diffDemorph: Extending Reference-Free Demorphing to Unseen Faces
This addresses the need for more practical and generalizable demorphing techniques in security and biometric applications, representing a significant advance beyond previous constrained methods.
The paper tackled the problem of reference-free demorphing of face images by introducing diffDeMorph, a diffusion-based method that generalizes across morph techniques and face styles, achieving a performance improvement of at least 59.46% over the state of the art.
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.