Research map / 3D vision / Face and shape
ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative Adaptation
Kim Youwang, Lee Hyoseok, Park Subin, Gerard Pons-Moll, Tae-Hyun Oh
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 single-step rendering-guided diffusion enhancer instead of CAP4D full denoising | ELITE · Generated supervision images | CSIM: 0.5037 -> 0.9725 | Improved |
| use single-step rendering-guided diffusion enhancer instead of CAP4D full denoising | ELITE · Generated supervision images | seconds per image: 18 -> 0.3 | Improved |
| train MGPM on more identities (up to 334) (ablation) | ELITE · INSTA | avatar quality | Improved |
| use more supervision frames at test time (ablation) | ELITE · INSTA | fidelity and synthesis time | Mixed |
| add stage 1 test-time adaptation with real frames after MGPM initialization (ablation) | ELITE · INSTA | ID alignment | Improved |
| add stage 2 test-time generative adaptation (ablation) | ELITE · INSTA | visual detail and generalization | Improved |
| ELITE versus SplattingAvatar on SSIM | ELITE · INSTA self re-enactment | SSIM: 0.8831 -> 0.8771 | No clear effect |
| ELITE versus CAP4D on synthesis time | ELITE · INSTA self re-enactment | synthesis time: 400 mins -> 20 mins | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- CAP4D — CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025) · better on 7 of 7 shared results
- FlashAvatar — FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024) · better on 4 of 5 shared results
- SplattingAvatar — SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024) · better on 3 of 5 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
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · similarity 0.91)
- GASP: Gaussian Avatars with Synthetic Priors (CVPR 2025 · similarity 0.91)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.91)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.90)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024 · similarity 0.89)
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.89)
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.
