Research map / 3D vision / Face and shape
HADES: Human Avatar with Dynamic Explicit Hair Strands
Zhanfeng Liao, Hanzhang Tu, Cheng Peng, Hongwen Zhang, Boyao Zhou, Yebin Liu
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 separate dynamic hair modeling (ablation) | HADES · Self reenactment (ablation) | PSNR: 23.23 -> 24.19 | Improved |
| add separate dynamic hair modeling (ablation) | HADES · Self reenactment (ablation) | SSIM: 0.845 -> 0.886 | Improved |
| add separate dynamic hair modeling (ablation) | HADES · Self reenactment (ablation) | LPIPS: 0.123 -> 0.105 | Improved |
| add color mapping matrix (ablation) | HADES · Self reenactment (ablation) | PSNR: 23.54 -> 24.19 | Improved |
| add color mapping matrix (ablation) | HADES · Self reenactment (ablation) | SSIM: 0.875 -> 0.886 | Improved |
| add color mapping matrix (ablation) | HADES · Self reenactment (ablation) | LPIPS: 0.117 -> 0.105 | Improved |
| add 2D Mip filter (ablation) | HADES · Zoom-out/zoom-in rendering (qualitative) | visual quality | Improved |
| add multi-scale (long-focus) training data (ablation) | HADES · Zoom-out rendering (qualitative) | visual quality | Improved |
| train AnimatableGaussians on both short and long focus data instead of short only | AnimatableGaussians · Self reenactment (dynamic hair dataset) | PSNR: 22.27 -> 22.19 | No clear effect |
Closest papers by meaning
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.88)
- LUCAS: Layered Universal Codec Avatars (CVPR 2025 · similarity 0.88)
- SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing (CVPR 2025 · similarity 0.88)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.87)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.85)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.85)
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.
