Local Facial Makeup Transfer via Disentangled Representation

TL;DR

This paper introduces a novel adversarial disentangling network that separates face images into independent components, enabling precise control over local and global makeup styles and unifying makeup transfer and removal processes.

Contribution

The proposed method uniquely disentangles face images into four independent components, allowing flexible regulation of local and global makeup styles within a single framework.

Findings

Produces more realistic makeup transfer results than state-of-the-art methods.

Allows control over local and global makeup styles.

Integrates makeup transfer and removal into one framework.

Abstract

Facial makeup transfer aims to render a non-makeup face image in an arbitrary given makeup one while preserving face identity. The most advanced method separates makeup style information from face images to realize makeup transfer. However, makeup style includes several semantic clear local styles which are still entangled together. In this paper, we propose a novel unified adversarial disentangling network to further decompose face images into four independent components, i.e., personal identity, lips makeup style, eyes makeup style and face makeup style. Owing to the further disentangling of makeup style, our method can not only control the degree of global makeup style, but also flexibly regulate the degree of local makeup styles which any other approaches can't do. For makeup removal, different from other methods which regard makeup removal as the reverse process of makeup, we integrate the makeup transfer with the makeup removal into one uniform framework and obtain multiple makeup removal results. Extensive experiments have demonstrated that our approach can produce more realistic and accurate makeup transfer results compared to the state-of-the-art methods.