# Facial Demorphing via Identity Preserving Image Decomposition

arXiv: https://arxiv.org/abs/2408.10993 · HTML: https://mlsanity.com/paper/2408.10993/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 48 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [An Exponential Learning Rate Schedule for Deep Learning](https://mlsanity.com/paper/1910.07454/) (2019)
- [Face Morphing Attack Generation & Detection: A Comprehensive Survey](https://mlsanity.com/paper/2011.02045/) (2020)
- [Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors](https://mlsanity.com/paper/2203.06691/) (2022)
- [MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders](https://mlsanity.com/paper/2302.01843/) (2023)
- [Fast Image Processing with Fully-Convolutional Networks](https://mlsanity.com/paper/1709.00643/) (2017)
- [Differential Morph Face Detection using Discriminative Wavelet Sub-bands](https://mlsanity.com/paper/2106.13178/) (2021)
- [Image Smoothing via Unsupervised Learning](https://mlsanity.com/paper/1811.02804/) (2018)
- [Morph Detection Enhanced by Structured Group Sparsity](https://mlsanity.com/paper/2111.14943/) (2021)
- [Facial De-morphing: Extracting Component Faces from a Single Morph](https://mlsanity.com/paper/2209.02933/) (2022)
- [SDeMorph: Towards Better Facial De-morphing from Single Morph](https://mlsanity.com/paper/2308.11442/) (2023)
- [Semi-Global Weighted Least Squares in Image Filtering](https://mlsanity.com/paper/1705.01674/) (2017)

## Built on by (most cited first, 8 of 8)

- [dc-GAN: Dual-Conditioned GAN for Face Demorphing From a Single Morph](https://mlsanity.com/paper/2411.14494/) (2024)
- [Metric for Evaluating Performance of Reference-Free Demorphing Methods](https://mlsanity.com/paper/2501.12319/) (2025)
- [FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images](https://mlsanity.com/paper/2505.07530/) (2025)
- [diffDemorph: Extending Reference-Free Demorphing to Unseen Faces](https://mlsanity.com/paper/2505.14527/) (2025)
- [Facial Demorphing from a Single Morph Using a Latent Conditional GAN](https://mlsanity.com/paper/2507.18566/) (2025)
- [DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion](https://mlsanity.com/paper/2604.21627/) (2026)
- [DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection](https://mlsanity.com/paper/2604.17961/) (2026)
- [Enhancing Single-Image Facial Demorphing using Multimodal Large Language Models](https://mlsanity.com/paper/2605.25442/) (2026)

## Abstract (arXiv)

A face morph is created by combining the face images usually pertaining to two distinct identities. The goal is to generate an image that can be matched with two identities thereby undermining the security of a face recognition system. To deal with this problem, several morph attack detection techniques have been developed. But these methods do not extract any information about the underlying bonafides used to create them. Demorphing addresses this limitation. However, current demorphing techniques are mostly reference-based, i.e, they need an image of one of the identities to recover the other. In this work, we treat demorphing as an ill-posed decomposition problem. We propose a novel method that is reference-free and recovers the bonafides with high accuracy. Our method decomposes the morph into several identity-preserving feature components. A merger network then weighs and combines these components to recover the bonafides. Our method is observed to reconstruct high-quality bonafides in terms of definition and fidelity. Experiments on the CASIA-WebFace, SMDD and AMSL datasets demonstrate the effectiveness of our method.