Research map / Image generation / Text-to-image diffusion
Universal Fingerprint Generation: Controllable Diffusion Model With Multimodal Conditions
Steven A. Grosz, Anil K. Jain
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on GenPrint synthetic data instead of FPGAN-Control | ResNet50 · N2N slap-rolled-contactless | TAR@FAR=0.1%: 74.52 -> 86.08 | Improved |
| train on GenPrint synthetic data instead of PrintsGAN | ResNet50 · NIST SD27 latent-rolled | TAR@FAR=0.1%: 18.60 -> 39.53 | Improved |
| train on GenPrint instead of PrintsGAN | ResNet50 · NIST SD4 rolled-rolled | TAR@FAR=0.1%: 96.15 -> 97.85 | Improved |
| train on GenPrint synthetic data instead of the real N2N set | ResNet50 · PolyU contact-contactless | TAR@FAR=0.1%: 47.08 -> 75.26 | Improved |
| add GenPrint synthetic impressions to N2N | ResNet50 · PolyU contact-contactless | TAR@FAR=0.1%: 47.08 -> 90.90 | Improved |
| add FPGAN-Control synthetic data to N2N | ResNet50 · PolyU contact-contactless | TAR@FAR=0.1%: 47.08 -> 68.25 | Improved |
| add GenPrint synthetic impressions to 35,000 real MSP identities | ResNet50 · NIST SD27 latent-rolled | TAR@FAR=0.1%: 62.02 -> 69.38 | Improved |
| add GenPrint synthetic impressions to 35,000 real MSP identities | ResNet50 · NIST SD4 rolled-rolled | TAR@FAR=0.1%: 99.80 -> 99.70 | No clear effect |
| use GenPrint instead of FPGAN-Control on ViT | ViT · PolyU contact-contact | TAR@FAR=0.1%: 45.92 -> 95.75 | Improved |
| use GenPrint instead of FPGAN-Control on ResNet18 | ResNet18 · NIST SD27 latent-rolled | TAR@FAR=0.1%: 8.14 -> 23.64 | Improved |
| use GenPrint instead of SFinGe | ResNet50 · N2N slap-rolled-contactless | TAR@FAR=0.1%: 7.62 -> 86.08 | Improved |
| generate 100,000 identities with GenPrint rather than PrintsGAN | identity generator · duplicate identities | duplicate identity rate (%): 14.43% -> 0.535% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PrintsGAN — PrintsGAN: Synthetic Fingerprint Generator (TPAMI 2022) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ManiFPT: Defining and Analyzing Fingerprints of Generative Models (CVPR 2024 · similarity 0.85)
- OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting (AAAI 2025 · similarity 0.85)
- WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.84)
- Fingerprinting Denoising Diffusion Probabilistic Models (CVPR 2025 · similarity 0.83)
- Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models (CVPR 2025 · similarity 0.83)
- Scalable Fingerprinting of Large Language Models (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
