3D models over the centuries: From old floor plans to 3D representation

Riedinger, Christophe; Jordan, Michel; Tabia, Hedi

doi:10.1109/ic3d.2014.7032583

Cited by 6 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ahmed et al [27] distinguished walls from other components by dividing the lines into three levels: thick, medium, and thin. Riedinger et al [28] took the binarization process for the floor plan first, then the main walls and the dividing walls were detected and located based on the thickness of dark sketches, which represent wall seams. Grimenez et al [9] identified building components like walls, doors, windows, and rooms from floor plans using the method of pattern recognition.…”

Section: Traditional Methods For Components Recognitionmentioning

confidence: 99%

A Deep Learning-Based Method to Detect Components from Scanned Structural Drawings for Reconstructing 3D Models

2020

View full text Add to dashboard Cite

Among various building information model (BIM) reconstruction methods for existing building, image-based method can identify building components from scanned as-built drawings and has won great attention due to its lower cost, less professional operators and better reconstruction performance. However, this kind of method will cost a great deal of time to design and extract features. Moreover, the manually extracted features have poor robustness and contain less non-geometric information. In order to solve this problem, this paper proposes a deep learning-based method to detect building components from scanned 2D drawings. Taking structural drawings as an example, in this article, 1500 images of structural drawings were firstly collected and preprocessed to guarantee the quality of data. After that, the neural network model—You Only Look Once (YOLO) was trained, verified and tested. In addition, a series of metrics were utilized to evaluate the performance of recognition. The results of test experiments show that the components in structural drawings (e.g., grid reference, column and beam) can be successfully detected, while the average detection accuracy of the whole image is over 80% and the average detection time for each image is 0.71 s. The experimental results demonstrate that the proposed method is robust and timesaving, which provides a good basis for the reconstruction of BIM from 2D drawings.

show abstract

Section: Traditional Methods For Components Recognitionmentioning

confidence: 99%

A Deep Learning-Based Method to Detect Components from Scanned Structural Drawings for Reconstructing 3D Models

2020

View full text Add to dashboard Cite

show abstract

“…Some researchers interpret the information from floor plans along with the information from other types of documentation to make up for this missing information. In [15], Riedinger et al use elevations to map textures onto wall polygons through the triangulation of the elevation image and fix height information of the resulting 3D model. Lewis et al [7] read the information of a reflected ceiling plan to define the spatial regions corresponding to room ceilings using a partitioning algorithm.…”

Section: Input Documentationmentioning

confidence: 99%

“…Downsampling involves downscaling the size of an image to reduce dimensionality and the amount of information present in the image. For example, in Riedinger et al [15], the input image is downscaled by sampling it on a r × r grid of pixels and keeping the darkest pixel of the sample. There are different implementations of downscaling [15,16,22]; however, these methods inherently result in some form of information loss.…”

Section: Raster Drawingsmentioning

confidence: 99%

“…For example, in Riedinger et al [15], the input image is downscaled by sampling it on a r × r grid of pixels and keeping the darkest pixel of the sample. There are different implementations of downscaling [15,16,22]; however, these methods inherently result in some form of information loss. As an alternative, tiling/merging preserves all the original information, partitioning the input image into tiles, processing and analysing each tile individually and merging them back together after processing.…”

Section: Raster Drawingsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Reconstruction of 3D Models from 2D Drawings: A State-of-the-Art Review

Feist,

Jacques de Sousa,

Sanhudo

et al. 2024

Eng

View full text Add to dashboard Cite

Among the methods of 3D reconstruction, the automatic generation of 3D models from building documentation is one of the most accessible and inexpensive. For 30 years, researchers have proposed multiple methods to automatically generate 3D models from 2D drawings. This study compiles this research and discusses the different methods used to generate 3D models from 2D drawings. It offers a critical review of these methods, focusing on the coverage and completeness of the reconstruction process. This review allows us to identify the research gaps in the literature, and opportunities for improvement are identified for future research.

show abstract

“…Regarding the second type, most approaches are based on automatic or semiautomatic analysis of architectural floor plans [29] including topological information [30,31]. The input can be scanned plans [32][33][34] as well as mechanical drawings [35,36]. The conversion from 2D information to BIM models often requires recognition of 2D data and 3D model reconstruction processes [37,38].…”

Section: Related Workmentioning

confidence: 99%

ABGS: A System for the Automatic Generation of Building Information Models from Two-Dimensional CAD Drawings

Byun

Sohn

2020

Sustainability

View full text Add to dashboard Cite

Building Information Modeling (BIM) refers to 3D-based digital modeling of buildings and infrastructure for efficient design, construction, and management. Governments have recognized and encouraged BIM as a primary method for enabling advanced construction technologies. However, BIM is not universally employed in industries, and most designers still use Computer-Aided Design (CAD) drawings, which have been used for several decades. This is because the initial costs for setting up a BIM work environment and the maintenance costs involved in using BIM software are substantially high. With this motivation, we propose a novel software system that automatically generates BIM models from two-dimensional (2D) CAD drawings. This is highly significant because only 2D CAD drawings are available for most of the existing buildings. Notably, such buildings can benefit from the BIM technology using our low-cost conversion system. One of the common problems in existing methods is possible loss of information that may occur during the process of conversion from CAD to BIM because they mainly focus on creating 3D geometric models for BIM by using only floor plans. The proposed method has an advantage of generating BIM that contains property information in addition to the 3D models by analyzing floor plans and other member lists in the input design drawings together. Experimental results show that our method can quickly and accurately generate BIM models from 2D CAD drawings.

show abstract

3D models over the centuries: From old floor plans to 3D representation

Cited by 6 publications

References 13 publications

A Deep Learning-Based Method to Detect Components from Scanned Structural Drawings for Reconstructing 3D Models

A Deep Learning-Based Method to Detect Components from Scanned Structural Drawings for Reconstructing 3D Models

Automatic Reconstruction of 3D Models from 2D Drawings: A State-of-the-Art Review

ABGS: A System for the Automatic Generation of Building Information Models from Two-Dimensional CAD Drawings

Contact Info

Product

Resources

About