面向扩散换脸的属性保持伪标签方法
Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
提出教师-学生扩散框架，用条件去模糊和属性感知反演生成伪标签，替代掩码条件以保留肤色、光照、妆容等属性，可复用于其他需保持属性的图像编辑任务。
原文依据 we propose APPLE (Attribute-Preserving Pseudo-Labeling), a fully diffusion-based teacher-student framework for attribute-preserving face swapping.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论换脸旨在将源人脸的身份转移到目标人脸上，同时保留目标特有的属性，如姿态、表情、光照、肤色和妆容。然而，由于换脸缺乏真实真值，同时实现准确的身份转移和高质量的属性保持仍然具有挑战性。近期基于扩散模型的方法尝试通过对掩码目标图像进行条件图像修复来提高视觉保真度，但掩码条件移除了关键的外观线索，导致属性看似合理却未对齐。为解决这一局限，我们提出 APPLE（属性保持伪标签），一种用于属性保持换脸的完全基于扩散模型的教师-学生框架。我们的方法引入教师设计，通过（1）条件去模糊公式化，改善肤色和光照等全局属性的保持，以及（2）属性感知反演方案，进一步增强妆容等细粒度属性的保持，从而生成与目标属性对齐的伪标签。APPLE 以干净的伪标签而非退化的掩码输入作为学生模型的条件，从而实现更忠实的属性保持。因此，APPLE 在属性保持方面达到了最优性能，同时保持了有竞争力的身份转移能力。
英文原文摘要 1390 字符
Face swapping aims to transfer the identity of a source face onto a target face while preserving target-specific attributes such as pose, expression, lighting, skin tone, and makeup. However, since real ground truth for face swapping is unavailable, achieving both accurate identity transfer and high-quality attribute preservation remains challenging. Recent diffusion-based approaches attempt to improve visual fidelity through conditional inpainting on masked target images, but the masked condition removes crucial appearance cues, resulting in plausible yet misaligned attributes. To address this limitation, we propose APPLE (Attribute-Preserving Pseudo-Labeling), a fully diffusion-based teacher-student framework for attribute-preserving face swapping. Our approach introduces a teacher design to produce pseudo-labels aligned with the target attributes through (1) a conditional deblurring formulation that improves the preservation of global attributes such as skin tone and illumination, and (2) an attribute-aware inversion scheme that further enhances fine-grained attribute preservation such as makeup. APPLE conditions the student on clean pseudo-labels rather than degraded masked inputs, enabling more faithful attribute preservation. As a result, APPLE achieves state-of-the-art performance in attribute preservation while maintaining competitive identity transferability.