Corpus ID: 235458276

IFCNet: A Benchmark Dataset for IFC Entity Classification

@article{Emunds2021IFCNetAB,
  title={IFCNet: A Benchmark Dataset for IFC Entity Classification},
  author={Christoph Emunds and N. Pauen and Veronika Richter and J. Frisch and C. V. Treeck},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.09712}
}
Enhancing interoperability and information exchange between domain-specific software products for BIM is an important aspect in the Architecture, Engineering, Construction and Operations industry. Recent research started investigating methods from the areas of machine and deep learning for semantic enrichment of BIM models. However, training and evaluation of these machine learning algorithms requires sufficiently large and comprehensive datasets. This work presents IFCNet, a dataset of single… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 24 REFERENCES
A geometric deep learning approach for checking element-to-entity mappings in infrastructure building information models
Data interoperability between domain-specific applications is a key prerequisite for building information modeling (BIM) to solidify its position as a central medium for collaboration andExpand
Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations
TLDR
This work proposes a procedure for establishing a knowledge base that associates objects with their features and relationships, and a matching algorithm based on a similarity measurement between the knowledge base and facts, for use in future semantic enrichment systems. Expand
Comparing machine learning and rule-based inferencing for semantic enrichment of BIM models
TLDR
This work illustrates the use of machine learning algorithms for semantic enrichment of BIM models, and compares it to rule-inferencing, through application to the problem of classification of room types in residential apartments, showing that machine learning is directly applicable to the space classification problem. Expand
Semantic Enrichment for Building Information Modeling
TLDR
This work proposes an innovative approach for supplementing an IFC exchange file with semantically useful concepts inferred from the explicit and implicit information contained in the building model, and demonstrates semantic enrichment with precast concrete building models. Expand
Recognizing and Classifying Unknown Object in BIM Using 2D CNN
TLDR
Train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs and expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of B IM. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
Interoperability analysis of IFC-based data exchange between heterogeneous BIM software
TLDR
A suggested method for improving the existing bidirectional data sharing and exchange is presented: BIM software tools export models using IFC format, and these IFC models are imported into a common IFC-based BIM platform for data interoperability. Expand
ImageNet: A large-scale hierarchical image database
TLDR
A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets. Expand
Reduction, simplification, translation and interpretation in the exchange of model data
TLDR
This paper provides an overview of issues that arise when data transformation is necessary for “downstream” applica-tions that use data authored by model based CAD and/or other interoperable software. Expand
Automatic Geometry Generation from Point Clouds for BIM
TLDR
An automated workflow for the generation of BIM data from 3D point clouds is presented and quality indicators for reconstructed geometry elements and a framework in which to assess the quality of the reconstructed geometry against a reference are presented. Expand
...
1
2
3
...