, 2016.
[16] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks”, in Advances in neural information processing systems, 2012, pp. 1097–1105.
[17] A. Yu and K. Grauman, “Fine-grained visual comparisons with local learning”, in Computer Vision and Pattern Recognition (CVPR), 2014.
[18] A. Yu and K. Grauman, “Semantic jitter: Dense supervision for visual comparisons via synthetic images”, in International Conference on Computer Vision (ICCV), 2017.
[19] Z. Liu, P. Luo, X. Wang, and X. Tang, “Deep learning face attributes in the wild”, in Proceedings of International Conference on Computer Vision (ICCV), 2015.