Research map / 3D vision / Gaussian splatting
HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
Gent Serifi, Marcel C. Buehler
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 |
|---|---|---|---|
| replace 3D Gaussians with HyperGaussians (n=8) | FlashAvatar · Monocular (19 subjects, 5 datasets) | PSNR: 29.43 -> 29.99 | Improved |
| replace 3D Gaussians with HyperGaussians | FlashAvatar · Monocular (19 subjects, 5 datasets) | LPIPS (x10^-2): 5.107 -> 4.978 | Improved |
| replace 3D Gaussians with HyperGaussians | GaussianHeadAvatar · Multi-view NeRSemble (10 subjects) | PSNR: 24.10 -> 24.38 | Improved |
| replace 3D Gaussians with HyperGaussians | GaussianHeadAvatar · Multi-view NeRSemble (10 subjects) | SSIM (x10^-1): 8.819 -> 8.819 | No clear effect |
| replace 3D Gaussians with HyperGaussians | GaussianHeadAvatar · Multi-view NeRSemble (10 subjects) | LPIPS (x10^-2): 20.273 -> 19.768 | Improved |
| deepen deformation MLP instead of HyperGaussians (ablation) | FlashAvatar · Monocular FlashAvatar ablation | LPIPS: 0.0498 -> 0.0572 | Hurt |
| widen deformation MLP instead of HyperGaussians (ablation) | FlashAvatar · Monocular FlashAvatar ablation | LPIPS: 0.0498 -> 0.0512 | Hurt |
| deepen MLP instead of HyperGaussians (ablation) | FlashAvatar · Monocular FlashAvatar ablation | rendering FPS: 300 -> 158 | Hurt |
| add inverse covariance trick (ablation) | HyperGaussian conditioning · Conditioning n=8 | speed: +150% | Improved |
| add inverse covariance trick (ablation) | HyperGaussian conditioning · Conditioning n=8 | memory (MB): 42 -> 22 | Improved |
| use latent dimension n=1 instead of none (ablation) | HyperGaussians FlashAvatar · Monocular (19 subjects, 5 datasets) | quality | Improved |
| add HyperGaussians to training | GaussianHeadAvatar · Training time | time: +30min (1%) | No clear effect |
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.
- FlashAvatar — FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024) · better on 3 of 3 shared results
- GaussianHeadAvatar — Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024) · better on 2 of 3 shared results
- SplattingAvatar — SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024) · better on 2 of 2 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
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.90)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.90)
- GASP: Gaussian Avatars with Synthetic Priors (CVPR 2025 · similarity 0.90)
- MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks (CVPR 2025 · similarity 0.90)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · 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.
