Edition-oriented 3D model rebuilt from photography: Giving affordance to 3D capture

Joaquim Silvestre, François Guéna, Yasushi Ikeda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The topic of this paper is about a technique to turn pictures into an intuitively modifiable 3D model. The research employs an analytical method using algorithms to conceptualise and digitalise architectural spaces in order to highlight parametric shapes. Usually, from one group of digital photos, photogrammetry techniques produce a 3D-model mesh through a high-density 3D point cloud. This discordance between our intuitive partitioning of the mesh and its bare polygonal structure makes it interact poorly compared to the affordance of shape and component in our daily experience. Through a capture device, a visualisation of architecture in a digital data form is produced. They are processed by computer vision algorithms and machine learning systems in order to be refined into a parametric model. Parametric elements can be described as a compound of formulas and parameters. By keeping the formula and changing the parameters, these elements can be easily modified in a range of likenesses. After being detected during scans, these shapes can be adapted to fit the intention of the designer during the design phase.

Original languageEnglish
Title of host publicationCAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing
PublisherThe Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Pages445-454
Number of pages10
ISBN (Electronic)9789881902672
Publication statusPublished - 2016
Event21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016 - Melbourne, Australia
Duration: 2016 Mar 302016 Apr 2

Other

Other21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016
CountryAustralia
CityMelbourne
Period16/3/3016/4/2

Fingerprint

Photography
Learning systems
Photogrammetry
Computer vision
Visualization

Keywords

  • 3d model
  • Convolutional neural network
  • Design tool
  • Photogrammetry

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Building and Construction

Cite this

Silvestre, J., Guéna, F., & Ikeda, Y. (2016). Edition-oriented 3D model rebuilt from photography: Giving affordance to 3D capture. In CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing (pp. 445-454). The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA).

Edition-oriented 3D model rebuilt from photography : Giving affordance to 3D capture. / Silvestre, Joaquim; Guéna, François; Ikeda, Yasushi.

CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2016. p. 445-454.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Silvestre, J, Guéna, F & Ikeda, Y 2016, Edition-oriented 3D model rebuilt from photography: Giving affordance to 3D capture. in CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), pp. 445-454, 21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016, Melbourne, Australia, 16/3/30.
Silvestre J, Guéna F, Ikeda Y. Edition-oriented 3D model rebuilt from photography: Giving affordance to 3D capture. In CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). 2016. p. 445-454
Silvestre, Joaquim ; Guéna, François ; Ikeda, Yasushi. / Edition-oriented 3D model rebuilt from photography : Giving affordance to 3D capture. CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2016. pp. 445-454
@inproceedings{0164b2244b104a63b7cbbd1b1c3fa27b,
title = "Edition-oriented 3D model rebuilt from photography: Giving affordance to 3D capture",
abstract = "The topic of this paper is about a technique to turn pictures into an intuitively modifiable 3D model. The research employs an analytical method using algorithms to conceptualise and digitalise architectural spaces in order to highlight parametric shapes. Usually, from one group of digital photos, photogrammetry techniques produce a 3D-model mesh through a high-density 3D point cloud. This discordance between our intuitive partitioning of the mesh and its bare polygonal structure makes it interact poorly compared to the affordance of shape and component in our daily experience. Through a capture device, a visualisation of architecture in a digital data form is produced. They are processed by computer vision algorithms and machine learning systems in order to be refined into a parametric model. Parametric elements can be described as a compound of formulas and parameters. By keeping the formula and changing the parameters, these elements can be easily modified in a range of likenesses. After being detected during scans, these shapes can be adapted to fit the intention of the designer during the design phase.",
keywords = "3d model, Convolutional neural network, Design tool, Photogrammetry",
author = "Joaquim Silvestre and Fran{\cc}ois Gu{\'e}na and Yasushi Ikeda",
year = "2016",
language = "English",
pages = "445--454",
booktitle = "CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing",
publisher = "The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)",

}

TY - GEN

T1 - Edition-oriented 3D model rebuilt from photography

T2 - Giving affordance to 3D capture

AU - Silvestre, Joaquim

AU - Guéna, François

AU - Ikeda, Yasushi

PY - 2016

Y1 - 2016

N2 - The topic of this paper is about a technique to turn pictures into an intuitively modifiable 3D model. The research employs an analytical method using algorithms to conceptualise and digitalise architectural spaces in order to highlight parametric shapes. Usually, from one group of digital photos, photogrammetry techniques produce a 3D-model mesh through a high-density 3D point cloud. This discordance between our intuitive partitioning of the mesh and its bare polygonal structure makes it interact poorly compared to the affordance of shape and component in our daily experience. Through a capture device, a visualisation of architecture in a digital data form is produced. They are processed by computer vision algorithms and machine learning systems in order to be refined into a parametric model. Parametric elements can be described as a compound of formulas and parameters. By keeping the formula and changing the parameters, these elements can be easily modified in a range of likenesses. After being detected during scans, these shapes can be adapted to fit the intention of the designer during the design phase.

AB - The topic of this paper is about a technique to turn pictures into an intuitively modifiable 3D model. The research employs an analytical method using algorithms to conceptualise and digitalise architectural spaces in order to highlight parametric shapes. Usually, from one group of digital photos, photogrammetry techniques produce a 3D-model mesh through a high-density 3D point cloud. This discordance between our intuitive partitioning of the mesh and its bare polygonal structure makes it interact poorly compared to the affordance of shape and component in our daily experience. Through a capture device, a visualisation of architecture in a digital data form is produced. They are processed by computer vision algorithms and machine learning systems in order to be refined into a parametric model. Parametric elements can be described as a compound of formulas and parameters. By keeping the formula and changing the parameters, these elements can be easily modified in a range of likenesses. After being detected during scans, these shapes can be adapted to fit the intention of the designer during the design phase.

KW - 3d model

KW - Convolutional neural network

KW - Design tool

KW - Photogrammetry

UR - http://www.scopus.com/inward/record.url?scp=84973541091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973541091&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84973541091

SP - 445

EP - 454

BT - CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing

PB - The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)

ER -