Research map / 3D vision / Face and shape
UIKA: Fast Universal Head Avatar from Pose-Free Images
Zijian Wu, Boyao Zhou, Liangxiao Hu, Hongyu Liu, Yuan Sun, Xuan Wang, Xun Cao, Yujun Shen, Hao Zhu
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 |
|---|---|---|---|
| train with synthetic multi-view head dataset (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | PSNR: 21.86 -> 22.61 | Improved |
| add UV attention branch (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | PSNR: 22.21 -> 22.61 | Improved |
| add aggregated UV color and confidence map with self-adaptive fusion (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | PSNR: 22.39 -> 22.61 | Improved |
| add UV attention branch (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | LPIPS: 0.091 -> 0.082 | Improved |
| add UV attention branch (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | AKD: 3.086 -> 3.037 | No clear effect |
| add synthetic dataset (ablation) | UIKA · Monocular self reenactment (NeRSemble-v2) | AED: 0.060 -> 0.055 | No clear effect |
| increase number of input images from 1 to 16 | UIKA · VFHQ and NeRSemble-v2 qualitative | 3D consistency and details | Improved |
| use UIKA with UV-guided correspondence instead of GPAvatar/InvertAvatar multi-view aggregation | multi-view avatar reconstruction · Multi-view self reenactment (NeRSemble-v2) | PSNR: 17.11 -> 22.50 vs GPAvatar | Improved |
| use UIKA instead of GAGAvatar in monocular cross reenactment | monocular avatar reconstruction · Monocular cross reenactment (VFHQ + NeRSemble-v2) | CSIM: 0.678 -> 0.649 | Hurt |
| use UIKA instead of GAGAvatar in monocular self reenactment | monocular avatar reconstruction · Monocular self reenactment (VFHQ + NeRSemble-v2) | PSNR: 20.34 -> 21.69 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GPAvatar — GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025) · better on 3 of 3 shared results
- Portrait4D-v2 — Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 2024) · better on 3 of 3 shared results
- DiffusionRig — DiffusionRig: Learning Personalized Priors for Facial Appearance Editing (CVPR 2023) · better on 1 of 1 shared result
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
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.89)
- Gaussian Eigen Models for Human Heads (CVPR 2025 · similarity 0.89)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024 · similarity 0.88)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.88)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.88)
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · 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.
