AI Paper Atlas

Research map / Video / Video generation

AudioAvatar: Personalized Audio-driven Whole-body Talking Avatars

Seungeun Lee, SeungJun Moon, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park

CVPR 2026 · Video › Video generation · approach: Talking face generation

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
add audio-particle motion embedding (ablation)AudioAvatar · Test set (30 subjects)SyncC: 7.05 -> 7.20Improved
add patchified alignment strategy (ablation)AudioAvatar · Test set (30 subjects)FVD: 252 -> 240Improved
add hand and face refinement module (ablation)AudioAvatar · Test set (30 subjects)HKC: 0.860 -> 0.897Improved
add hybrid talking-video data synthesis (ablation)AudioAvatar · Test set (30 subjects)SyncC: 6.85 -> 7.20Improved
add video score distillation loss (ablation)AudioAvatar · Test set (30 subjects)FVD: 290 -> 240Improved
add trajectory alignment loss (ablation)AudioAvatar · Test set (30 subjects)SyncD: 6.20 -> 5.42Improved
drive avatar directly from audio instead of audio-to-pose converter with LHM/PERSONAGaussian avatars · Test set (30 subjects)SyncD: 6.80 -> 5.42 (vs PERSONA)Improved
use Gaussian avatar with distilled priors instead of video diffusion modelsAudioAvatar vs HunyuanVideo-Avatar · Test set (30 subjects)FVD: 320 -> 240Improved

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