This paper proposes an assistive system for architects that converts a large-scale point cloud into a standardized digital representation of a building for Building Information Modeling (BIM) applications.
The process is known as Scan-to-BIM, which requires many hours of manual work even for a single building floor by a professional architect. Given its challenging nature, the paper focuses on helping architects on the Scan-to-BIM process, instead of replacing them.
Concretely, we propose an assistive Scan-to-BIM system that takes the raw sensor data and edit history (including the current BIM model), then auto-regressively predicts a sequence of model editing operations as APIs of a professional BIM software (i.e., Autodesk Revit).
The paper also presents the first building-scale Scan2BIM dataset that contains a sequence of model editing operations as the APIs of Autodesk Revit. The dataset contains 89 hours of Scan2BIM modeling processes by professional architects over 16 scenes, spanning over 35,000 square meter.
We report our system's reconstruction quality with standard metrics, and we introduce a novel metric that measures how natural the order of reconstructed operations is. A simple modification to the reconstruction module helps improve performance, and our method is far superior to two other baselines in the order metric.
We created a custom Revit plugin that records modeling history of architects. Use the slider to interpolate between start and end of the modeling session.
Our assistive tool learns from collected modeling history, and offers the most natural suggestions. See the video below for a demo of our tool and its functionality in Revit.
@article{weilian2023ascan2bim,
author = {Song, Weilian and Luo, Jieliang and Zhao, Dale and Fu, Yan and Cheng, Chin-Yi and Furukawa, Yasutaka},
title = {A-Scan2BIM: Assistive Scan to Building Information Modeling},
journal = {BMVC},
year = {2023},
}This research is partially supported by NSERC Discovery Grants with Accelerator Supplements and the DND/NSERC Discovery Grant Supplement, NSERC Alliance Grants, and the John R. Evans Leaders Fund (JELF). We are also grateful to the CV4AEC CVPR workshop for providing the point clouds.