Research map / 3D vision / Face and shape
Dual-Generator Face Reenactment
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 localization loss (ablation) | DG IDSG · RaFD | ACE: 8.07 ± 2.59 -> 6.93 ± 1.90 | Helped |
| add action loss after localization loss (ablation) | DG IDSG · RaFD | ACE: 6.93 ± 1.90 -> 6.61 ± 1.65 | Helped |
| add visible local shape loss (ablation) | DG IDSG · RaFD | ACE: 6.61 ± 1.65 -> 4.13 ± 1.12 | Helped |
| add identity loss (ablation) | DG RFG · RaFD | CSIM: 0.211 -> 0.775 | Helped |
| add style consistency loss (ablation) | DG RFG · RaFD | CSIM: 0.775 -> 0.803 | Helped |
| add landmark loss (ablation) | DG RFG · RaFD | CSIM: 0.803 -> 0.844 | Helped |
| add shape discriminator (ablation) | DG RFG · RaFD | FID: 5.59 -> 3.99 | Helped |
Closest papers by meaning
- Pose Adapted Shape Learning for Large-Pose Face Reenactment (CVPR 2024 · similarity 0.89)
- FReeNet: Multi-Identity Face Reenactment (CVPR 2020 · similarity 0.87)
- HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion (CVPR 2025 · similarity 0.85)
- JR2Net: Joint Monocular 3D Face Reconstruction and Reenactment (AAAI 2023 · similarity 0.84)
- ControlFace: Harnessing Facial Parametric Control for Face Rigging (CVPR 2025 · similarity 0.83)
- ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image (AAAI 2025 · similarity 0.82)
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.