AI RESEARCH
From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data
arXiv CS.CV
•
ArXi:2605.07861v1 Announce Type: new Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods formulate this task as unsupervised image-to-image translation, relying on surrogate objectives and often yielding limited performance. Recent diffusion- and flow-based approaches instead exploit synthetic data for supervised