问题出在泄漏中：用于高保真发型转移的解缠双净化框架
The Devil Is in the Leakage: A Disentangled Dual-Purification Framework for High-Fidelity Hairstyle Transfer
浏览论文内容
中文总结 AI 辅助
研究发型转移中参考发型与源身份纠缠及现有方法泄漏问题，提出双净化框架，含对抗发型净化和对比几何净化两个正则化器，实现高保真、身份保留的发型转移并达领先性能。
中文摘要 AI 辅助
发型转移旨在将参考图像中的发型移植到源主体上，同时保留源身份，合成逼真的肖像。近期基础模型虽有强大生成能力，但在零样本解缠方面存在困难。现有基于扩散的管道存在身份泄漏和缺陷泄漏问题。为此提出双净化框架（DPF），引入对抗发型净化（AHP）和对比几何净化（CGP）两个互补的训练正则化器。通过联合净化发型表示和几何路径，DPF在各种基准测试中实现了高保真、身份保留的发型转移和领先性能。
英文摘要
Hairstyle transfer aims to synthesize a photorealistic portrait by transplanting the hairstyle from a reference image onto a source subject while preserving the source identity. Recent foundation models show strong generative capability, but they struggle with the zero-shot disentanglement required for precise local editing, often entangling the reference hairstyle with its original identity and pose. Existing diffusion-based pipelines typically decompose the task by first generating a "bald" image from the source and then injecting hairstyle features from the reference. However, we show that this paradigm suffers from a fundamental leakage problem. Identity Leakage in Hairstyle occurs when hairstyle features retain reference identity or pose information, while Flaw Leakage in Bald arises when residual artifacts in the bald image are propagated into the final synthesis. To address both issues, we propose the Dual-Purification Framework (DPF), which introduces two complementary training-time regularizers. Adversarial Hairstyle Purification (AHP) purifies hairstyle features by suppressing identity predictability under a mutual-information-inspired adversarial objective. Contrastive Geometric Purification (CGP) regularizes the ControlNet pathway with a contrastive objective, reducing the model's reliance on geometric artifacts in the bald condition. By jointly purifying the hairstyle representation and geometric pathway, DPF achieves high-fidelity, identity-preserving hairstyle transfer and state-of-the-art performance on diverse benchmarks.
发表机构
- SAI, UCAS（中国科学院大学 模式识别国家重点实验室）
- MAIS, CASIA（中国科学院自动化所 模式识别国家重点实验室）
- CAIR, HKSIS, CAS（中国科学院香港创新研究院 计算机与信息工程实验室）
- SCSE, FIE, M.U.S.T（澳门科技大学 资讯科技学院）
机构由 AI 辅助整理，请以论文原文为准。
