Research map / Video / Video generation
ReenactGAN: Learning to Reenact Faces via Boundary Transfer
Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, Chen Change Loy
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 the boundary latent space to the encoder-decoder reconstruction (vs plain Pix2Pix) (ablation) | Pix2Pix encoder-decoder · Face reconstruction (qualitative) | reconstruction quality | No clear effect |
| add the target-specific boundary transformer before the decoder (ablation) | ReenactGAN decoder · Face reenactment (qualitative and user study) | image quality (TrueSkill) and artifacts | Improved |
| add the shape constraint loss to the GAN loss for the transformer (ablation) | Boundary transformer · Transformer loss ablation (qualitative) | adherence of boundary to source pose | Improved |
| add the cycle loss on top of GAN and shape losses (ablation) | Boundary transformer · Transformer loss ablation (qualitative) | quality of eyes and mouth regions | Improved |
| use ReenactGAN boundary-space transfer instead of CycleGAN pixel-space transfer | CycleGAN · User study, TrueSkill quality | quality score | Improved |
| apply to unseen wild input instead of seen data | ReenactGAN · User study, TrueSkill quality | quality score | Hurt |
| use ReenactGAN instead of Face2Face for expression transfer | Face2Face · Facial action unit response correlation with source | AU response correlation | Improved |
Closest papers by meaning
- HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces (ICCV 2023 · similarity 0.90)
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos (CVPR 2016 · similarity 0.89)
- FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features (CVPR 2024 · similarity 0.89)
- One-Shot Neural Face Reenactment via Finding Directions in GAN’s Latent Space (IJCV 2024 · similarity 0.88)
- VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment (CVPR 2024 · similarity 0.86)
- Enhancing Identity-Deformation Disentanglement in StyleGAN for One-Shot Face Video Re-Enactment (AAAI 2025 · 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.
