MakeupBag: Disentangling Makeup Extraction and Application

TL;DR

MakeupBag is a new method for automatic makeup style transfer that disentangles makeup extraction from application, enabling customizable and precise makeup transfer, including classical and extreme styles, outperforming existing methods.

Contribution

It introduces a novel approach that separates makeup disentanglement from application, allowing for customization and handling of diverse makeup styles, which was not possible with previous methods.

Findings

High-quality, accurate makeup transfer demonstrated through extensive experiments.

Outperforms current state-of-the-art approaches in style transfer quality.

Capable of transferring both classical and extreme costume makeup styles.

Abstract

This paper introduces MakeupBag, a novel method for automatic makeup style transfer. Our proposed technique can transfer a new makeup style from a reference face image to another previously unseen facial photograph. We solve makeup disentanglement and facial makeup application as separable objectives, in contrast to other current deep methods that entangle the two tasks. MakeupBag presents a significant advantage for our approach as it allows customization and pixel specific modification of the extracted makeup style, which is not possible using current methods. Extensive experiments, both qualitative and numerical, are conducted demonstrating the high quality and accuracy of the images produced by our method. Furthermore, in contrast to most other current methods, MakeupBag tackles both classical and extreme and costume makeup transfer. In a comparative analysis, MakeupBag is shown to outperform current state-of-the-art approaches.