1

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

3DV, 2025. Best Paper Award. We propose Object Images, a 2D representation that enables realistic 3D shape generation with UV maps using image-based models like Diffusion Transformers.

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

CVPR, 2022 A transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds.

RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud

ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2019 A deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape.

Transductive Zero-Shot Learning with Visual Structure Constraint

NIPS 2019