Research map / Image generation / Editing and style transfer
Towards Trustworthy and Identifiable Virtual Face Generation
Chunyang Li, Haoyue Wang, Zhenxing Qian, Sheng Li, Xinpeng Zhang, Jian liu, Yixuan Pei, Weiqiang Wang
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 |
|---|---|---|---|
| add diversity loss to VIP training (ablation) | VIP · CelebA | diversity: 0.001 -> 0.881 | Improved |
| add anonymization loss to VIP training (ablation) | VIP · CelebA | protection rate: 0.844 -> 0.979 | Improved |
| add intra-identity loss (ablation) | VIP · CelebA | EER: 0.122 -> 0.036 | Improved |
| add inter-identity loss (ablation) | VIP · CelebA | EER: 0.055 -> 0.036 | Improved |
| add distribution regularization loss (ablation) | VIP · CelebA | FID: 73.503 -> 33.530 | Improved |
| add anonymization loss to VIP training (ablation) | VIP · CelebA | AUC: 0.988 -> 0.988 | No clear effect |
| add pose condition (3D normal map via ControlNet) (ablation) | PoseID-Diff · CelebA | pose and expression preservation | Improved |
| use IGGW identity-bound watermark instead of static-pattern watermarks | generative watermarking · Watermark forgery inversion-and-regeneration | attack success rate (%): 33.4 -> 1.5 (best baseline Tree-Ring) | Improved |
| use IGGW identity-bound watermark instead of PRC | generative watermarking · Watermark forgery face-swap | attack success rate (%): 81.4 -> 18.2 | Improved |
| replace GAN-based IVF generation with diffusion TIVDiff | IVFG · CelebA | FID: 186.685 -> 33.530 | Improved |
Closest papers by meaning
- Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning (NeurIPS 2026 · similarity 0.86)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.84)
- How Private is Private? A Comparative Study for Face De-Identification (NeurIPS 2026 · similarity 0.83)
- ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling (NeurIPS 2024 · similarity 0.83)
- $\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition (NeurIPS 2024 · similarity 0.83)
- Enhancing Facial Privacy Protection via Weakening Diffusion Purification (CVPR 2025 · similarity 0.83)
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.
