# Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth

Source: [Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth](<https://www.sota2.com/research/paper/68fa734e1e209131cea5bb2e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:06.600Z

Authors: Zhaoyang Sun, Shengwu Xiong, Yaxiong Chen, Yi Rong

Published: 2024-05-27T14:57:40.000Z

## Abstract

The absence of real targets to guide the model training is one of the main problems with the makeup transfer task. Most existing methods tackle this problem by synthesizing pseudo ground truths (PGTs). However, the generated PGTs are often sub-optimal and their imprecision will eventually lead to performance degradation. To alleviate this issue, in this paper, we propose a novel Content-Style Decoupled Makeup Transfer (CSD-MT) method, which works in a purely unsupervised manner and thus eliminates the negative effects of generating PGTs. Specifically, based on the frequency characteristics analysis, we assume that the low-frequency (LF) component of a face image is more associated with its makeup style information, while the high-frequency (HF) component is more related to its content details. This assumption allows CSD-MT to decouple the content and makeup style information in each face image through the frequency decomposition. After that, CSD-MT realizes makeup transfer by maximizing the consistency of these two types of information between the transferred result and input images, respectively. Two newly designed loss functions are also introduced to further improve the transfer performance. Extensive quantitative and qualitative analyses show the effectiveness of our CSD-MT method. Our code is available at https://github.com/Snowfallingplum/CSD-MT.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Makeup Transfer on CPM-real and Wild-MT](<https://www.sota2.com/research/sota/makeup-transfer-on-cpm-real-and-wild-mt.md>): Makeup Transfer; CPM-real and Wild-MT; Selection Ratio: 20.5.

- [Makeup Transfer on CPM-real](<https://www.sota2.com/research/sota/makeup-transfer-on-cpm-real.md>): Makeup Transfer; CPM-real; CSD (Fidelity Distance): 0.418.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.17240>)

[PDF](<https://arxiv.org/pdf/2405.17240.pdf>)
