用真实参考图提升美妆迁移精度，解决伪目标导致的细节丢失问题
Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer
- 分两阶段训练：先用合成目标初始化，再用真实参考图精细化修正
- 在8573张真实人脸数据上测试，复杂妆容保真度显著提升
- 适合需要高保真妆容迁移的数字人、影视特效和虚拟试妆场景
美妆迁移旨在将参考妆容迁移到源人脸，同时保持身份和几何结构。然而该任务受限于缺乏真实配对训练数据。现有方法依赖弱先验或基于大规模编辑模型生成的合成伪目标，导致细粒度细节退化、合成伪影和身份漂移。为此，我们提出现实锚定美妆迁移（ART），一种两阶段框架，包含现实锚定的精修循环。第一阶段使用伪目标初始化，实现基本语义对齐和全局妆容布局；第二阶段将监督从伪目标切换至真实参考，通过可微分循环从无妆图像重建真实妆容，惩罚遗漏细节并消除合成伪影。此外，我们构建了首个2K分辨率的真实场景美妆人像数据集MakeupFaces2K（MF2K），含8,573张图像。大量实验表明，该方法在妆容保真度、背景稳定性与身份一致性方面均表现优异，尤其适用于复杂妆容。
原文摘要 · Abstract (English)
Makeup transfer applies a reference cosmetic style to a source face while preserving its identity and geometry. However, this task is severely hindered by the lack of real paired training data. Current methods rely on either weak priors or synthetic pseudo-targets from large-scale editing models. These paradigms provide suboptimal guidance, often leading to degraded fine-grained details, synthetic artifacts, and identity drift. To this end, we propose Anchoring on Reality Makeup Transfer (ART), a two-stage framework with a reality-anchored refinement cycle. In Stage I, the model is initialized with pseudo-targets to establish basic semantic alignment and global makeup placement. Crucially, Stage II shifts supervision from pseudo-targets to the real reference, reconstructing it from its bare-skin counterpart through a differentiable cycle that penalizes any omitted detail and overrides synthetic artifacts. Furthermore, we introduce MakeupFaces2K (MF2K), the first 2K-resolution in-the-wild makeup portrait dataset comprising 8,573 images. Extensive experiments demonstrate that our method achieves superior makeup fidelity, strong background stability, and robust identity preservation, especially for complex makeup styles.
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。