Our Works

• Wonder3D Single Image to 3D using Cross-Domain Diffusion
• SyncDreamer Generating Multiview-consistent Images from a Single-view Image
• NeuS Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
• SO-SMPL Disentangled Clothed Avatar Generation from Text Descriptions
• SparseNeuS Fast Generalizable Neural Surface Reconstruction from Sparse Views
• Coverage AxisCoverage Axis: Inner Point Selection for 3D Shape Skeletonization
• EMDM Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation
• C·ASE Learning Conditional Adversarial Skill Embeddings for Physics-based Characters
• Gen6DGeneralizable 6DoF Object Pose Estimator
• NeRO Reconstructing Reflective Objects