FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation Cheng Peng*, Zhuo Su*, Liao Wang*, Chen Guo, Zhaohu Li, Chengjiang Long, Zheng Lv, Jingxiang Sun, Chenyangguang Zhang, Yebin Liu (*Equal Contribution)
arXiv 2025
[Project][PDF][BibTeX]
We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring camera poses or expression labels.
Publications
Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling Cheng Peng*, Jingxiang Sun*, Yushuo Chen, Zhaoqi Su, Zhuo Su, Yebin Liu (*Equal Contribution)
International Conference on 3D Vision, 3DV 2026
[Project][Arxiv][BibTeX]
We present the Parametric Gaussian Human Model (PGHM), a generalizable and efficient framework that integrates human priors into 3DGS for fast and high-fidelity avatar reconstruction from monocular videos.
HADES: Human Avatar with Dynamic Explicit Hair Strands
Zhanfeng Liao, Hanzhang Tu, Cheng Peng, Hongwen Zhang, Boyao Zhou, and Yebin Liu
International Conference on Computer Vision, ICCV 2025
[Project][Arxiv][BibTeX]
We introduce HADES, the first framework to seamlessly integrate dynamic hair into human avatars.
DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
Jingxiang Sun, Cheng Peng, Ruizhi Shao, Yuan-Chen Guo, Xiaochen Zhao, Yangguang Li, Yanpei Cao, Bo Zhang, Yebin Liu
IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI 2025
[Project][Arxiv][BibTeX]
We present DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets in 10 minutes.
Control4D: Efficient 4D Portrait Editing with Text
Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, Yebin Liu
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2024
[Project][Arxiv][Code][BibTeX]
We propose Control4D, an approach to high-fidelity and spatiotemporal-consistent 4D portrait editing with only text instructions.