Research map / 3D vision / Face and shape
One-shot Implicit Animatable Avatars with Model-based Priors
Yangyi Huang, Hongwei Yi, Weiyang Liu, Haofan Wang, Boxi Wu, Wenxiao Wang, Binbin Lin, Debing Zhang, Deng Cai
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 |
|---|---|---|---|
| model avatar with implicit HumanNeRF instead of explicit SMPL mesh texture (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 17.20 -> 22.61 | Improved |
| add SMPL mesh initialization (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 19.01 -> 22.61 | Improved |
| add CLIP-based semantic loss (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 21.46 -> 22.61 | Improved |
| add soft geometry constraint (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 21.68 -> 22.61 | Improved |
| use hard silhouette constraint instead of soft constraint (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 22.61 -> 20.58 | Hurt |
| add hybrid sampling strategy (body-part and rotation aware) (ablation) | ELICIT · ZJU-MoCap ablation | PSNR: 21.46 -> 22.61 | Improved |
| train with diverse motion sequences instead of input pose only (ablation) | ELICIT · ZJU-MoCap ablation | LPIPS: 0.1516 -> 0.1115 | Improved |
| combine text guidance with image guidance in CLIP loss (ablation) | ELICIT · qualitative (back-side garment) | visual quality | Improved |
| use text guidance only in CLIP loss (ablation) | ELICIT · qualitative | identity preservation | Hurt |
| replace per-subject baselines (NB, NHP) with ELICIT on single-image input | ZJU-MoCap novel view synthesis · ZJU-MoCap S_test | LPIPS: 0.175 -> 0.118 (vs NHP) | Improved |
Closest papers by meaning
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.91)
- Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models (NeurIPS 2024 · similarity 0.91)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.90)
- Relightable and Animatable Neural Avatars from Videos (AAAI 2024 · similarity 0.90)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024 · similarity 0.90)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.89)
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.
