My research focuses on deep learning, computer vision and 3D. I have developed novel deep learning architectures for 3D data (point clouds, volumetric grids and multi-view images) that have wide applications in 3D object classification, object part segmentation, semantic scene parsing, scene flow estimation and 3D reconstruction. Those deep architectures have been well adopted by both academic and industrial groups across the world. I have also invented several state-of-the-art methods for 3D object recognition, which reinforce current and future applications in augmented reality and robotics. My more recent interests are on scalable and data-efficient perception and data-driven simulation.