无需参考图，可还原任意人脸合成图像的原始身份。
diffDemorph: Extending Reference-Free Demorphing to Unseen Faces
- 基于扩散模型实现无参考人脸解混，不依赖特定合成方式或风格。
- 在六个数据集上提升超59%性能，且训练用合成图、测试用真实图。
- 首次支持跨不同人脸合成技术与风格的泛化，适合实际应用。
人脸合成是将两张对应不同身份的人脸图像融合生成一张复合图像，使其同时匹配两个原始身份。无参考（Reference-Free, RF）解混旨在仅凭合成图像还原原始身份，无需额外参考图。现有方法受限于对训练与测试中合成方式（如基于特征点）和人脸风格（如证件照）的假设。本文提出一种新型扩散模型方法 diffDeMorph，能高保真地从复合图像中解耦出原始人脸。该方法首次实现跨合成技术与人脸风格的泛化，在所有测试数据集上均优于当前最优方法至少59.46%。模型在合成图像上训练，却能在真实合成图像上有效还原，显著提升实用性。六组数据集及两种人脸匹配器的实验验证了其有效性。
原文摘要 · Abstract (English)
A face morph is created by combining two face images corresponding to two identities to produce a composite that successfully matches both the constituent identities. Reference-free (RF) demorphing reverses this process using only the morph image, without the need for additional reference images. Previous RF demorphing methods are overly constrained, as they rely on assumptions about the distributions of training and testing morphs such as the morphing technique used (e.g., landmark-based) and face image style (e.g., passport photos). In this paper, we introduce a novel diffusion-based approach, referred to as diffDeMorph, that effectively disentangles component images from a composite morph image with high visual fidelity. Our method is the first to generalize across morph techniques and face styles, beating the current state of the art by $\geq 59.46\%$ under a common training protocol across all datasets tested. We train our method on morphs created using synthetically generated face images and test on real morphs, thereby enhancing the practicality of the technique. Experiments on six datasets and two face matchers establish the utility and efficacy of our method.
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。