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

2026-04-27

AI Summary

This study addresses the challenges of insufficient semantic understanding and low geometric reconstruction accuracy in the automatic generation of IFC-compliant BIM models from 3D building point clouds. The authors propose a modular hybrid learning pipeline that integrates deep learning–driven semantic segmentation with topology-aware geometric reconstruction to enable fully automated, end-to-end BIM generation. A novel voxel-based intersection-over-union (vIoU) evaluation metric—requiring no instance matching—is introduced alongside an embedded topological optimization mechanism, significantly enhancing model consistency and geometric fidelity. Evaluated on the DeKH and CV4AEC datasets, the method substantially outperforms RANSAC-based baselines, demonstrating robustness, scalability, and high-fidelity reconstruction capabilities.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Scan-to-BIM
• Building Information Modeling
• 3D point clouds
• structural elements
• IFC-compliant

Innovation

• Scan-to-BIM
• hybrid learning
• topology-aware reconstruction
• vIoU
• IFC-compliant BIM