# Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models

arXiv: https://arxiv.org/abs/2503.18312 · HTML: https://mlsanity.com/paper/2503.18312/

## Key facts

- Cited by 3 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 31 of its 52 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [A Survey on Generative Diffusion Model](https://mlsanity.com/paper/2209.02646/) (2022)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [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)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition](https://mlsanity.com/paper/2009.09399/) (2020)
- [PrintsGAN: Synthetic Fingerprint Generator](https://mlsanity.com/paper/2201.03674/) (2022)
- [DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation](https://mlsanity.com/paper/2203.07931/) (2022)
- [It's All About Your Sketch: Democratising Sketch Control in Diffusion Models](https://mlsanity.com/paper/2403.07234/) (2024)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Dual Variational Generation for Low-Shot Heterogeneous Face Recognition](https://mlsanity.com/paper/1903.10203/) (2019)
- [Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors](https://mlsanity.com/paper/2409.02979/) (2024)
- [Palmprint Recognition in Uncontrolled and Uncooperative Environment](https://mlsanity.com/paper/1911.12514/) (2019)
- [High Fidelity Fingerprint Generation: Quality, Uniqueness, and Privacy](https://mlsanity.com/paper/2105.10403/) (2021)
- [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)
- [Towards Palmprint Verification On Smartphones](https://mlsanity.com/paper/2003.13266/) (2020)

## Built on by (most cited first, 3 of 3)

- [FingerVeinSyn-5M: A Million-Scale Dataset and Benchmark for Finger Vein Recognition](https://mlsanity.com/paper/2506.03635/) (2025)
- [FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation](https://mlsanity.com/paper/2604.09989/) (2026)
- [FVeinSyn: Synthetic Finger Vein Image Generator](https://mlsanity.com/paper/2608.27527/) (2026)

## Abstract (arXiv)

Palmprint recognition is significantly limited by the lack of large-scale publicly available datasets. Previous methods have adopted B'ezier curves to simulate the palm creases, which then serve as input for conditional GANs to generate realistic palmprints. However, without employing real data fine-tuning, the performance of the recognition model trained on these synthetic datasets would drastically decline, indicating a large gap between generated and real palmprints. This is primarily due to the utilization of an inaccurate palm crease representation and challenges in balancing intra-class variation with identity consistency. To address this, we introduce a polynomial-based palm crease representation that provides a new palm crease generation mechanism more closely aligned with the real distribution. We also propose the palm creases conditioned diffusion model with a novel intra-class variation control method. By applying our proposed K-step noise-sharing sampling, we are able to synthesize palmprint datasets with large intra-class variation and high identity consistency. Experimental results show that, for the first time, recognition models trained solely on our synthetic datasets, without any fine-tuning, outperform those trained on real datasets. Furthermore, our approach achieves superior recognition performance as the number of generated identities increases.