A flexible scene representation for 3D reconstruction using an RGB-D camera

Diego Thomas, Akihiro Sugimoto

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

18 Citations (Scopus)

Abstract

Updating a global 3D model with live RGB-D measurements has proven to be successful for 3D reconstruction of indoor scenes. Recently, a Truncated Signed Distance Function (TSDF) volumetric model and a fusion algorithm have been introduced (KinectFusion), showing significant advantages such as computational speed and accuracy of the reconstructed scene. This algorithm, however, is expensive in memory when constructing and updating the global model. As a consequence, the method is not well scalable to large scenes. We propose a new flexible 3D scene representation using a set of planes that is cheap in memory use and, nevertheless, achieves accurate reconstruction of indoor scenes from RGB-D image sequences. Projecting the scene onto different planes reduces significantly the size of the scene representation and thus it allows us to generate a global textured 3D model with lower memory requirement while keeping accuracy and easiness to update with live RGB-D measurements. Experimental results demonstrate that our proposed flexible 3D scene representation achieves accurate reconstruction, while keeping the scalability for large indoor scenes.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2800-2807
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - Jan 1 2013
Externally publishedYes
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: Dec 1 2013Dec 8 2013

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CountryAustralia
CitySydney, NSW
Period12/1/1312/8/13

Fingerprint

Cameras
Data storage equipment
Scalability
Fusion reactions

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Thomas, D., & Sugimoto, A. (2013). A flexible scene representation for 3D reconstruction using an RGB-D camera. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 2800-2807). [6751459] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.348

A flexible scene representation for 3D reconstruction using an RGB-D camera. / Thomas, Diego; Sugimoto, Akihiro.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 2800-2807 6751459 (Proceedings of the IEEE International Conference on Computer Vision).

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

Thomas, D & Sugimoto, A 2013, A flexible scene representation for 3D reconstruction using an RGB-D camera. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751459, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 2800-2807, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 12/1/13. https://doi.org/10.1109/ICCV.2013.348
Thomas D, Sugimoto A. A flexible scene representation for 3D reconstruction using an RGB-D camera. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 2800-2807. 6751459. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.348
Thomas, Diego ; Sugimoto, Akihiro. / A flexible scene representation for 3D reconstruction using an RGB-D camera. Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. pp. 2800-2807 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{d6673b9dfd6a42ff96716988eb876a54,
title = "A flexible scene representation for 3D reconstruction using an RGB-D camera",
abstract = "Updating a global 3D model with live RGB-D measurements has proven to be successful for 3D reconstruction of indoor scenes. Recently, a Truncated Signed Distance Function (TSDF) volumetric model and a fusion algorithm have been introduced (KinectFusion), showing significant advantages such as computational speed and accuracy of the reconstructed scene. This algorithm, however, is expensive in memory when constructing and updating the global model. As a consequence, the method is not well scalable to large scenes. We propose a new flexible 3D scene representation using a set of planes that is cheap in memory use and, nevertheless, achieves accurate reconstruction of indoor scenes from RGB-D image sequences. Projecting the scene onto different planes reduces significantly the size of the scene representation and thus it allows us to generate a global textured 3D model with lower memory requirement while keeping accuracy and easiness to update with live RGB-D measurements. Experimental results demonstrate that our proposed flexible 3D scene representation achieves accurate reconstruction, while keeping the scalability for large indoor scenes.",
author = "Diego Thomas and Akihiro Sugimoto",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCV.2013.348",
language = "English",
isbn = "9781479928392",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2800--2807",
booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

TY - GEN

T1 - A flexible scene representation for 3D reconstruction using an RGB-D camera

AU - Thomas, Diego

AU - Sugimoto, Akihiro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Updating a global 3D model with live RGB-D measurements has proven to be successful for 3D reconstruction of indoor scenes. Recently, a Truncated Signed Distance Function (TSDF) volumetric model and a fusion algorithm have been introduced (KinectFusion), showing significant advantages such as computational speed and accuracy of the reconstructed scene. This algorithm, however, is expensive in memory when constructing and updating the global model. As a consequence, the method is not well scalable to large scenes. We propose a new flexible 3D scene representation using a set of planes that is cheap in memory use and, nevertheless, achieves accurate reconstruction of indoor scenes from RGB-D image sequences. Projecting the scene onto different planes reduces significantly the size of the scene representation and thus it allows us to generate a global textured 3D model with lower memory requirement while keeping accuracy and easiness to update with live RGB-D measurements. Experimental results demonstrate that our proposed flexible 3D scene representation achieves accurate reconstruction, while keeping the scalability for large indoor scenes.

AB - Updating a global 3D model with live RGB-D measurements has proven to be successful for 3D reconstruction of indoor scenes. Recently, a Truncated Signed Distance Function (TSDF) volumetric model and a fusion algorithm have been introduced (KinectFusion), showing significant advantages such as computational speed and accuracy of the reconstructed scene. This algorithm, however, is expensive in memory when constructing and updating the global model. As a consequence, the method is not well scalable to large scenes. We propose a new flexible 3D scene representation using a set of planes that is cheap in memory use and, nevertheless, achieves accurate reconstruction of indoor scenes from RGB-D image sequences. Projecting the scene onto different planes reduces significantly the size of the scene representation and thus it allows us to generate a global textured 3D model with lower memory requirement while keeping accuracy and easiness to update with live RGB-D measurements. Experimental results demonstrate that our proposed flexible 3D scene representation achieves accurate reconstruction, while keeping the scalability for large indoor scenes.

UR - http://www.scopus.com/inward/record.url?scp=84898787527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898787527&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.348

DO - 10.1109/ICCV.2013.348

M3 - Conference contribution

AN - SCOPUS:84898787527

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2800

EP - 2807

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -