Research map / 3D vision / Face and shape
SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar
Jun Xiang, Yudong Guo, Boyang Guo, Yancheng Yuan, Juyong Zhang
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 Gaussian avatar dataset (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | PSNR: 23.037 -> 24.949 | Improved |
| add Gaussian avatar dataset (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | MSE (x1e-3): 5.283 -> 3.527 | Improved |
| add input-aware decoder (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | PSNR: 23.114 -> 24.949 | Improved |
| add input-aware decoder (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | MSE (x1e-3): 5.281 -> 3.527 | Improved |
| add Gaussian inverse for color decoding (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | PSNR: 22.733 -> 24.949 | Improved |
| add Gaussian inverse for color decoding (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | MSE (x1e-3): 5.846 -> 3.527 | Improved |
| add semantic guidance in Gaussian inverse (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | PSNR: 24.477 -> 24.949 | Improved |
| add semantic guidance in Gaussian inverse (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | LPIPS: 0.0583 -> 0.0527 | Improved |
| add semantic guidance in Gaussian inverse (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | SSIM: 0.9328 -> 0.9365 | Improved |
| add Gaussian avatar dataset (ablation) | SplatCtrlA · Seamless Interaction ablation (face masked) | SSIM: 0.9326 -> 0.9365 | Improved |
| add facial enhancement module (ablation) | SplatCtrlA · Qualitative face region | face detail quality | Improved |
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.
- GUAVA — GUAVA: Generalizable Upper Body 3D Gaussian Avatar (ICCV 2025) · better on 6 of 6 shared results
- IDOL — IDOL: Inertial Deep Orientation-Estimation and Localization (AAAI 2021) · better on 6 of 6 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
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025 · similarity 0.89)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · similarity 0.89)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.88)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.88)
- Expressive Gaussian Human Avatars from Monocular RGB Video (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.
