Publications

2026

1. ACM MM

   

   ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction

   Zhuoqiang Cai, Yujie Sun, Chaoyue Niu, Hongyun Yu, Zhiwen Chen, Chengfei Lv, and Fan Wu

   ACM MM · 2026 First Author

   A structured anchor–residual formulation that separates speech-constrained articulation from one-to-many listener reactions under dual-stream audio-only input.

   Project page →

   In Proceedings of the 34th ACM International Conference on Multimedia, Nov 2026

   Abstract DOI BibTeX Paper

   ECHO models dyadic 3D facial motion from dual-stream conversational audio by separating stable speech-related articulation from diverse listener reactions through a deterministic anchor and stochastic residual.

   @inproceedings{cai2026echo,
     title = {ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction},
     author = {Cai, Zhuoqiang and Sun, Yujie and Niu, Chaoyue and Yu, Hongyun and Chen, Zhiwen and Lv, Chengfei and Wu, Fan},
     booktitle = {Proceedings of the 34th ACM International Conference on Multimedia},
     year = {2026},
     month = nov,
     address = {Rio de Janeiro, Brazil},
     doi = {10.1145/3767308.3834964},
   }

2. CVPR

   

   FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures

   Yujie Sun, Zhuoqiang Cai, Chaoyue Niu, Jianchuan Chen, Zhiwen Chen, Chengfei Lv, and Fan Wu

   CVPR · 2026 Co-author

   A fast few-shot 3D Gaussian avatar framework with composable face and hair representations, supporting real-time animation and editing.

   Project page →

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

   Abstract arXiv BibTeX

   FHAvatar reconstructs composable face-and-hair 3D Gaussian head avatars from only a few casual captures, enabling fast personalization, real-time animation, hairstyle transfer, and stylized editing.

   @inproceedings{sun2026fhavatar,
     title = {FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures},
     author = {Sun, Yujie and Cai, Zhuoqiang and Niu, Chaoyue and Chen, Jianchuan and Chen, Zhiwen and Lv, Chengfei and Wu, Fan},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     year = {2026},
   }