AI Paper Atlas

Research map / Video / Video generation

CtrlCoMo: Controllable Co-Speech Motion Generation with Gesture–Action Disentanglement

Xinghan Wang, Ming Zhou, Yanbo Zheng, Youjiang Xu, Yuan Zhang, Mingyuan Gao, Nan Zhuang, Yadong Mu

ECCV 2026 · Video › Video generation · approach: Talking face generation · 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
replace plain residual VQ with Pyramid-VQ (multi-scale, large-to-small codebooks) (ablation)CtrlCoMo · CoHuMo testFGD: 109.63 -> 23.61Improved
add CLIP-based layer-wise semantic regularization (ablation)Pyramid-VQ · CoHuMo testFGD / R-Precision Top-1: 23.61 -> 22.27 FGD; 0.344 -> 0.373 Top-1Improved
add CLIP semantic regularization (ablation)Pyramid-VQ · CoHuMo testMM-Dist: 1.235 -> 1.257Hurt
add audio condition (train and inference) (ablation)CtrlCoMo · CoHuMo testFGD / MAJE: 24.50 -> 22.27 FGD; 10.282 -> 8.932 MAJEImproved
add text condition (train and inference) (ablation)CtrlCoMo · CoHuMo testR-Precision Top-1: 0.198 -> 0.373Improved
drop audio only at inference (ablation)CtrlCoMo · CoHuMo testFGD: 22.27 -> 109.42Hurt
scale training data from 10k to 200k samples (ablation)CtrlCoMo · CoHuMo testFGD: 38.15 -> 22.27Improved
CtrlCoMo vs TalkSHOWCtrlCoMo · CoHuMo testFGD: 22.98 -> 22.27Improved
CtrlCoMo vs ProbtalkCtrlCoMo · CoHuMo testR-Precision Top-3: 0.532 -> 0.608Improved

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