💻(he)
PhD Student
I am currently a Ph.D. candidate at the Ai4City-Lab, Urban Governance and Design Thrust, Society Hub, The Hong Kong University of Science and Technology (Guangzhou), under the supervision of Prof. Wufan Zhao and Prof. Yuan Liu. Prior to this, I obtained my Master’s degree from the School of Geospatial Engineering and Science, Sun Yat-sen University, where I was advised by Prof. Wuming Zhang and Prof. Yiping Chen.
My research focuses on 3D visual perception, intelligent interpretation and processing of point cloud data, and multi-modal urban foundation models. I am particularly interested in bridging geometric understanding with semantic reasoning in large-scale urban environments, with an emphasis on open-vocabulary learning, training-free paradigms, and cross-modal fusion between 2D and 3D data.
My goal is to develop scalable, interpretable, and generalizable AI systems for urban analysis, enabling applications such as digital twin construction, urban scene understanding, and intelligent infrastructure management.
PhD in UGOD (URBAN GOVERNANCE AND DESIGN)
2024-09
--
The Hong Kong University of Science and Technology (Guangzhou).
M.S in Remote Sensing and Geoinformation Engineering
2021-09
2024-06
SUN YAT-SEN UNIVERSITY
B.E in Surveying and Mapping Engineering
2017-09
2021-06
Shandong University Of Science and Technology
My research explores how cities can be understood through multimodal intelligence. I focus on integrating heterogeneous data—particularly 3D point clouds, imagery, and text—to build unified representations of complex urban environments. My current research interests include:
3D Urban Perception: Combining geometric cues with visual and linguistic data for scalable, city-level scene understanding.
Urban Foundation Models: Leveraging vision-language models to develop training-efficient, open-vocabulary paradigms for spatial reasoning.
Intelligent City Systems: Moving beyond isolated tasks to build unified frameworks for large-scale infrastructure analysis.
Feel free to reach out for collaboration! 😃
This paper proposes PVCFormer, a cross-attention architecture combining point and voxel representations with CosFormer for efficient large-scale outdoor point cloud semantic …
This paper presents Chat3D, a method for applying large language models to urban ecological construction by combining the results of 3D point cloud semantic segmentation. The …