FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Ismayilov, Raul, Sero, Dzemila, Spreeuwers, Luuk
Format: Recurso digital
Published: Zenodo 2025
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901968726786048
author Ismayilov, Raul
Sero, Dzemila
Spreeuwers, Luuk
author_facet Ismayilov, Raul
Sero, Dzemila
Spreeuwers, Luuk
contents <p dir="ltr">Synthetic face datasets are increasingly used to overcome the limitations of real-world biometric data, including privacy concerns, demographic imbalance, and high collection costs. However, many existing methods lack fine-grained control over identity attributes and fail to produce paired, identity-consistent images under structured capture conditions. We introduce FLUXSynID, a framework for generating high-resolution synthetic face datasets along with a dataset of 14,889 synthetic identities. We generate synthetic faces with user-defined identity attribute distributions, offering both document-style and trusted live capture images. The dataset generated using the FLUXSynID framework shows improved alignment with real-world identity distributions and greater inter-class diversity compared to prior work. Our work is publicly released to support biometric research, including face recognition and morphing attack detection.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17511960
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images
Ismayilov, Raul
Sero, Dzemila
Spreeuwers, Luuk
<p dir="ltr">Synthetic face datasets are increasingly used to overcome the limitations of real-world biometric data, including privacy concerns, demographic imbalance, and high collection costs. However, many existing methods lack fine-grained control over identity attributes and fail to produce paired, identity-consistent images under structured capture conditions. We introduce FLUXSynID, a framework for generating high-resolution synthetic face datasets along with a dataset of 14,889 synthetic identities. We generate synthetic faces with user-defined identity attribute distributions, offering both document-style and trusted live capture images. The dataset generated using the FLUXSynID framework shows improved alignment with real-world identity distributions and greater inter-class diversity compared to prior work. Our work is publicly released to support biometric research, including face recognition and morphing attack detection.</p>
title FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images
url https://doi.org/10.5281/zenodo.17511960