Synthetic Face Generation

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

IDPrior: Decoupling Identity Generation from Facial Image Synthesis
Nov 5, 2026Fadi Boutros, Meriç Demirörs, Darian Tomašević +2Synthetic Face Generation Image Generation
Fraunhofer Institute for Computer Graphics Research IGD, Germany · University of Ljubljana, Slovenia · TU Darmstadt, Germany
SynthFaces: Balanced Large Scale Human Dataset
Oct 29, 2026Sergey Karpukhin, Denis Bobkov, Kirill Morozov +1Synthetic Face Generation Synthetic Data Generation
FusionBrain Lab, AXXX Moscow, Russia · HSE University Moscow, Russia · MSU Moscow, Russia
SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation
May 29, 2026Yuxi Mi, Qiuyang Yuan, Jianqing Xu +5Synthetic Face Generation Image Generation
Fudan University Shanghai, China · Youtu Lab, Tencent Shanghai, China · WeChat Pay Lab33, Tencent Shenzhen, China
PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models
May 21, 2026Jose Edgar Hernandez Cancino Estrada, Mauro Díaz Lupone, Žiga Emeršič +3Synthetic Face Generation Latent Diffusion Models
University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia · University of Ljubljana, Faculty of Electrical Engineering, Ljubljana, Slovenia
Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
May 18, 2026Yuyang Ji, Yixuan Shen, Anil Jain +2Synthetic Face Generation Face Recognition
Department of Computer Science, Drexel University · Department of Computer Science and Engineering, Michigan State University · Department of Computer Science, University of North Carolina at Chapel Hill
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
May 14, 2026Yang Yue, Fangyun Wei, Tianyu He +10Synthetic Face Generation Image Tokenization
Tsinghua University · Microsoft Research
IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation
Feb 21, 2026Fadi Boutros, Eduarda Caldeira, Tahar Chettaoui +1Synthetic Face Generation Synthetic Data Generation
Fraunhofer Institute for Computer Graphics Research IGD, Germany · TU Darmstadt, Germany
Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation
Jan 18, 2026Mengting Wei, Aditya Gulati, Guoying Zhao +1Synthetic Face Generation Conditional Image Generation
University of Oulu, Oulu, Finland · ELLIS Alicante, Alicante, Spain

Nov 5, 2026J/K move · Enter open · S save

IDPrior: Decoupling Identity Generation from Facial Image Synthesis

Fadi Boutros, Meriç Demirörs, Darian Tomašević, Vitomir Štruc+1

Fraunhofer Institute for Computer Graphics Research IGD, Germany · University of Ljubljana, Slovenia · TU Darmstadt, Germany

Synthetic Face Generation Image Generation Diffusion-Based Image Generation Conditional Image Generation

Open paper AskPDF arXiv

Large-scale identity-labeled face datasets are essential for training modern face recognition models, yet collecting and annotating such data is costly and raises privacy and ethical concerns. Existing synthetic face generation methods typically derive identities from predefined class labels, unconditional image generation, or predefined latent sampling strategies, without explicitly modeling the underlying distribution of facial identities. In this paper, we propose IDPrior, a two-stage framework that decouples identity generation from image synthesis. We first learn a diffusion prior in the embedding space of a pretrained face recognition model to model the distribution of facial identities and generate novel identity embeddings. These embeddings are then used to condition a pretrained identity-conditioned diffusion model (DM), enabling the synthesis of multiple images of the same identity. This modular design provides a scalable approach to identity generation while remaining compatible with existing and future identity-conditioned DMs. Experiments indicate that IDPrior generates diverse and well-separated identities while maintaining a closer correspondence to the distribution of authentic identities. Face recognition models trained on datasets generated using IDPrior-generated identities achieve competitive or improved performance compared with existing synthetic-data-based methods across multiple face verification benchmarks. Code and generated datasets are publicly available at https://github.com/fdbtrs/IDperturb.