Facial Demorphing from a Single Morph Using a Latent Conditional GAN

TL;DR

This paper introduces a novel latent conditional GAN-based method for demorphing face images, effectively recovering constituent faces from a single morph even with unseen morph techniques and styles.

Contribution

The proposed method overcomes limitations of existing demorphing techniques by decomposing morphs in latent space, enabling accurate demorphing across various morphing methods and face styles.

Findings

Outperforms existing demorphing methods significantly.

Successfully demorphs images created from unseen morph techniques.

Produces high-fidelity, realistic demorphed face images.

Abstract

A morph is created by combining two (or more) face images from two (or more) identities to create a composite image that is highly similar to all constituent identities, allowing the forged morph to be biometrically associated with more than one individual. Morph Attack Detection (MAD) can be used to detect a morph, but does not reveal the constituent images. Demorphing - the process of deducing the constituent images - is thus vital to provide additional evidence about a morph. Existing demorphing methods suffer from the morph replication problem, where the outputs tend to look very similar to the morph itself, or assume that train and test morphs are generated using the same morph technique. The proposed method overcomes these issues. The method decomposes a morph in latent space allowing it to demorph images created from unseen morph techniques and face styles. We train our method on morphs created from synthetic faces and test on morphs created from real faces using different morph techniques. Our method outperforms existing methods by a considerable margin and produces high fidelity demorphed face images.