用新数据集和框架实现高保真可控美妆编辑
EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad
- 构建包含四类图像的 MakeupQuad 数据集，支持多阶段训练
- 在真实数据集上优于已有方法，兼顾妆容保真与身份一致性
- 单模型支持参考图和文本双重控制的全脸/局部美妆编辑
面部美妆编辑旨在将参考妆容真实地迁移到目标人脸。现有方法常因缺乏结构化成对数据（源与结果同身份、参考与结果同妆容）而产生粗糙细节，难以同时保持身份与妆容保真。为此，我们提出 MakeupQuad——一个大规模高质量数据集，包含非化妆人脸、参考图、编辑结果及文本妆容描述。基于此，我们设计 EvoMakeup 统一训练框架，缓解多阶段知识蒸馏中的图像退化问题，实现数据与模型质量的迭代提升。尽管仅在合成数据上训练，EvoMakeup 在真实世界基准上表现优异，支持高保真、可控制的多任务美妆编辑，包括全脸与局部参考驱动编辑、以及文本引导编辑。实验表明，该方法在妆容保真度与身份保留之间取得更好平衡。代码与数据集将在论文接受后发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。