Published multiple papers such as 'WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving', 'VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences', etc. Involved in projects like MonoSE(3)-Diffusion, GigaSLAM, AD-GS, etc.
Research Experience
Was a research scientist in the Department of Electrical and Computer Engineering at New York University Abu Dhabi and New York University Tandon School of Engineering.
Education
Ph.D. from the Department of Computing, Hong Kong Polytechnic University, under the supervision of Prof. Lei Zhang.
Background
Currently a Professor at the School of Intelligence Science and Technology, Nanjing University. Research focuses on 3D computer vision and its applications in autonomous driving and robotic manipulation, intersecting with machine learning, computer vision, computer graphics, and robotics. Specific research interests include 3D low-level imaging, 2D/3D scene understanding, 3D object navigation and planning, 2D/3D object and scene generation, 6D pose estimation, and grasping. Also interested in vision foundation models and generative models.
Miscellany
Looking for self-motivated and talented undergraduate, master, and Ph.D. students to join his team, and recruiting postdocs to join the team.