AI Paper Atlas

Research map / 3D vision / Gaussian splatting

HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars

Gent Serifi, Marcel C. Buehler

CVPR 2026 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace 3D Gaussians with HyperGaussians (n=8)FlashAvatar · Monocular (19 subjects, 5 datasets)PSNR: 29.43 -> 29.99Improved
replace 3D Gaussians with HyperGaussiansFlashAvatar · Monocular (19 subjects, 5 datasets)LPIPS (x10^-2): 5.107 -> 4.978Improved
replace 3D Gaussians with HyperGaussiansGaussianHeadAvatar · Multi-view NeRSemble (10 subjects)PSNR: 24.10 -> 24.38Improved
replace 3D Gaussians with HyperGaussiansGaussianHeadAvatar · Multi-view NeRSemble (10 subjects)SSIM (x10^-1): 8.819 -> 8.819No clear effect
replace 3D Gaussians with HyperGaussiansGaussianHeadAvatar · Multi-view NeRSemble (10 subjects)LPIPS (x10^-2): 20.273 -> 19.768Improved
deepen deformation MLP instead of HyperGaussians (ablation)FlashAvatar · Monocular FlashAvatar ablationLPIPS: 0.0498 -> 0.0572Hurt
widen deformation MLP instead of HyperGaussians (ablation)FlashAvatar · Monocular FlashAvatar ablationLPIPS: 0.0498 -> 0.0512Hurt
deepen MLP instead of HyperGaussians (ablation)FlashAvatar · Monocular FlashAvatar ablationrendering FPS: 300 -> 158Hurt
add inverse covariance trick (ablation)HyperGaussian conditioning · Conditioning n=8speed: +150%Improved
add inverse covariance trick (ablation)HyperGaussian conditioning · Conditioning n=8memory (MB): 42 -> 22Improved
use latent dimension n=1 instead of none (ablation)HyperGaussians FlashAvatar · Monocular (19 subjects, 5 datasets)qualityImproved
add HyperGaussians to trainingGaussianHeadAvatar · Training timetime: +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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy