FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912485669339136 |
|---|---|
| author | Ismayilov, Raul Sero, Dzemila Spreeuwers, Luuk |
| author_facet | Ismayilov, Raul Sero, Dzemila Spreeuwers, Luuk |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images Ismayilov, Raul Sero, Dzemila Spreeuwers, Luuk Computer Vision and Pattern Recognition 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. |
| title | FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.07530 |