AI Paper Atlas

Research map / 3D vision / Face and shape

Feed-forward Gaussian Registration for Head Avatar Creation and Editing

Malte Prinzler, Paulo Gotardo, Siyu Tang, Timo Bolkart

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 0 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
use registration-guided attention instead of dense attention (ablation)MATCH · Ava-256 (300k iterations)LPIPS: 0.221 -> 0.187Improved
add pretrained Sapiens features (ablation)MATCH · Ava-256 (300k iterations)LPIPS: 0.202 -> 0.187Improved
add skip connections for color and location (ablation)MATCH · Ava-256 (300k iterations)LPIPS: 0.192 -> 0.187Improved
use adapted TEMPEH global stage instead of original TEMPEH for coarse mesh (ablation)MATCH · Ava-256 (300k iterations)LPIPS: 0.190 -> 0.187Improved
increase UV texture resolution from 256 to 1024 (ablation)MATCH · Ava-256 (300k iterations)LPIPS: 0.194 (256) -> 0.190 (512) -> 0.187Improved
smaller k of image tokens to attend to in registration-guided attention (ablation)MATCH · Ava-256reconstruction qualityImproved
joint training on Ava-256 and NeRSemble without NeRSemble geometry supervision (ablation)MATCH · NeRSembleLPIPS: 0.168 (NeRSemble only) -> 0.152Improved
train on Ava-256 only and test on unseen NeRSemble (ablation)MATCH · NeRSembleLPIPS: FaceLift 0.200 vs Ava-256 only 0.182Improved
build GEM avatars from MATCH-predicted GaussiansGEM · Ava-256 subject-specific avatarsreconstruction time: 45.3h -> 4.6hImproved
build GEM avatars from MATCH-predicted GaussiansGEM · Ava-256 cross-reenactmentEmoL1: 9.866 -> 9.837No clear effect
use MATCH geometry instead of TEMPEH in mouth and eye regionsMATCH · Ava-256 geometry (eyes)P2S (mm): Mouth P2S 0.69 -> 0.72; Eyes P2S 0.62 -> 0.61Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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