PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
Authors:
- Huiwen ChangHCHuiwen Chang
- Jingwan LuJLJingwan Lu
- Fisher YuFYFisher Yu
- Adam FinkelsteinAFAdam Finkelstein
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 40-48
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Makeup-Go: Blind Reversion of Portrait Edit2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Example-based synthesis of stylized facial animationsACM Transactions on Graphics, 2017
- Dilated Residual Networks2017
- Deep Photo Style Transfer2017
- Image Style Transfer Using Convolutional Neural Networks2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Simulating makeup through physics-based manipulation of intrinsic image layers2015
- Image analogies2001
- Rank Analysis of Incomplete Block Designs: I. The Method of Paired ComparisonsBiometrika, 1952