Research map / 3D vision / Human pose estimation
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
Kangyeol Kim, Sunghyun Park, Jaeseong Lee, Sunghyo Chung, Junsoo Lee, Jaegul Choo
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 AnimeCeleb to VoxCeleb training | PIRenderer with pose mapping · Self-identity (AnimeCeleb) | FID: 134.91 -> 16.07 | Improved |
| add AnimeCeleb to VoxCeleb training | FOMM · Self-identity (AnimeCeleb) | FID: 47.91 -> 45.01 | Improved |
| add AnimeCeleb to VoxCeleb training | FOMM · Self-identity (VoxCeleb) | FID: 16.10 -> 19.60 | Hurt |
| add AnimeCeleb to VoxCeleb training | FOMM · Cross-domain (Vox->Anime) | FID: 122.83 -> 144.88 | Hurt |
| add pose mapping T and AnimeCeleb joint training | PIRenderer · Cross-domain (Vox->Anime) | FID: 95.75 -> 69.80 | Improved |
| add domain-specific warping and editing networks (ablation) | PIRenderer+T · Cross-domain (Vox->Anime) | FID: 69.80 -> 18.78 | Improved |
| add domain-specific warping and editing networks (ablation) | PIRenderer+T · Cross-domain (Anime->Vox) | FID: 61.67 -> 41.04 | Improved |
| add domain-specific warping and editing networks (ablation) | PIRenderer+T · Cross-domain (Vox->Anime) | HAE: 0.195 -> 0.128 | Improved |
| use AnimeCeleb pose vector instead of keypoints | PIRenderer · AnimeCeleb same-identity | FID: 27.84 -> 20.27 | Improved |
| use AnimeCeleb pose vector instead of keypoints | PIRenderer · AnimeCeleb cross-identity | FID: 21.48 -> 16.52 | Improved |
| use pose vector PIRenderer instead of FOMM | AnimeCeleb training · AnimeCeleb cross-identity | FID: 29.94 -> 16.52 | Improved |
| train on iCartoonFace instead of AnimeCeleb | FOMM and PIRenderer · iCartoonFace reenactment | qualitative quality | Hurt |
Closest papers by meaning
- ToonTalker: Cross-Domain Face Reenactment (ICCV 2023 · similarity 0.86)
- PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters (CVPR 2023 · similarity 0.85)
- Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters (CVPR 2025 · similarity 0.84)
- HRAvatar: High-Quality and Relightable Gaussian Head Avatar (CVPR 2025 · similarity 0.83)
- FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video (CVPR 2025 · similarity 0.83)
- GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image (CVPR 2024 · similarity 0.83)
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.
