AI Paper Atlas

Research map / Image generation / Editing and style transfer

VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition Dataset

Minsoo Kim, Min-Cheol Sagong, Gi Pyo Nam, Junghyun Cho, Ig-Jae Kim

ICCV 2025 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 6 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
scale virtual identities from 10K to 120K (0.5M to 6.0M images) (ablation)VIGFace · Avg of 5 benchmarksverification accuracy (%): 92.56 -> 94.91Improved
scale virtual identities from 10K to 60K (0.5M to 1.2M images) (ablation)VIGFace · Avg of 5 benchmarksverification accuracy (%): 92.56 -> 94.64Improved
add synthetic images of real IDs to real data (ablation)VIGFace(B) · Avg of 5 benchmarks (augmentation)verification accuracy (%): 94.93 -> 95.85Improved
add synthetic virtual IDs to real data (ablation)VIGFace(B) · Avg of 5 benchmarks (augmentation)verification accuracy (%): 94.93 -> 95.19Improved
add both real-ID synthesis and virtual IDs to real data (ablation)VIGFace(B) · Avg of 5 benchmarks (augmentation)verification accuracy (%): 94.93 -> 95.92Improved
add GANDiffFace synthetic data to real dataGANDiffFace · Avg of 5 benchmarks (augmentation)verification accuracy (%): 94.93 -> 94.80Hurt
add HSFace20K synthetic data to real dataHSFace20K · Avg of 5 benchmarks (augmentation)verification accuracy (%): 94.93 -> 95.59Improved
add landmark-pose conditioning (virtual-only training) (ablation)VIGFace(B) · CFP-FPverification accuracy (%): 96.63 -> 97.07Improved
add landmark-pose conditioning (virtual-only training) (ablation)VIGFace(L) · CPLFWverification accuracy (%): 90.23 -> 91.12Improved
train on VIGFace(L) instead of real CASIA-WebFaceVIGFace(L) · AgeDBverification accuracy (%): 94.68 -> 93.82Hurt
add virtual embeddings to update virtual prototypes (ablation)Stage 1 ArcFace · prototype similarityverification accuracy (%)Improved
set classifier-free guidance weight to 4.0 (ablation)diffusion model · consistency vs varianceverification accuracy (%)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most 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

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