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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace plain residual VQ with Pyramid-VQ (multi-scale, large-to-small codebooks) (ablation) | CtrlCoMo · CoHuMo test | FGD: 109.63 -> 23.61 | Improved |
| add CLIP-based layer-wise semantic regularization (ablation) | Pyramid-VQ · CoHuMo test | FGD / R-Precision Top-1: 23.61 -> 22.27 FGD; 0.344 -> 0.373 Top-1 | Improved |
| add CLIP semantic regularization (ablation) | Pyramid-VQ · CoHuMo test | MM-Dist: 1.235 -> 1.257 | Hurt |
| add audio condition (train and inference) (ablation) | CtrlCoMo · CoHuMo test | FGD / MAJE: 24.50 -> 22.27 FGD; 10.282 -> 8.932 MAJE | Improved |
| add text condition (train and inference) (ablation) | CtrlCoMo · CoHuMo test | R-Precision Top-1: 0.198 -> 0.373 | Improved |
| drop audio only at inference (ablation) | CtrlCoMo · CoHuMo test | FGD: 22.27 -> 109.42 | Hurt |
| scale training data from 10k to 200k samples (ablation) | CtrlCoMo · CoHuMo test | FGD: 38.15 -> 22.27 | Improved |
| CtrlCoMo vs TalkSHOW | CtrlCoMo · CoHuMo test | FGD: 22.98 -> 22.27 | Improved |
| CtrlCoMo vs Probtalk | CtrlCoMo · CoHuMo test | R-Precision Top-3: 0.532 -> 0.608 | Improved |
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.
- SemGes — SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning (ICCV 2025) · better on 3 of 3 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
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.91)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.91)
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model (CVPR 2024 · similarity 0.90)
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.89)
- Towards Variable and Coordinated Holistic Co-Speech Motion Generation (CVPR 2024 · similarity 0.89)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.89)
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.
