Makeup like a superstar: Deep Localized Makeup Transfer Network

TL;DR

This paper introduces a Deep Localized Makeup Transfer Network that automatically recommends and applies realistic, localized makeup to faces, allowing for controllable makeup intensity and diverse cosmetic styles.

Contribution

The paper presents a novel end-to-end deep network capable of localized, cosmetic-specific makeup transfer with natural results and adjustable makeup lightness, outperforming previous methods.

Findings

The network achieves more natural results than prior methods.

It effectively transfers multiple makeup types including foundation, lip gloss, and eye shadow.

Experiments demonstrate superior performance quantitatively and qualitatively.

Abstract

In this paper, we propose a novel Deep Localized Makeup Transfer Network to automatically recommend the most suitable makeup for a female and synthesis the makeup on her face. Given a before-makeup face, her most suitable makeup is determined automatically. Then, both the beforemakeup and the reference faces are fed into the proposed Deep Transfer Network to generate the after-makeup face. Our end-to-end makeup transfer network have several nice properties including: (1) with complete functions: including foundation, lip gloss, and eye shadow transfer; (2) cosmetic specific: different cosmetics are transferred in different manners; (3) localized: different cosmetics are applied on different facial regions; (4) producing naturally looking results without obvious artifacts; (5) controllable makeup lightness: various results from light makeup to heavy makeup can be generated. Qualitative and quantitative experiments show that our network performs much better than the methods of [Guo and Sim, 2009] and two variants of NerualStyle [Gatys et al., 2015a].