We are the 3D Digital Human team from the Tongyi Lab at Alibaba, dedicated to researching and developing intelligent generation and interaction systems for 3D digital humans.
- OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar. (CVPR 2026) Project,Code
- GlobalDiff: Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints. (AAAI 2026) Paper,Code
- CartoonAlive: Towards Expressive Live2D Modeling from Single Portraits. Paper, Code
- EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation.(ACMMM 2025) Paper
- SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis.(ICCV 2025) Paper
- Textoon: Generating Vivid 2D Cartoon Characters from Text Descriptions. Paper, Code
- Make-A-Character 2: Animatable 3D Character Generation From a Single Image. Paper
- Make-A-Character: High Quality Text-to-3D Character Generation within Minutes. Paper
- HRN: A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images.(CVPR 2023) Paper