Research map / 3D vision / 3D generation
FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image
Fei Yin, Mallikarjun B R, Chun-Han Yao, Rafal K. Mantiuk, Varun Jampani
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 warping-based control generation (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | CLIP-I: 0.8151 -> 0.8162 | Improved |
| add warping-based control generation (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | FID: 172.43 -> 166.96 | Improved |
| add cross-view mutual attention (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | ID: 0.4915 -> 0.4984 | Improved |
| add cross-view mutual attention (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | CLIP-I: 0.7886 -> 0.8162 | Improved |
| add both warping and mutual attention (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | CLIP-I: 0.7328 -> 0.8162 | Improved |
| add both warping and mutual attention (ablation) | FaceCraft4D multiview generation · FFHQ multiview ablation | FID: 182.27 -> 166.96 | Improved |
| add COIN training (ablation) | FaceCraft4D 4D optimization · FFHQ animation ablation | FID: 144.95 -> 142.80 | Improved |
| add COIN training (ablation) | FaceCraft4D 4D optimization · FFHQ animation ablation | CLIP-I: 0.7688 -> 0.7729 | Improved |
| add COIN training (ablation) | FaceCraft4D 4D optimization · FFHQ animation ablation | ID: 0.4952 -> 0.5010 | Improved |
| add video prior (ablation) | FaceCraft4D · FFHQ | expression quality (qualitative) | Improved |
| replace PanoHead with FaceCraft4D | PanoHead · static 3D head generation | FID: 195.28 -> 174.36 | Improved |
| replace PanoHead with FaceCraft4D | PanoHead · static 3D head generation | CLIP-I: 0.8233 -> 0.8053 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PanoHead — PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg (CVPR 2023) · better on 6 of 7 shared results
- Portrait-4D — Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025 · similarity 0.91)
- Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion (CVPR 2025 · similarity 0.89)
- Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 2024 · similarity 0.88)
- AvatarArtist: Open-Domain 4D Avatarization (CVPR 2025 · similarity 0.88)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024 · similarity 0.88)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.88)
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.
