Intra-finger Variability of Diffusion-based Latent Fingerprint Generation

• URL: http://arxiv.org/abs/2604.10040v1
• Date: Sat, 11 Apr 2026 05:24:23 GMT
• Title: Intra-finger Variability of Diffusion-based Latent Fingerprint Generation
• Abstract summary: The primary goal of this work is to evaluate the intra-finger variability of synthetic fingerprints generated using a state-of-the-art diffusion model.<n>We focus on enhancing the latent style diversity of the generative model by constructing a comprehensive.<n>textitlatent style bank curated from seven diverse datasets.<n>We also implement a semi-automated framework to understand the integrity of fingerprint ridges and minutiae in the generated impressions.
• Score: 35.645082991821155
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The primary goal of this work is to systematically evaluate the intra-finger variability of synthetic fingerprints (particularly latent prints) generated using a state-of-the-art diffusion model. Specifically, we focus on enhancing the latent style diversity of the generative model by constructing a comprehensive \textit{latent style bank} curated from seven diverse datasets, which enables the precise synthesis of latent prints with over 40 distinct styles encapsulating different surfaces and processing techniques. We also implement a semi-automated framework to understand the integrity of fingerprint ridges and minutiae in the generated impressions. Our analysis indicates that though the generation process largely preserves the identity, a small number of local inconsistencies (addition and removal of minutiae) are introduced, especially when there are poor quality regions in the reference image. Furthermore, mismatch between the reference image and the chosen style embedding that guides the generation process introduces global inconsistencies in the form of hallucinated ridge patterns. These insights highlight the limitations of existing synthetic fingerprint generators and the need to further improve these models to simultaneously enhance both diversity and identity consistency.

Related papers

• Identity-Consistent Multi-Pose Generation of Contactless Fingerprints [31.932777820189827]
  We propose Identity-Consistent Multi-Pose Generation of Contactless Fingerprints (IMPOSE)<n>IMPOSE is a physics-inspired framework that synthesizes identity-preserving, multi-pose contactless fingerprint samples.<n>Experiments on the UWA and PolyU CL2CB databases demonstrate that fine-tuning fixed-length dense descriptors (FDD) with IMPOSE-synthesized data achieves state-of-the-art cross-modal matching.
  arXiv  Detail & Related papers  (2026-05-05T14:59:03Z)
• IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness [9.981615514164469]
  IrisFP is a novel adversarial-example-based model fingerprinting framework.<n>It positions fingerprints near the intersection of all decision boundaries.<n>It constructs composite-sample fingerprints, each comprising multiple samples close to the multi-boundary intersection.<n>It assesses the discriminative power of generated fingerprints using statistical separability metrics.
  arXiv  Detail & Related papers  (2026-03-26T03:39:29Z)
• Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting [60.15416769662556]
  We study the problem of learning human-like brushstroke generation from a small set of hand-drawn samples.<n>We propose StrokeDiff, a diffusion-based framework with Smooth Regularization (SmR)<n>We show how the learned primitives can be made controllable through a Bézier-based conditioning module.
  arXiv  Detail & Related papers  (2026-03-01T13:42:35Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• Causal Fingerprints of AI Generative Models [18.85839181425287]
  We argue that a complete model fingerprint should reflect the causality between image provenance and model traces.<n>We propose a causality-decoupling framework that disentangles it from image-specific content and style.<n>Our approach outperforms existing methods in model attribution, indicating strong potential for forgery detection, model copyright tracing, and identity protection.
  arXiv  Detail & Related papers  (2025-09-18T20:33:27Z)
• Multi-focal Conditioned Latent Diffusion for Person Image Synthesis [59.113899155476005]
  The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation.<n>We propose a Multi-focal Conditioned Latent Diffusion (MCLD) method to address these limitations.<n>Our approach utilizes a multi-focal condition aggregation module, which effectively integrates facial identity and texture-specific information.
  arXiv  Detail & Related papers  (2025-03-19T20:50:10Z)
• Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling [49.41822427811098]
  We present Kaleido, a novel approach that enhances the diversity of samples by incorporating autoregressive latent priors. Kaleido integrates an autoregressive language model that encodes the original caption and generates latent variables. We show that Kaleido adheres closely to the guidance provided by the generated latent variables, demonstrating its capability to effectively control and direct the image generation process.
  arXiv  Detail & Related papers  (2024-05-31T17:41:11Z)
• Universal Fingerprint Generation: Controllable Diffusion Model with Multimodal Conditions [25.738682467090335]
  GenPrint is a framework to produce fingerprint images of various types while maintaining identity. GenPrint is not confined to replicating style characteristics from the training dataset alone. Results demonstrate the benefits of GenPrint in terms of identity preservation, explainable control, and universality of generated images.
  arXiv  Detail & Related papers  (2024-04-21T23:01:08Z)
• Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques [0.44739156031315924]
  We generate live fingerprints from noise with a variety of methods, and we use image translation techniques to translate live fingerprint images to spoof. We assess the diversity and realism of the generated live fingerprint images mainly through the Fr'echet Inception Distance (FID) and the False Acceptance Rate (FAR)
  arXiv  Detail & Related papers  (2024-03-20T18:36:30Z)
• ManiFPT: Defining and Analyzing Fingerprints of Generative Models [16.710998621718193]
  We formalize the definition of artifact and fingerprint in generative models. We propose an algorithm for computing them in practice. We study the structure of the fingerprints and observe that it is very predictive of the effect of different design choices on the generative process.
  arXiv  Detail & Related papers  (2024-02-16T01:58:35Z)
• Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations [61.132408427908175]
  zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain. With only a single representative text feature instead of real images, the synthesized images gradually lose diversity. We propose a novel method to find semantic variations of the target text in the CLIP space.
  arXiv  Detail & Related papers  (2023-08-21T08:12:28Z)
• Auto-regressive Image Synthesis with Integrated Quantization [55.51231796778219]
  This paper presents a versatile framework for conditional image generation. It incorporates the inductive bias of CNNs and powerful sequence modeling of auto-regression. Our method achieves superior diverse image generation performance as compared with the state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-21T22:19:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.