dc-GAN: Dual-Conditioned GAN for Face Demorphing From a Single Morph

TL;DR

This paper introduces dc-GAN, a dual-conditioned generative adversarial network that effectively demorphs face images into their original components, overcoming previous limitations like morph replication and dependency on shared identities.

Contribution

The paper presents a novel dual-conditioned GAN for face demorphing that is highly generalizable and produces high-fidelity reconstructions, addressing key limitations of existing methods.

Findings

Overcomes morph replication problem

Produces high-fidelity face reconstructions

Effective on multiple datasets

Abstract

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.