AI Paper Atlas

Research map / 3D vision / Face and shape

Instant Expressive Gaussian Head Avatars at Over 100 FPS

Kaiwen Jiang, Xueting Li, Seonwook Park, Ravi Ramamoorthi, Shalini De Mello, Koki Nagano

ECCV 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
deform Gaussians in feature space instead of spatial attributes (ablation)Instant Gaussian avatar · Self-reenactment ablationAED: 0.634 -> 0.507Improved
feature-space instead of spatial deformation, speed cost (ablation)Instant Gaussian avatar · Self-reenactment ablationFPS: 141.61 -> 132.87Hurt
use lightweight X-NeMo motion encoder instead of DINO-v2 (ablation)Instant Gaussian avatar · Self-reenactment ablationFPS: 22.47 -> 132.87Improved
use X-NeMo motion encoder instead of DINO-v2 (ablation)Instant Gaussian avatar · Self-reenactment ablationAED: 0.597 -> 0.507Improved
train on synthetic diffusion-generated expressions instead of real dataset (ablation)Instant Gaussian avatar · Self-reenactment ablationAED: 0.543 -> 0.507Improved
train on synthetic diffusion-generated expressions instead of real dataset (ablation)Instant Gaussian avatar · Self-reenactment ablationPSNR/MEt3R: PSNR 23.10 -> 23.18; MEt3R 0.073 -> 0.073No clear effect
retrain Portrait4D-v2 and GAGAvatar on the synthetic datasetPortrait4D-v2 · Cross-reenactmentAED: 0.886 -> 0.972Hurt
use Ours instead of X-NeMo (2D diffusion teacher)Instant Gaussian avatar · Cross-reenactmentAED: 0.805 -> 0.731Improved
use Ours instead of InvertAvatar for image fidelityInstant Gaussian avatar · Self-reenactmentPSNR: 23.43 -> 22.34Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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