Automatic generation of LEGO building instructions from multiple photographic images of real objects

Takuya Kozaki, Hiroshi Tedenuma, Takashi Maekawa

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We introduce a system to reconstruct large scale LEGO models from multiple two dimensional images of objects taken from different views. We employ a unit voxel with an edge length ratio of 5:5:6 for the shape from silhouette method that reconstructs an octree voxel-based three dimensional model with color information from images. We then convert the resulting voxel model with color information into a LEGO sculpture. In order to minimize the number of LEGO bricks, we use a stochastic global optimization method, simulated annealing, to hollow the model as much as possible but keep its strength for portability. Several real complex LEGO models are provided to demonstrate the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)13-22
Number of pages10
JournalCAD Computer Aided Design
Volume70
DOIs
Publication statusPublished - 2016 Jan 1
Externally publishedYes

Fingerprint

Color
Global optimization
Brick
Simulated annealing

Keywords

  • 3D reconstruction
  • LEGO
  • Shape from silhouette
  • Simulated annealing

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Industrial and Manufacturing Engineering

Cite this

Automatic generation of LEGO building instructions from multiple photographic images of real objects. / Kozaki, Takuya; Tedenuma, Hiroshi; Maekawa, Takashi.

In: CAD Computer Aided Design, Vol. 70, 01.01.2016, p. 13-22.

Research output: Contribution to journalArticle

Kozaki, Takuya ; Tedenuma, Hiroshi ; Maekawa, Takashi. / Automatic generation of LEGO building instructions from multiple photographic images of real objects. In: CAD Computer Aided Design. 2016 ; Vol. 70. pp. 13-22.
@article{a28aa1afdf064eb28981b88212845d64,
title = "Automatic generation of LEGO building instructions from multiple photographic images of real objects",
abstract = "We introduce a system to reconstruct large scale LEGO models from multiple two dimensional images of objects taken from different views. We employ a unit voxel with an edge length ratio of 5:5:6 for the shape from silhouette method that reconstructs an octree voxel-based three dimensional model with color information from images. We then convert the resulting voxel model with color information into a LEGO sculpture. In order to minimize the number of LEGO bricks, we use a stochastic global optimization method, simulated annealing, to hollow the model as much as possible but keep its strength for portability. Several real complex LEGO models are provided to demonstrate the effectiveness of the proposed method.",
keywords = "3D reconstruction, LEGO, Shape from silhouette, Simulated annealing",
author = "Takuya Kozaki and Hiroshi Tedenuma and Takashi Maekawa",
year = "2016",
month = "1",
day = "1",
doi = "10.1016/j.cad.2015.06.020",
language = "English",
volume = "70",
pages = "13--22",
journal = "CAD Computer Aided Design",
issn = "0010-4485",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Automatic generation of LEGO building instructions from multiple photographic images of real objects

AU - Kozaki, Takuya

AU - Tedenuma, Hiroshi

AU - Maekawa, Takashi

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We introduce a system to reconstruct large scale LEGO models from multiple two dimensional images of objects taken from different views. We employ a unit voxel with an edge length ratio of 5:5:6 for the shape from silhouette method that reconstructs an octree voxel-based three dimensional model with color information from images. We then convert the resulting voxel model with color information into a LEGO sculpture. In order to minimize the number of LEGO bricks, we use a stochastic global optimization method, simulated annealing, to hollow the model as much as possible but keep its strength for portability. Several real complex LEGO models are provided to demonstrate the effectiveness of the proposed method.

AB - We introduce a system to reconstruct large scale LEGO models from multiple two dimensional images of objects taken from different views. We employ a unit voxel with an edge length ratio of 5:5:6 for the shape from silhouette method that reconstructs an octree voxel-based three dimensional model with color information from images. We then convert the resulting voxel model with color information into a LEGO sculpture. In order to minimize the number of LEGO bricks, we use a stochastic global optimization method, simulated annealing, to hollow the model as much as possible but keep its strength for portability. Several real complex LEGO models are provided to demonstrate the effectiveness of the proposed method.

KW - 3D reconstruction

KW - LEGO

KW - Shape from silhouette

KW - Simulated annealing

UR - http://www.scopus.com/inward/record.url?scp=84942506447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942506447&partnerID=8YFLogxK

U2 - 10.1016/j.cad.2015.06.020

DO - 10.1016/j.cad.2015.06.020

M3 - Article

AN - SCOPUS:84942506447

VL - 70

SP - 13

EP - 22

JO - CAD Computer Aided Design

JF - CAD Computer Aided Design

SN - 0010-4485

ER -