AI and Computer Vision for Construction and the Built Environment

My research focuses on AI-enabled inspection workflows combining synthetic image generation, 3D reconstruction, and spatio-temporal modeling to transform visual data into actionable insights for progress tracking and decision-making.

About Me

I am a Ph.D. student at the University of Illinois Urbana-Champaign, specializing in computer vision, synthetic data generation, and 3D reconstruction for automated construction monitoring.

This summer, I will join Google Cloud as a Software Engineering Intern (PhD). I also work as a Computer Vision Engineer Intern at Reconstruct Inc., where I develop production-level vision pipelines for large-scale 3D reconstruction and object retrieval (e.g., defect detection).

I was awarded the Government Fellowship for Studying Abroad (2024-2026) and have led both academic and industry-backed AI initiatives across the U.S. and Taiwan.

Education

Ph.D., Construction Engineering & Management University of Illinois Urbana-Champaign • 2022–present
M.C.S., Computer Science University of Illinois Urbana-Champaign • 2023–2024

Experience

Incoming Software Engineering Intern (PhD) | Google Cloud Summer 2026
Computer Vision Engineer Intern | Reconstruct Inc. 2023–present • Building robust 3D reconstruction pipelines for commercial deployments.
Project Lead | NTUCE-NCREE AI Research Center 2020–2022 • Leading image-based defect inspection projects for tunnels, bridges, and buildings.

Publication highlights

Self-Evaluation of Single and Multi-Agent LLMs as Assistants in Inspection Reporting Workflows

Shun-Hsiang Hsu, Yoonhwa Jung, Junryu Fu, and 1 more author

In Joint CSCE Construction Specialty & CRC Conference, 2025
Beyond Cracks: Synthetic Image and Geometry Generation for Computer Vision Detection and Severity Assessment of Diverse Concrete Surface Defects

Shun-Hsiang Hsu and Mani Golparvar-Fard

Automation in Construction, 2026

Under review

Website
Defect inspection of indoor components in buildings using deep learning object detection and augmented reality

Shun-Hsiang Hsu, Ho-Tin Hung, Yu-Qi Lin, and 1 more author

Earthquake Engineering and Engineering Vibration, 2023
VisualSiteDiary: A detector-free Vision-Language Transformer model for captioning photologs for daily construction reporting and image retrievals

Yoonhwa Jung, Ikhyun Cho, Shun-Hsiang Hsu, and 1 more author

Automation in Construction, 2024
VL-Con: Vision-Language Dataset for Deep Learning-based Construction Monitoring Applications

Shun-Hsiang Hsu, Junryu Fu, and Mani Golparvar-Fard

In ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, 2024
Requirements for Parametric Design of Physics-Based Synthetic Data Generation for Learning and Inference of Defect Conditions

Shun-Hsiang Hsu and Mani Golparvar-Fard

In Construction Research Congress 2024, 2024