近期許多深度學習中模型在影像風格轉移和圖片超解析上取得重大的成功。但在這些方法中，有兩個問題是會常常遇到的：(1)會受到GPU的空間限制，導致深度學習在影像處理的應用圖片只能在128px以內。(2)影像風格轉移時，大部分只能整張圖片進行風格轉移，無法針對單一物件、背景或是照片給人的感覺進行風格轉移。

因此本論文提出SceneGAN，一個創新且具規模性的方法，透過單一模型進行圖片局部風格轉移並使用圖片超解析進行圖片放大。這種單一的模型使得SceneGAN相較於其他的模型能狗產生高品質的風格轉移，並解決生成256px圖片以上需要較高的GPU空間的限制，讓有生成128px圖片的硬體設備也可以產生256px或是更高畫素的圖片。

In recent years, many deep learning models have achieved great success in image style transfer and image super resolution. However, in these methods, two problems are often encountered :(1) the memory size of GPU is limited, resulting in the fact that applications of deep learning can only deal with images of resolution of 128px. (2) when the image style is transferred, mostly of the images can only be transferred as a whole, but can not be transferred to a single object or to the background.

Therefore, this paper proposes SceneGAN, an innovative method which uses a single model to transfer image styles both locally and globally. This single model makes SceneGAN, when compared with other models, can produce higher quality of style transfer, and solve the problem of generating images with resolutions of 256 px or more by modifying the popular StarGAN model.

[1] Yunjey Choi, Min-Je Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. CoRR, abs/1711.09020, 2017.
[2] Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image super- resolution using deep convolutional networks. CoRR, abs/1501.00092, 2015.
[3] Chao Dong, Chen Change Loy, and Xiaoou Tang. Accelerating the super- resolution convolutional neural network. CoRR, abs/1608.00367, 2016.
[4] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde- Farley, Sherjil Ozair, Aaron Courville, and Yoshua 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] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015.
[6] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. Image-to-image translation with conditional adversarial networks. CoRR, abs/1611.07004, 2016.
[7] Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, and Jiwon Kim. Learning to discover cross-domain relations with generative adversarial networks. CoRR, abs/1703.05192, 2017.
[8] Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. CoRR, abs/1312.6114, 2013.
[9] Oliver Langner, Ron Dotsch, Gijsbert Bijlstra, Daniel H. J. Wigboldus, Skyler T. Hawk, and Ad van Knippenberg. Presentation and validation of the radboud faces database. Cognition and Emotion, 24(8):1377–1388, 2010.
[10] Mu Li, Wangmeng Zuo, and David Zhang. Deep identity-aware transfer of facial attributes. CoRR, abs/1610.05586, 2016.
[11] Ming-Yu Liu, Thomas Breuel, and Jan Kautz. Unsupervised image-to-image translation networks. CoRR, abs/1703.00848, 2017.
[12] Ming-Yu Liu and Oncel Tuzel. Coupled generative adversarial networks. CoRR, abs/1606.07536, 2016.
[13] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), 2015.
[14] Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets.
CoRR, abs/1411.1784, 2014.
[15] Mahesh Chandra Mukkamala and Matthias Hein. Variants of RMSProp and Adagrad with logarithmic regret bounds. In Doina Precup and Yee Whye Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 2545–2553, International Convention Centre, Sydney, Australia, 06–11 Aug 2017. PMLR.
[16] Guim Perarnau, Joost van de Weijer, Bogdan Raducanu, and Jose M. A´lvarez. Invertible conditional gans for image editing. CoRR, abs/1611.06355, 2016.
[17] Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR, abs/1511.06434, 2015.
[18] Martin Riedmiller and Heinrich Braun. A direct adaptive method for faster backpropagation learning: The rprop algorithm. In IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, pages 586–591, 1993.
[19] O. Ronneberger, P.Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer- Assisted Intervention (MICCAI), volume 9351 of LNCS, pages 234–241. Springer, 2015. (available on arXiv:1505.04597 [cs.CV]).
[20] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. CoRR, abs/1409.4842, 2014.
[21] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR, abs/1703.10593, 2017.