Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos
PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model
LAM: Large Avatar Model for One-shot Animatable Gaussian Head
LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow
Gaussian-Informed Continuum for Physical Property Identification and Simulation: Leveraging 3D Gaussian Representation to Advance Physical Property Identification
MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling
Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decomposition
Research Experience
Researcher at Alibaba
Education
Ph.D., Hong Kong University of Science and Technology (HKUST), Advisors: Prof. Qifeng Chen, Prof. Long Quan, Dr. Jian Sun
Background
Research Interests: 3D Computer Vision, AIGC, Embodied AI, and Digital Avatar