AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Emotion Director: Speech-Preserving Semantic Control of Facial Expressions in "In-the-Wild" Videos

CVPR 2022 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 36 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 NED instead of GANmutMEAD self-translation · MEAD self-translation, avg. (7)FID: 4.3 -> 2.9Helped
Use NED instead of GANmutMEAD user study · MEAD user study, avg.Emotion recognition accuracy: 77% -> 35%Hurt
Use NED instead of GANmutMEAD user study · MEAD user study, avg.Realism ratings (4 or 5): 11% -> 28%Helped
Add detailed shape images as renderer conditioning (ablation)NED face renderer · YouTube Actors renderer self-reenactmentMAPD: 13.27 -> 12.20Helped
Add face alignment (ablation)NED face renderer · YouTube Actors renderer self-reenactmentMAPD: 14.59 -> 12.20Helped
Add meta-renderer pretraining (ablation)NED face renderer · YouTube Actors renderer self-reenactmentMAPD: 12.20 -> 11.66Helped
Add the speech-preserving jaw-opening correlation loss (ablation)NED emotion manipulator · Speech-preserving emotion translationPreservation of mouth movementHelped

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