AI Paper Atlas

Research map / Image generation / Editing and style transfer

FVeinSyn: Synthetic Finger Vein Image Generator

Yifan Wang, Jie Gui, Adams Wai Kin KONG, Baosheng Yu, Changsheng Chen, Qi Li, Zhenan Sun, James Tin-Yau Kwok, Alex C. Kot

TPAMI 2026 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
train on FVeinSyn instead of real data with same number of identitiesrecognition model · Open-set recognition (average)TAR@FAR=1e-3: 0.6428 -> 0.7976Improved
scale FVeinSyn to 10k identities x 50 samplesrecognition model · Open-set recognition (average)TAR@FAR=1e-3: 0.7976 -> 0.9171Improved
increase samples per identity from 10 to 50 at 1.9k identitiesFVeinSyn · Open-set recognition (average)TAR@FAR=1e-3: 0.7976 -> 0.8625Improved
increase identities from 1.9k to 10k at 10 samples eachFVeinSyn · Open-set recognition (average)TAR@FAR=1e-3: 0.7976 -> 0.8576Improved
pretrain with FVeinSyn before training on real datarecognition model · Cross-dataset evaluation (average over test sets)TAR@FAR=1e-3: 0.2106 -> 0.7622Improved
pretrain with FVeinSyn on HKPU-FV test setrecognition model · Cross-dataset HKPU-FVTAR@FAR=1e-3: 0.1823 -> 0.7937Improved
use FVeinSyn pretraining with only 100 identities instead of real data with 1,969recognition model · Limited identitiesTAR@FAR=1e-3: 0.6222 -> 0.6924Improved
use FVeinSyn instead of real data at 50 identitiesrecognition model · Limited identities (50 IDs)TAR@FAR=1e-3: 0.0008 -> 0.3148Improved
use FVeinSyn instead of BTUSyn for one-shot enrollmentrecognition model · Few-shot N=1, PLUS-FV3TAR@FAR=1e-3: 0.3834 -> 0.8874Improved
use FVeinSyn instead of BTUSyn for one-shot enrollmentrecognition model · Few-shot N=1, THU-FV3TAR@FAR=1e-3: 0.6213 -> 0.5826Hurt
use all mixed intra-class variations instead of shift only (ablation)ICDG · ICDG ablation (average)TAR@FAR=1e-3: 0.8789 -> 0.9171Improved
use all mixed intra-class variations instead of skin scattering only (ablation)ICDG · ICDG ablation (average)TAR@FAR=1e-3: 0.8801 -> 0.9171Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy