AI Paper Atlas

Research map / 3D vision / Gaussian splatting

EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization

Haolan Xu, Keli Cheng, Lei Wang, Ning Bi, Xiaoming Liu

CVPR 2026 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human 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
remove Semantic Emotion Guidance (emotion distillation from DeepFace) (ablation)EmoTaG · Emotional set (5s)LMD: 3.067 -> 2.456Improved
add score distillation (L_Score) to the gate branch (ablation)EmoTaG · Emotional set (5s)Sync-C: 5.874 -> 6.147Improved
add KL emotion-distribution distillation (L_KL) to the residual branch (ablation)EmoTaG · Emotional set (5s)PSNR: 29.36 -> 29.95Improved
add gate branch to the motion decoder (ablation)EmoTaG · Emotional set (5s)Sync-C: 5.004 -> 6.147Improved
add residual branch to the motion decoder (ablation)EmoTaG · Emotional set (5s)LMD: 3.572 -> 2.456Improved
add AdaIN-based identity modulation (ablation)EmoTaG · Emotional set (5s)LMD: 4.021 -> 2.456Improved
use EmoTaG instead of InsTaG on the emotional test setfew-shot talking head · Emotional set (5s)LMD: 3.428 -> 2.456Improved
use EmoTaG instead of Real3DPortrait on lip syncfew-shot talking head · Emotional set (5s)Sync-C: 6.583 -> 6.147Hurt
use EmoTaG instead of InsTaG on OOD audiofew-shot talking head · Cross-identity audioSync-C: 4.722 -> 5.814Improved
use EmoTaG instead of InsTaG on rendering speedfew-shot talking head · Neutral set efficiencyFPS: 82.5 -> 76.4Hurt
use EmoTaG instead of TalkingGaussian on training timetalking head · Efficiencytraining time: 27 min -> 11 minHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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