# Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Models

arXiv: https://arxiv.org/abs/2411.02188 · HTML: https://mlsanity.com/paper/2411.02188/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [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)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data](https://mlsanity.com/paper/2206.10520/) (2022)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [SDFR: Synthetic Data for Face Recognition Competition](https://mlsanity.com/paper/2404.04580/) (2024)
- [Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognition](https://mlsanity.com/paper/2305.00358/) (2023)
- [ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation](https://mlsanity.com/paper/2307.05151/) (2023)
- [Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2404.10378/) (2024)
- [FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2311.10476/) (2023)
- [Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion](https://mlsanity.com/paper/2405.00228/) (2024)
- [SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data](https://mlsanity.com/paper/2308.14852/) (2023)
- [Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognition](https://mlsanity.com/paper/2407.07627/) (2024)

## Built on by (most cited first, 9 of 9)

- [Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise](https://mlsanity.com/paper/2510.17372/) (2025)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices](https://mlsanity.com/paper/2504.19646/) (2025)
- [Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data](https://mlsanity.com/paper/2507.20782/) (2025)
- [Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation](https://mlsanity.com/paper/2605.04769/) (2026)
- [Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion](https://mlsanity.com/paper/2507.16790/) (2025)
- [ArtFace: Towards Historical Portrait Face Identification via Model Adaptation](https://mlsanity.com/paper/2508.20626/) (2025)
- [Benchmarking Face Recognition without Real Faces](https://mlsanity.com/paper/2607.14932/) (2026)
- [SynThermFace: Amplifying Limited Paired Data for Visible-Thermal Face Recognition via Synthetic Data Generation](https://mlsanity.com/paper/2609.10303/) (2026)

## Abstract (arXiv)

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale datasets are often collected without explicit consent, raising ethical and privacy concerns. To address this, there have been proposals to use synthetic datasets for training face recognition models. Yet, such models still rely on real data to train the generative models and generally exhibit inferior performance compared to those trained on real datasets. One of these datasets, DigiFace, uses a graphics pipeline to generate different identities and intra-class variations without using real data in model training. However, the performance of this approach is poor on face recognition benchmarks, possibly due to the lack of realism in the images generated by the graphics pipeline. In this work, we introduce a novel framework for realism transfer aimed at enhancing the realism of synthetically generated face images. Our method leverages the large-scale face foundation model, and we adapt the pipeline for realism enhancement. By integrating the controllable aspects of the graphics pipeline with our realism enhancement technique, we generate a large amount of realistic variations, combining the advantages of both approaches. Our empirical evaluations demonstrate that models trained using our enhanced dataset significantly improve the performance of face recognition systems over the baseline. The source code and dataset will be publicly accessible at the following link: https://www.idiap.ch/paper/digi2real