# Identity-Consistent Multi-Pose Generation of Contactless Fingerprints

arXiv: https://arxiv.org/abs/2605.03830 · HTML: https://mlsanity.com/paper/2605.03830/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 23 of 23)

- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Learning a Fixed-Length Fingerprint Representation](https://mlsanity.com/paper/1909.09901/) (2019)
- [PrintsGAN: Synthetic Fingerprint Generator](https://mlsanity.com/paper/2201.03674/) (2022)
- [C2CL: Contact to Contactless Fingerprint Matching](https://mlsanity.com/paper/2104.02811/) (2021)
- [AFR-Net: Attention-Driven Fingerprint Recognition Network](https://mlsanity.com/paper/2211.13897/) (2022)
- [Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN](https://mlsanity.com/paper/1812.10482/) (2018)
- [High Fidelity Fingerprint Generation: Quality, Uniqueness, and Privacy](https://mlsanity.com/paper/2105.10403/) (2021)
- [Fingerprint Synthesis: Search with 100 Million Prints](https://mlsanity.com/paper/1912.07195/) (2019)
- [SynCoLFinGer: Synthetic Contactless Fingerprint Generator](https://mlsanity.com/paper/2110.09144/) (2021)
- [Monocular 3D Fingerprint Reconstruction and Unwarping](https://mlsanity.com/paper/2205.00967/) (2022)
- [Universal Fingerprint Generation: Controllable Diffusion Model with Multimodal Conditions](https://mlsanity.com/paper/2404.13791/) (2024)
- [SynFi: Automatic Synthetic Fingerprint Generation](https://mlsanity.com/paper/2002.08900/) (2020)
- [Fixed-length Dense Descriptor for Efficient Fingerprint Matching](https://mlsanity.com/paper/2311.18576/) (2023)
- [FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic Data](https://mlsanity.com/paper/2310.19024/) (2023)
- [Finger Pose Estimation for Under-screen Fingerprint Sensor](https://mlsanity.com/paper/2505.02481/) (2025)
- [Fixed-Length Dense Fingerprint Representation with Alignment and Robust Enhancement](https://mlsanity.com/paper/2505.03597/) (2025)
- [Pose-Specific 3D Fingerprint Unfolding](https://mlsanity.com/paper/2404.17149/) (2024)
- [Improving Contactless Fingerprint Recognition with Robust 3D Feature Extraction and Graph Embedding](https://mlsanity.com/paper/2409.08782/) (2024)

## Abstract (arXiv)

Contactless fingerprint recognition has gained increasing attention due to its advantages in hygiene and acquisition flexibility. However, the absence of physical contact constraints introduces severe nonlinear geometric distortions caused by free finger poses in 3D space, resulting in a substantial cross-modal domain gap between contactless and conventional contact-based fingerprints. Existing solutions largely rely on explicit geometric correction or image enhancement, which are fragile under extreme pose variations. In this paper, we propose Identity-Consistent Multi-Pose Generation of Contactless Fingerprints (IMPOSE), a physics-inspired framework that synthesizes identity-preserving, multi-pose contactless fingerprint samples to empower recognition models. IMPOSE consists of three stages: (1) rolled fingerprint identity generation via latent diffusion with discrete codebook representations, (2) cross-modal translation from rolled to contactless modality guided by Sauvola-based local adaptive binarization as an identity anchor, and (3) physics-based multi-pose simulation through 3D finger model texture mapping and projection. The generated samples maintain strict identity consistency at the ridge topology level and spatial alignment with standard fingerprint coordinate space. Extensive 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, reducing EER to 8.74% on UWA and 2.26% on PolyU CL2CB. Synthetic data also yields consistent gains across mainstream representations including DeepPrint and AFRNet, and the hybrid strategy combining synthetic and real data achieves the best overall results. The code and generated samples are available at https://github.com/Yu-Yy/IMPOSE.