Tsinghua University
Master Student in Department of Electronic Engineering, advised by Shengjin Wang.

Huazhong University of Science and Technology
B.S. in School of Optical and Electronic Information.

ByteDance
Computer Vision Research & Engineer Intern. Stereo Matching / Optical Flow Estimation.

Alibaba
3D Vision Engineer. 3D layout generation / 3D model generation.

Hybrid Physical Metric For 6-DoF Grasp Pose Detection We proposed the hybrid physical metric to generate confidence labels for 6-dof grasp poses, and designed a transformer-based point cloud learning network, FGC_graspnet, to predict 6-dof grasp poses.

VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes The VL-Grasp is a interactive grasp policy combined with visual grounding and 6-dof grasp pose detection tasks. The robot can adapt to various observation views and more diverse indoor scenes to grasp the target according to a human's language command by applying the VL-Grasp. Meanwhile, we build a new visual grounding dataset specially designed for the robot interaction grasp task, called RoboRefIt.