Dr. Kyle Gao

Postdoctoral Fellow (Department of Systems Design Engineering)
kyle

Download CV (PDF)

y56gao@uwaterloo.ca

Office: EV1-345

Research Interests

My PhD thesis research focused on leveraging interdisciplinary techniques from computer vision, computer graphics, and geographic information systems (GIS) to transform aerial and satellite images into detailed 3D representations of urban landscapes. I also work on cloud mapping platform data integration, and Large Language Model-based data analytics for urban digital twin systems. 

I also perform more general remote sensing based 2D and 3D computer vision research on the analysis of 2D images including object detection, classification, and segmentation, as well as 3D point cloud object detection, classification, and segmentation. Sometimes, 2D, 3D, and natural language modalities are combined to solve remote-sensing and GIS problems.

Education

  • Doctor of Philosophy (PhD), Systems Design Engineering, University of À¶Ý®ÊÓƵ 2021-2025
  • Master of Science (MSc), Accelerator Physics program, University of Victoria, 2017-2020
  • Honours Bachelors degree in Mathematics (Hon. Math), Mathematical Physics Co-op program, University of À¶Ý®ÊÓƵ, 2011-2016

Publications

  • Gao, Kyle, et al. "NeRF: Neural radiance field in 3d vision, a comprehensive review." arXiv preprint arXiv:2210.00379.
  • Gao, Kyle, et al. "Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery." IEEE Transactions on Geoscience and Remote Sensing (2025).
  • Gao, Kyle, et al. "Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires." arXiv preprint arXiv:2503.00566 (2025).
  • Gao, Kyle, et al. "Digital Twin Buildings: 3D Modeling, GIS Integration, and Visual Descriptions Using Gaussian Splatting, ChatGPT/Deepseek, and Google Maps Platforms." arXiv preprint arXiv:2502.05769 (2025).
  • Gao, Kyle, et al. "Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting." arXiv preprint arXiv:2501.00625 (2024).
  • Gao, Kyle, et al. "Optimizing and evaluating swin transformer for aircraft classification: Analysis and generalizability of the mtarsi dataset." IEEE Access 10 (2022): 134427-134439.