AI Paper Atlas

Research map / 3D vision / Face and shape

AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation

Hao Li, Ju Dai, Feng Zhou, Kaida Ning, Lei Li, Junjun Pan

ICCV 2025 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 4 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
train on AU-Blendshape data (AUBlendSet) instead of D3DFACS direct AU annotations (ablation)AUBlendNet · AUBlendSet test setMSE_S single-AU (x1e-9): 226.41 -> 4.55Improved
train on AUBlendSet instead of CK+ (ablation)AUBlendNet · AUBlendSet test setMSE_M multi-AU (x1e-9): 2028.14 -> 7.62Improved
predict blendshape bases once then blend, instead of predicting each posture from AU labels (ablation)AUBlendNet · AUBlendSet test setinference time (s): 2.7 -> 0.3Improved
use AUBlendNet's non-autoregressive AdaLN-Zero design rather than Diffusion, VQ-VAE or Transformer generators (ablation)AUBlendNet · AUBlendSetMSE_S single-AU (x1e-9): 5.66 -> 4.55 (vs Diffusion)Improved
add AUBlendNet expression manipulation to speech-driven modelsFaceformer · MEADDiversity (x1e-6): 2.16 -> 2.74Improved
add AUBlendNet expression manipulation to speech-driven modelsFaceformer · MEADLVE (x1e-4): 2.83 -> 3.04Hurt
add AUBlendNet expression manipulation to FaceDiffuserFaceDiffuser · MEADLVE (x1e-4): 1.47 -> 1.76Hurt
add AUBlendNet expression manipulation to speech-driven modelsFaceformer · MEADV-LVE (x1e-5): 2.64 -> 2.64No clear effect
use AUBlendNet-generated data augmentation for AU detection (HMP-PS)HMP-PS · D3DFACSF1 score: 55.04 -> 57.96Improved
use AUBlendNet-generated data augmentation for AU detection (SRERL)SRERL · DISFAF1 score: 55.75 -> 56.32Improved

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