BIMStruct3D: A Fully Automated Hybrid Learning Scan-to-BIM Pipeline with Integrated Topology Refinement

TL;DR

This paper introduces BIMStruct3D, an automated pipeline that combines learning and topology refinement to generate accurate, IFC-compliant BIM models from 3D scans, with a new evaluation metric and a new dataset.

Contribution

It presents a hybrid learning and topology-aware approach for Scan-to-BIM, introduces vIoU for model evaluation, and releases a new high-resolution dataset for benchmarking.

Findings

Significant improvements over RANSAC-based methods.

Robustness and scalability demonstrated on multiple datasets.

Effective integration of semantic segmentation with geometric reconstruction.

Abstract

Automatic generation of Building Information Models (BIM) from building scans is a key challenge in architecture and construction. We present a modular pipeline for generating IFC-compliant BIM from 3D point clouds. The hybrid approach combines learning-based semantic segmentation with topology-aware geometric reconstruction to model structural elements accurately. We propose vIoU, adapting voxel-based overlap evaluation to Scan-to-BIM by enabling holistic, instance-matching-free comparison of reconstructed and ground-truth models. We release the German Hospital dataset (DeKH), including high-resolution point clouds, ground truth BIMs, and semantic annotations. Experiments on DeKH and CV4AEC datasets show significant improvements over a RANSAC-based baseline, demonstrating robustness and scalability.