dc-GAN: Dual-Conditioned GAN for Face Demorphing From a Single Morph
This addresses security vulnerabilities in facial recognition systems by enabling recovery of original identities from morphed images, though it is an incremental improvement over existing demorphing techniques.
The paper tackles the problem of face demorphing from a single morph image by proposing dc-GAN, a dual-conditioned GAN that overcomes morph replication and generalizes across datasets, achieving high-fidelity reconstructions as demonstrated on AMSL, FRLL-Morphs, and MorDiff datasets.
A facial morph is an image strategically created by combining two face images pertaining to two distinct identities. The goal is to create a face image that can be matched to two different identities by a face matcher. Face demorphing inverts this process and attempts to recover the original images constituting a facial morph. Existing demorphing techniques have two major limitations: (a) they assume that some identities are common in the train and test sets; and (b) they are prone to the morph replication problem, where the outputs are merely replicates of the input morph. In this paper, we overcome these issues by proposing dc-GAN (dual-conditioned GAN), a novel demorphing method conditioned on the morph image as well as the embedding extracted from the image. Our method overcomes the morph replication problem and produces high-fidelity reconstructions of the constituent images. Moreover, the proposed method is highly generalizable and applicable to both reference-based and reference-free demorphing methods. Experiments were conducted using the AMSL, FRLL-Morphs, and MorDiff datasets to demonstrate the efficacy of the method.