Research map / 3D vision / Face and shape
AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
Taewoong Kang, Hyojin Jang, Sohyun Jeong, Seunggi Moon, Gihwi Kim, Hoon Jin Jung, 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 GAGAvatar head reenactment augmentation (ablation) | AHS · SHHQ ablation | CLIP-I (Head): 0.7575 -> 0.9122 | Improved |
| add GAGAvatar head reenactment augmentation (ablation) | AHS · SHHQ ablation | Head orientation error: 17.34 -> 8.72 | Improved |
| add GAGAvatar head reenactment augmentation (ablation) | AHS · SHHQ ablation | ID sim: 0.8492 -> 0.6237 | Hurt |
| add mask augmentation (ablation) | AHS · SHHQ ablation | ID sim: 0.4098 -> 0.6237 | Improved |
| add mask augmentation (ablation) | AHS · SHHQ ablation | FID: 8.99 -> 8.98 | Improved |
| add mask augmentation (ablation) | AHS · SHHQ ablation | Expression error: 5.6719 -> 6.4273 | Hurt |
| add head encoder (ablation) | AHS · SHHQ ablation | CLIP-I (Head): 0.8912 -> 0.9122 | Improved |
| add head encoder (ablation) | AHS · SHHQ ablation | Expression error: 8.8247 -> 6.4273 | Improved |
| add face and head encoders (ablation) | AHS · SHHQ ablation | FID: 9.66 -> 8.98 | Improved |
| add decoupled cross-attention (ablation) | AHS · SHHQ ablation | CLIP-I (Head): 0.8050 -> 0.9122 | Improved |
| add decoupled cross-attention (ablation) | AHS · SHHQ ablation | ID sim: 0.5124 -> 0.6237 | Improved |
| add decoupled cross-attention (ablation) | AHS · SHHQ ablation | Expression error: 8.7458 -> 6.4273 | Improved |
Closest papers by meaning
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · similarity 0.88)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.87)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.87)
- Zero-Shot Head Swapping in Real-World Scenarios (CVPR 2025 · similarity 0.86)
- Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025 · similarity 0.86)
- GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image (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.
