IMPOSE generates identity-consistent multi-pose contactless fingerprints via latent diffusion, Sauvola-guided translation, and 3D finger model projection, enabling SOTA cross-modal matching with EER reduced to 8.74% on UWA and 2.26% on PolyU CL2CB.
Synfi: Automatic synthetic fingerprint generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Diffusion-generated synthetic latent fingerprints largely preserve finger identity but introduce small local minutiae inconsistencies and global ridge hallucinations when style or reference quality is mismatched.
citing papers explorer
-
Identity-Consistent Multi-Pose Generation of Contactless Fingerprints
IMPOSE generates identity-consistent multi-pose contactless fingerprints via latent diffusion, Sauvola-guided translation, and 3D finger model projection, enabling SOTA cross-modal matching with EER reduced to 8.74% on UWA and 2.26% on PolyU CL2CB.
-
Intra-finger Variability of Diffusion-based Latent Fingerprint Generation
Diffusion-generated synthetic latent fingerprints largely preserve finger identity but introduce small local minutiae inconsistencies and global ridge hallucinations when style or reference quality is mismatched.