Research map / 3D vision / Face and shape
Fine-Grained 3D Gaussian Head Avatars Modeling from Static Captures via Joint Reconstruction and Registration
Yuan Sun, Xuan Wang, Cong Wang, WeiLi Zhang, Yanbo Fan, Yu Guo, Fei Wang
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 joint registration to bind prior-free Gaussians (ablation) | Base GaussianAvatars on static captures · NeRSemble ID 074 high-res | PSNR: 24.73 -> 25.13 | Improved |
| add position regularization from registration (ablation) | Base + registration · NeRSemble ID 074 high-res | PSNR: 25.13 -> 25.48 | Improved |
| add scale regularization (ablation) | Base + registration + position reg. · NeRSemble ID 074 high-res | PSNR: 25.48 -> 25.53 | Improved |
| add teeth enhancement (ablation) | full pipeline · NeRSemble ID 074 high-res | PSNR: 25.53 -> 25.54 | No clear effect |
| joint registration and reconstruction vs prior-based HeadGAP | Gaussian head avatar from 15 images · NeRSemble self-reenactment low res | PSNR: 24.51 -> 25.77 | Improved |
| joint registration and reconstruction vs prior-based HeadGAP | Gaussian head avatar from 15 images · NeRSemble self-reenactment high res | LPIPS: 0.199 -> 0.172 | Improved |
| static images with our method vs GaussianAvatars trained on 15 videos | Ours · NeRSemble self-reenactment low res | LPIPS: 0.135 (videos) -> 0.111 (ours); SSIM 0.907 vs 0.889 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GPAvatar — GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025) · better on 1 of 1 shared result
- 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
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.93)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.91)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024 · similarity 0.91)
- Gaussian Eigen Models for Human Heads (CVPR 2025 · similarity 0.91)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.91)
- Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping (ICLR 2025 · similarity 0.91)
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.
