Published multiple papers, including 'Towards In-the-wild 3D Plane Reconstruction from a Single Image' (CVPR 2025), 'Computer-Aided Layout Generation for Building Design: A Review' (CVMJ 2025), 'MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction' (IROS 2024), 'NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolation' (ICRA 2024), 'End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement' (ECCV 2022), and 'PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo' (CVPR 2022). Some of the papers received oral presentations or highlight showcases.
Research Experience
Worked as a machine learning engineer at Tiktok; research projects involved 3D plane reconstruction, scene layout generation, etc.
Education
Received a PhD in Information Sciences and Technology from Penn State University in 2024, advised by Dr. Sharon X. Huang. Completed a bachelor's degree at Beihang University in China.
Background
Currently a machine learning engineer at Tiktok in San Jose. Research interests include 3D vision and generative AI, specifically structured 3D reconstruction, scene understanding, and their downstream applications, as well as generalizable 3D reconstruction across various environments.