Research map / 3D vision / Gaussian splatting
HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting
Zhenglin Zhou, Fan Ma, Hehe Fan, Zongxin Yang, Yi Yang
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 |
|---|---|---|---|
| use HeadStudio instead of text-to-3D baselines for avatar texture | HeadArtist · Static head avatars | CLIP-Score ViT-L/14: 0.272 -> 0.275 | Improved |
| use HeadStudio (3DGS) instead of TADA for rendering | TADA · Dynamic head avatars, Kratos | rendering speed (fps): 3 fps -> 52 fps | Improved |
| add super-dense Gaussian initialization (K=10 versus K=1) | HeadStudio · head avatar generation (qualitative) | avatar fidelity | Improved |
| add FLAME-based control and landmark condition | HeadStudio · head avatar generation (qualitative) | shape consistency | Improved |
| add denoised score distillation | HeadStudio · head avatar generation (qualitative) | texture quality | Improved |
| train with animation (pose and expression sampling) | HeadStudio · head avatar generation (qualitative) | deformation artifacts | Improved |
| add adaptive geometry regularization with mesh-area scale | HeadStudio · head avatar generation (qualitative) | alignment vs representation | Improved |
| use Realistic Vision 5.1 instead of SD2.1 or SD1.5 as diffusion model | HeadStudio · head avatar generation (qualitative) | visual appeal | Improved |
| increase geometry regularization weight too far | HeadStudio · head avatar generation (qualitative) | representation ability | Hurt |
Later papers that compared with this method
1 later accepted paper reports HeadStudio as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors (ICCV 2025 · better on 4 of 4 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
- GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning (CVPR 2024 · similarity 0.90)
- GASP: Gaussian Avatars with Synthetic Priors (CVPR 2025 · similarity 0.90)
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation (ICML 2024 · similarity 0.88)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024 · 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.
