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

arXiv: https://arxiv.org/abs/2405.17240 · HTML: https://mlsanity.com/paper/2405.17240/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 27 May 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer](https://mlsanity.com/paper/1909.06956/) (2019)
- [LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup](https://mlsanity.com/paper/1904.11272/) (2019)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer](https://mlsanity.com/paper/2104.01867/) (2021)
- [EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer](https://mlsanity.com/paper/2207.09840/) (2022)
- [SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal](https://mlsanity.com/paper/2112.03631/) (2021)
- [Facial Attribute Transformers for Precise and Robust Makeup Transfer](https://mlsanity.com/paper/2104.02894/) (2021)
- [PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal](https://mlsanity.com/paper/2105.12324/) (2021)
- [Disentangled Makeup Transfer with Generative Adversarial Network](https://mlsanity.com/paper/1907.01144/) (2019)
- [Semi-parametric Makeup Transfer via Semantic-aware Correspondence](https://mlsanity.com/paper/2203.02286/) (2022)
- [Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss](https://mlsanity.com/paper/1908.00274/) (2019)

## Built on by (most cited first, 15 of 15)

- [FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer](https://mlsanity.com/paper/2508.05069/) (2025)
- [Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method](https://mlsanity.com/paper/2411.11135/) (2024)
- [BeautyBank: Encoding Facial Makeup in Latent Space](https://mlsanity.com/paper/2411.11231/) (2024)
- [MoFRR: Mixture of Diffusion Models for Face Retouching Restoration](https://mlsanity.com/paper/2507.19770/) (2025)
- [AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars](https://mlsanity.com/paper/2507.02419/) (2025)
- [EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad](https://mlsanity.com/paper/2508.05994/) (2025)
- [FFHQ-Makeup: Paired Synthetic Makeup Dataset with Facial Consistency Across Multiple Styles](https://mlsanity.com/paper/2508.03241/) (2025)
- [DreamMakeup: Face Makeup Customization using Latent Diffusion Models](https://mlsanity.com/paper/2510.10918/) (2025)
- [FBSDiff++: Improved Frequency Band Substitution of Diffusion Features for Efficient and Highly Controllable Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2601.19115/) (2026)
- [Supervised makeup transfer with a curated dataset: Decoupling identity and makeup features for enhanced transformation](https://mlsanity.com/paper/2602.00729/) (2026)
- [DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation](https://mlsanity.com/paper/2507.13292/) (2025)
- [Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation](https://mlsanity.com/paper/2509.02445/) (2025)
- [Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features](https://mlsanity.com/paper/2603.20012/) (2026)
- [MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer](https://mlsanity.com/paper/2607.20924/) (2026)
- [Multi-Tool Image Editing Attribution in Facial Forgery](https://mlsanity.com/paper/2609.02751/) (2026)

## Abstract (arXiv)

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.