Research map / Image generation / Editing and style transfer
FReeNet: Multi-Identity 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 |
|---|---|---|---|
| Replace Pix2Pix with the GAG generator | Face reenactment on RaFD · RaFD | SSIM: 0.629 -> 0.659 | Helped |
| Replace Pix2Pix with the GAG generator | Face reenactment on RaFD · RaFD | FID: 12.84 -> 11.67 | Helped |
| Add ULC to GAG (ablation) | FReeNet · RaFD | SSIM: 0.659 -> 0.711 | Helped |
| Add ULC to GAG (ablation) | FReeNet · RaFD | FID: 11.67 -> 13.26 | Hurt |
| Add triplet perceptual loss to GAG+ULC (ablation) | FReeNet · RaFD | SSIM: 0.711 -> 0.717 | Helped |
| Add triplet perceptual loss to GAG+ULC (ablation) | FReeNet · RaFD | FID: 13.26 -> 12.17 | Helped |
| Add cycle-consistent loss to ULC training (ablation) | ULC · RaFD | ACE: 7.236±0.015 -> 4.526±0.015 | Helped |
| Add discriminator losses to ULC training (ablation) | ULC · RaFD | ACE: 4.526±0.015 -> 0.895±0.010 | Helped |
| Use full FReeNet instead of Pix2Pix | Face reenactment · RaFD | AMT: 41.3% -> 74.9% | Helped |
| Use one unified FReeNet model for multiple identities | Multi-identity reenactment · All transformations among n persons | Parameters (M), transfer: 4.5 | Helped |
| Use one unified FReeNet model for multiple identities | Multi-identity reenactment · All transformations among n persons | Speed (FPS): 57 FPS; Pix2Pix 75, Xu et al. 73, ReenactGAN 48, X2Face 16 | Mixed |
Closest papers by meaning
- FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features (CVPR 2024 · similarity 0.87)
- TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction (ICLR 2025 · similarity 0.86)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.85)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.85)
- Enhancing Identity-Deformation Disentanglement in StyleGAN for One-Shot Face Video Re-Enactment (AAAI 2025 · similarity 0.85)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.85)
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.