Research map / 3D vision / Face and shape
Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
Xianfang Zeng, Yusu Pan, Mengmeng Wang, Jiangning Zhang, Yong Liu
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 |
|---|---|---|---|
| Use DAE-GAN without finetuning instead of tuned baselines | DAE-GAN · VoxCeleb1 test set | SSIM | Improved |
| Use DAE-GAN without finetuning instead of tuned baselines | DAE-GAN · VoxCeleb1 test set | FID | Improved |
| Replace a single-frame face embedder with a multi-frame face embedder (ablation) | DAE-GAN vanilla variation · VoxCeleb1 | SSIM | Improved |
| Replace a single-frame face embedder with a multi-frame face embedder (ablation) | DAE-GAN vanilla variation · VoxCeleb1 | FID | Improved |
| Add a multi-scale pose embedder (ablation) | DAE-GAN with multi-frame face embedder · VoxCeleb1 | SSIM | Improved |
| Add a multi-scale pose embedder (ablation) | DAE-GAN with multi-frame face embedder · VoxCeleb1 | FID | Improved |
| Add the generator and discriminator (ablation) | DAE-GAN with multi-frame and multi-scale deforming autoencoders · VoxCeleb1 | FID | Improved |
| Add the smoothness loss (ablation) | DAE-GAN deforming autoencoders · VoxCeleb1 | visual quality | Improved |
| Add the feature matching loss (ablation) | DAE-GAN generator · VoxCeleb1 | performance | Improved |
Closest papers by meaning
- HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces (ICCV 2023 · similarity 0.91)
- One-Shot Neural Face Reenactment via Finding Directions in GAN’s Latent Space (IJCV 2024 · similarity 0.89)
- DPE: Disentanglement of Pose and Expression for General Video Portrait Editing (CVPR 2023 · similarity 0.88)
- Enhancing Identity-Deformation Disentanglement in StyleGAN for One-Shot Face Video Re-Enactment (AAAI 2025 · similarity 0.87)
- VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment (CVPR 2024 · similarity 0.87)
- FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features (CVPR 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.
