Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion
Xingqun Qi, Yatian Wang, Hengyuan Zhang, Jiahao Pan, Wei Xue, Shanghang Zhang, Wenhan Luo, Qifeng Liu, Yike Guo
Abstract
I didn't see that one coming. SPEAKER B (on the right): No, you didn't see it coming. Co 3 Gesture Figure 1: Diverse exemplary clips sampled by our method from our newly collected GES-Inter dataset. The vital frames are visualized to demonstrate the concurrent upper body dynamics of two speakers generated by our Co 3 Gesture framework displaying temporal coherent interaction with each other, respectively. Best view on screen.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Lune answers from
the full paper · 4 top-tier papers that cite it · related work
Free to start. No credit card required.
Cited by top-tier papers4
- ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual BodyJuze Zhang, Changan Chen, Xin Chen, Heng Yu et al.CVPR 2026 · 7 citations
- Freedance: Towards Harmonic Free-Number Group Dance Generation Via a Unified FrameworkYiwen Zhao, Yang Wang, Liting Wen, Hengyuan Zhang et al.ICCV 2025 · 7 citations
- DanceEditor: Towards Iterative Editable Music-Driven Dance Generation with Open-Vocabulary DescriptionsHengyuan Zhang, Zhe Li, Xingqun Qi, Mengze Li et al.ICCV 2025 · 3 citations
- ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance GenerationJingzhong Lin, Xinru Li, Yuanyuan Qi, Bohao Zhang et al.ICLR 2026 · 1 citation
Builds on29
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 9,451 citations
- Improved Denoising Diffusion Probabilistic ModelsAlexander Quinn Nichol, Prafulla DhariwalICML 2021 · 5,234 citations
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human FeedbackYann Dubois, Chen Xuechen Li, Rohan Taori, Tianyi Zhang et al.NeurIPS 2023 · 948 citations
Related papers
- Understanding Co-Speech Gestures in-the-WildSindhu B. Hegde, K. R. Prajwal, Taein Kwon, Andrew ZissermanICCV 2025 · 4 citations
- LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture GenerationYihao Zhi, Xiaodong Cun, Xuelin Chen, Xi Shen et al.ICCV 2023 · 48 citations
- Audio-Driven Co-Speech Gesture Video GenerationXian Liu, Qianyi Wu, Hang Zhou, Yuanqi Du et al.NeurIPS 2022 · 77 citations
- From Audio to Photoreal Embodiment: Synthesizing Humans in ConversationsEvonne Ng, Javier Romero, Timur M. Bagautdinov, Shaojie Bai et al.CVPR 2024 · 37 citations
- TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion InterpolationHaiyang Liu, Xingchao Yang, Tomoya Akiyama, Yuantian Huang et al.ICLR 2025
