mlsanityData to 14 Oct 2026

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

arXiv 2405.17240 ↗First posted 27 May 2024cs.CVcited by 15

Not on the map. Why?

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.

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

24 of 35 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  5. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  6. 2016Least Squares Generative Adversarial Networkscited by 1,001
  7. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  8. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  9. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  10. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 291
  11. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  12. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
12 more
  1. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  2. 2019PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfercited by 66
  3. 2019LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeupcited by 64
  4. 2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
  5. 2021Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfercited by 35
  6. 2022EleGANt: Exquisite and Locally Editable GAN for Makeup Transfercited by 28
  7. 2021SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removalcited by 22
  8. 2021Facial Attribute Transformers for Precise and Robust Makeup Transfercited by 17
  9. 2021PSGAN++: Robust Detail-Preserving Makeup Transfer and Removalcited by 17
  10. 2019Disentangled Makeup Transfer with Generative Adversarial Networkcited by 7
  11. 2022Semi-parametric Makeup Transfer via Semantic-aware Correspondencecited by 5
  12. 2019Content and Colour Distillation for Learning Image Translations with the Spatial Profile Losscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 8; 2026: 5.

15 papers.

Sort:

By area:

  1. 2025FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformercited by 5
  2. 2024Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Methodcited by 4
  3. 2024BeautyBank: Encoding Facial Makeup in Latent Spacecited by 4
  4. 2025MoFRR: Mixture of Diffusion Models for Face Retouching Restorationcited by 4
  5. 2025AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatarscited by 3
  6. 2025EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuadcited by 3
  7. 2025FFHQ-Makeup: Paired Synthetic Makeup Dataset with Facial Consistency Across Multiple Stylescited by 2
  8. 2025DreamMakeup: Face Makeup Customization using Latent Diffusion Modelscited by 1
  9. 2026FBSDiff++: Improved Frequency Band Substitution of Diffusion Features for Efficient and Highly Controllable Text-Driven Image-to-Image Translationcited by 1
  10. 2026Supervised makeup transfer with a curated dataset: Decoupling identity and makeup features for enhanced transformationcited by 1
  11. 2025DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimationcited by 0
  12. 2025Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generationcited by 0
3 more
  1. 2026Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Featurescited by 0
  2. 2026MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfercited by 0
  3. 2026Multi-Tool Image Editing Attribution in Facial Forgerycited by 0