PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup

被引:178
作者
Chang, Huiwen [1 ]
Lu, Jingwan [2 ]
Yu, Fisher [3 ]
Finkelstein, Adam [1 ]
机构
[1] Princeton Univ, Princeton, NJ 08544 USA
[2] Adobe Res, San Francisco, CA USA
[3] Univ Calif Berkeley, Berkeley, CA 94720 USA
来源
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年
关键词
D O I
10.1109/CVPR.2018.00012
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper introduces an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo. Our unsupervised learning approach relies on a new framework of cycle-consistent generative adversarial networks. Different from the image domain transfer problem, our style transfer problem involves two asymmetric functions: a forward function encodes example-based style transfer, whereas a backward function removes the style. We construct two coupled networks to implement these functions one that transfers makeup style and a second that can remove makeup such that the output of their successive application to an input photo will match the input. The learned style network can then quickly apply an arbitrary makeup style to an arbitrary photo. We demonstrate the effectiveness on a broad range of portraits and styles.
引用
收藏
页码:40 / 48
页数:9
相关论文
共 24 条
[1]  
[Anonymous], 2016, P IEEE C COMPUTER VI
[2]  
[Anonymous], AAAI C ART INT
[3]  
[Anonymous], 2017, ARXIV170307511
[4]  
[Anonymous], 2017, ARXIV170501088
[5]  
[Anonymous], ABS171000756 CORR
[6]  
[Anonymous], 2016, ARXIV161102200
[7]  
[Anonymous], 2015, ABS150602025 CORR
[8]  
[Anonymous], 2017, COMPUTER VISION PATT
[9]  
[Anonymous], 2017, ARXIV170300848
[10]  
[Anonymous], 2017, IEEE INT C COMP VIS