Research map / 3D vision / Face and shape
HHAvatar: Gaussian Head Avatar with Dynamic Hairs
Zhanfeng Liao, Yuelang Xu, Zhe Li, Qijing Li, Boyao Zhou, Ruifeng Bai, Di Xu, Hongwen Zhang, 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 super resolution network (ablation) | HHAvatar · Self reenactment (2K) | LPIPS (2K): 0.202 -> 0.098 | Improved |
| add super resolution network (ablation) | HHAvatar · Self reenactment (2K) | FID (2K): 45.50 -> 18.50 | Improved |
| add super resolution network (ablation) | HHAvatar · Self reenactment | PSNR: 27.82 -> 27.70 | Mixed |
| use geometry-guided initialization instead of FLAME initialization (ablation) | HHAvatar · Self reenactment | LPIPS: 0.123 -> 0.108 | Improved |
| use geometry-guided initialization instead of FLAME initialization (ablation) | HHAvatar · Self reenactment | PSNR: 28.73 -> 28.94 | Improved |
| use fully learned deformation instead of mesh LBS deformation (ablation) | HHAvatar · Self reenactment | LPIPS: 0.116 -> 0.108 | Improved |
| use fully learned deformation instead of mesh LBS deformation (ablation) | HHAvatar · Self reenactment | PSNR: 28.83 -> 28.94 | Improved |
| add separate dynamic hair module (ablation) | HHAvatar · Self reenactment with hair | PSNR: 26.23 -> 27.02 | Improved |
| add separate dynamic hair module (ablation) | HHAvatar · Self reenactment with hair | SSIM: 0.825 -> 0.876 | Improved |
| add occlusion perception module (ablation) | HHAvatar · Self reenactment with hair | LPIPS: 0.116 -> 0.108 | Improved |
| add occlusion perception module (ablation) | HHAvatar · Self reenactment with hair | PSNR: 26.83 -> 27.02 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GaussianAvatars — GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (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
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.94)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.91)
- DGH: Dynamic Gaussian Hair (NeurIPS 2025 · similarity 0.91)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.90)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.90)
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024 · similarity 0.90)
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.
