Unsupervised Learning–Based Scan-to-BIM for Modular Construction

This project aims to create a simple and reliable method to turn 3D scan data from modular construction factories into BIM models using unsupervised learning. By focusing on basic geometric patterns in point-cloud data, it reduces the need for manual labeling and helps build a semi-automated Scan-to-BIM workflow. The interns will develop a full pipeline that includes preprocessing, geometric feature extraction, clustering, and BIM integration. The project will benefit both participating institutions: Concordia University will gain new algorithms, datasets, and tools that support its research in digital construction, while Gyeongsang National University will strengthen its skills in AI-based point-cloud processing and expand international research collaboration.

Faculty Supervisor:

Sang Hyeok Han

Student:

Partner:

Gyeongsang National University

Discipline:

Engineering

Sector:

Artificial Intelligence; Manufacturing and Construction; Advanced Manufacturing

University:

Concordia University

Program: