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
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 |
|---|---|---|---|
| scale virtual identities from 10K to 120K (0.5M to 6.0M images) (ablation) | VIGFace · Avg of 5 benchmarks | verification accuracy (%): 92.56 -> 94.91 | Improved |
| scale virtual identities from 10K to 60K (0.5M to 1.2M images) (ablation) | VIGFace · Avg of 5 benchmarks | verification accuracy (%): 92.56 -> 94.64 | Improved |
| add synthetic images of real IDs to real data (ablation) | VIGFace(B) · Avg of 5 benchmarks (augmentation) | verification accuracy (%): 94.93 -> 95.85 | Improved |
| add synthetic virtual IDs to real data (ablation) | VIGFace(B) · Avg of 5 benchmarks (augmentation) | verification accuracy (%): 94.93 -> 95.19 | Improved |
| add both real-ID synthesis and virtual IDs to real data (ablation) | VIGFace(B) · Avg of 5 benchmarks (augmentation) | verification accuracy (%): 94.93 -> 95.92 | Improved |
| add GANDiffFace synthetic data to real data | GANDiffFace · Avg of 5 benchmarks (augmentation) | verification accuracy (%): 94.93 -> 94.80 | Hurt |
| add HSFace20K synthetic data to real data | HSFace20K · Avg of 5 benchmarks (augmentation) | verification accuracy (%): 94.93 -> 95.59 | Improved |
| add landmark-pose conditioning (virtual-only training) (ablation) | VIGFace(B) · CFP-FP | verification accuracy (%): 96.63 -> 97.07 | Improved |
| add landmark-pose conditioning (virtual-only training) (ablation) | VIGFace(L) · CPLFW | verification accuracy (%): 90.23 -> 91.12 | Improved |
| train on VIGFace(L) instead of real CASIA-WebFace | VIGFace(L) · AgeDB | verification accuracy (%): 94.68 -> 93.82 | Hurt |
| add virtual embeddings to update virtual prototypes (ablation) | Stage 1 ArcFace · prototype similarity | verification accuracy (%) | Improved |
| set classifier-free guidance weight to 4.0 (ablation) | diffusion model · consistency vs variance | verification 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.
- CemiFace — CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition (NeurIPS 2024) · better on 2 of 2 shared results
- Arc2Face — Arc2Face: A Foundation Model for ID-Consistent Human Faces (ECCV 2024) · better on 2 of 2 shared results
- DCFace — DCFace: Synthetic Face Generation With Dual Condition Diffusion Model (CVPR 2023) · better on 2 of 2 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
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.89)
- Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning (NeurIPS 2026 · similarity 0.88)
- HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere (ICLR 2025 · similarity 0.87)
- CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition (NeurIPS 2024 · similarity 0.87)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.87)
- $\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition (NeurIPS 2024 · similarity 0.86)
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.
