# EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad

arXiv: https://arxiv.org/abs/2508.05994 · HTML: https://mlsanity.com/paper/2508.05994/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer](https://mlsanity.com/paper/2203.03121/) (2022)
- [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)
- [SeedEdit 3.0: Fast and High-Quality Generative Image Editing](https://mlsanity.com/paper/2506.05083/) (2025)
- [Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model](https://mlsanity.com/paper/2403.07764/) (2024)
- [Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer](https://mlsanity.com/paper/2104.01867/) (2021)
- [SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer](https://mlsanity.com/paper/2104.10567/) (2021)
- [SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal](https://mlsanity.com/paper/2112.03631/) (2021)
- [SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network](https://mlsanity.com/paper/2011.11377/) (2020)
- [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)
- [CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer](https://mlsanity.com/paper/2008.10298/) (2020)
- [BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer](https://mlsanity.com/paper/2212.05855/) (2022)
- [Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth](https://mlsanity.com/paper/2405.17240/) (2024)
- [Asymmetric GAN for Unpaired Image-to-image Translation](https://mlsanity.com/paper/1912.11660/) (2019)
- [MAD: Makeup All-in-One with Cross-Domain Diffusion Model](https://mlsanity.com/paper/2504.02545/) (2025)

## Built on by (most cited first, 3 of 3)

- [Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features](https://mlsanity.com/paper/2603.20012/) (2026)
- [From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data](https://mlsanity.com/paper/2605.07861/) (2026)
- [Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer](https://mlsanity.com/paper/2606.31089/) (2026)

## Abstract (arXiv)

Facial makeup editing aims to realistically transfer makeup from a reference to a target face. Existing methods often produce low-quality results with coarse makeup details and struggle to preserve both identity and makeup fidelity, mainly due to the lack of structured paired data -- where source and result share identity, and reference and result share identical makeup. To address this, we introduce MakeupQuad, a large-scale, high-quality dataset with non-makeup faces, references, edited results, and textual makeup descriptions. Building on this, we propose EvoMakeup, a unified training framework that mitigates image degradation during multi-stage distillation, enabling iterative improvement of both data and model quality. Although trained solely on synthetic data, EvoMakeup generalizes well and outperforms prior methods on real-world benchmarks. It supports high-fidelity, controllable, multi-task makeup editing -- including full-face and partial reference-based editing, as well as text-driven makeup editing -- within a single model. Experimental results demonstrate that our method achieves superior makeup fidelity and identity preservation, effectively balancing both aspects. Code and dataset will be released upon acceptance.