# High Fidelity Fingerprint Generation: Quality, Uniqueness, and Privacy

arXiv: https://arxiv.org/abs/2105.10403 · HTML: https://mlsanity.com/paper/2105.10403/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN](https://mlsanity.com/paper/1812.10482/) (2018)
- [Separating the Real from the Synthetic: Minutiae Histograms as Fingerprints of Fingerprints](https://mlsanity.com/paper/1304.5409/) (2013)

## Built on by (most cited first, 14 of 14)

- [PrintsGAN: Synthetic Fingerprint Generator](https://mlsanity.com/paper/2201.03674/) (2022)
- [SpoofGAN: Synthetic Fingerprint Spoof Images](https://mlsanity.com/paper/2204.06498/) (2022)
- [Synthetic Latent Fingerprint Generator](https://mlsanity.com/paper/2208.13811/) (2022)
- [Universal Fingerprint Generation: Controllable Diffusion Model with Multimodal Conditions](https://mlsanity.com/paper/2404.13791/) (2024)
- [Synthesis and Reconstruction of Fingerprints using Generative Adversarial Networks](https://mlsanity.com/paper/2201.06164/) (2022)
- [RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition](https://mlsanity.com/paper/2307.14016/) (2023)
- [FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic Data](https://mlsanity.com/paper/2310.19024/) (2023)
- [Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models](https://mlsanity.com/paper/2503.18312/) (2025)
- [Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques](https://mlsanity.com/paper/2403.13916/) (2024)
- [Synthetic Latent Fingerprint Generation Using Style Transfer](https://mlsanity.com/paper/2309.15734/) (2023)
- [Conditional Synthetic Live and Spoof Fingerprint Generation](https://mlsanity.com/paper/2510.17035/) (2025)
- [Unbalanced Fingerprint Classification for Hybrid Fingerprint Orientation Maps](https://mlsanity.com/paper/2409.00779/) (2024)
- [Intra-finger Variability of Diffusion-based Latent Fingerprint Generation](https://mlsanity.com/paper/2604.10040/) (2026)
- [Identity-Consistent Multi-Pose Generation of Contactless Fingerprints](https://mlsanity.com/paper/2605.03830/) (2026)

## Abstract (arXiv)

In this work, we utilize progressive growth-based Generative Adversarial Networks (GANs) to develop the Clarkson Fingerprint Generator (CFG). We demonstrate that the CFG is capable of generating realistic, high fidelity, 512×512 pixels, full, plain impression fingerprints. Our results suggest that the fingerprints generated by the CFG are unique, diverse, and resemble the training dataset in terms of minutiae configuration and quality, while not revealing the underlying identities of the training data. We make the pre-trained CFG model and the synthetically generated dataset publicly available at https://github.com/keivanB/ClarksonFingerGen