AI Paper Atlas

Research map / 3D vision / Face and shape

PhysHead: Simulation-Ready Gaussian Head Avatars

Berna Kabadayi, Vanessa Sklyarova, Wojciech Zielonka, Justus Thies, Gerard Pons-Moll

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 1 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
compare PhysHead to GaussianHaircut on static appearancePhysHead · Ava-256 hair reconstruction vs GaussianHaircutPSNR: 30.55 -> 30.28No clear effect
compare PhysHead to GaussianHaircutPhysHead · Ava-256 hair reconstruction vs GaussianHaircutSSIM: 0.915 -> 0.946Improved
compare PhysHead to GaussianHaircutPhysHead · Ava-256 hair reconstruction vs GaussianHaircutLPIPS: 0.071 -> 0.061Improved
add strand-level color consistency loss (ablation)PhysHead · hidden hair strands (qualitative)hair color plausibilityImproved
use two-layer (head + hair) representation instead of single layer (ablation)PhysHead · hair animation (qualitative)artifactsImproved
use VLM-based bald proxy with Poisson blending instead of SDS (HairCUP)PhysHead · head layer (qualitative)artifacts / skin tone generalizationImproved

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