# DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models

arXiv: https://arxiv.org/abs/2405.04538 · HTML: https://mlsanity.com/paper/2405.04538/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 9 of 9)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [A Study on the Evaluation of Generative Models](https://mlsanity.com/paper/2206.10935/) (2022)
- [Synthetic ECG Signal Generation using Probabilistic Diffusion Models](https://mlsanity.com/paper/2303.02475/) (2023)
- [Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN](https://mlsanity.com/paper/1812.10482/) (2018)
- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Synthesis and Reconstruction of Fingerprints using Generative Adversarial Networks](https://mlsanity.com/paper/2201.06164/) (2022)
- [DDPM based X-ray Image Synthesizer](https://mlsanity.com/paper/2401.01539/) (2024)

## Built on by (most cited first, 2 of 2)

- [Conditional Synthetic Live and Spoof Fingerprint Generation](https://mlsanity.com/paper/2510.17035/) (2025)
- [Intra-finger Variability of Diffusion-based Latent Fingerprint Generation](https://mlsanity.com/paper/2604.10040/) (2026)

## Abstract (arXiv)

This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.