Research map / 3D vision / Face and shape
High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors
Read the paperCheck 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 |
|---|---|---|---|
| Learn a personalized latent subspace and encoder instead of per-frame GAN inversion | EG3D facial reconstruction · RGB face reconstruction | PSNR: 32.62 -> 34.70 | Helped |
| Use 3DMM coefficients to navigate a personalized latent subspace | EG3D face reenactment · 3DMM-driven face reenactment | PSNR: 31.52 -> 34.38 | Helped |
| Use audio features to navigate a personalized latent subspace | EG3D face reenactment · Audio-driven face reenactment | PSNR: 30.23 -> 32.57 | Helped |
| Add the orthogonal constraint to the basis (ablation) | Personalized latent subspace · RGB face reconstruction | PSNR: 33.36 -> 34.70 | Helped |
| Use 5 rather than 50 orthogonal basis vectors (ablation) | Personalized latent subspace · RGB face reconstruction | PSNR: 34.70 -> 28.64 | Hurt |
| Use 10 rather than 50 orthogonal basis vectors (ablation) | Personalized latent subspace · RGB face reconstruction | PSNR: 34.70 -> 30.83 | Hurt |
| Use 20 rather than 50 orthogonal basis vectors (ablation) | Personalized latent subspace · RGB face reconstruction | PSNR: 34.70 -> 33.98 | Hurt |
Closest papers by meaning
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · similarity 0.90)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.89)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.89)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.88)
- PEGASUS: Personalized Generative 3D Avatars with Composable Attributes (CVPR 2024 · similarity 0.88)
- PERSE: Personalized 3D Generative Avatars from A Single Portrait (CVPR 2025 · similarity 0.87)
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.