This month our work Fast-Asset: A Real Time Scan-To-3D Point Cloud BIM-Ready Asset Generation Method for Small MEP Elements is published in the proceedings of the 2026 European Conference on Computing in Construction (EC³), co-authored with Ibon Eskudero, Diego Sagasti and Sarah Noyé.
The problem
Scan-to-BIM methods based on laser scanning or photogrammetry require specialized hardware and offline processing. This makes it hard to update small assets frequently while maintaining digital twins.
The proposal
Fast-Asset is a real-time, on-site framework that combines mixed-reality capture, learning-based detection and incremental 3D reconstruction. In a single walkthrough it generates pre-segmented, BIM-ready point clouds of small MEP elements, with immediate visual feedback to validate and recapture in situ.
Results
The capture-to-model time is 3 to 10 times shorter than with laser scanning or photogrammetry, with comparable surface roughness and little background contamination.
Keywords: 3D point cloud segmentation, BIM, object detection, real-time 3D capture, scan-to-BIM.
You can read the paper through its DOI: 10.35490/ec3.2026.204. The full entry, with the BibTeX citation, is on the Publications page.
