Holistic 3D Scene Understanding from a Single Geo-tagged Image

Shenlong Wang; Sanja Fidler; Raquel Urtasun

doi:10.1109/CVPR.2015.7299022

Holistic 3D Scene Understanding from a Single Geo-tagged Image

Shenlong Wang, Sanja Fidler, Raquel Urtasun

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards this goal we propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well as depth reconstruction from a single image. Our approach takes advantage of large-scale crowd-sourced maps to generate dense geographic, geometric and semantic priors by rendering the 3D world. We demonstrate the effectiveness of our holistic model on the challenging KITTI dataset [13], and show significant improvements over the baselines in all metrics and tasks.

Original language	English (US)
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	3964-3972
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299022
State	Published - Oct 14 2015
Externally published	Yes
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: Jun 7 2015 → Jun 12 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Other

Other	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	6/7/15 → 6/12/15

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Online availability

10.1109/CVPR.2015.7299022

Library availability

Discover UIUC Full Text

Cite this

Wang, S., Fidler, S., & Urtasun, R. (2015). Holistic 3D Scene Understanding from a Single Geo-tagged Image. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 3964-3972). Article 7299022 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299022

Holistic 3D Scene Understanding from a Single Geo-tagged Image. / Wang, Shenlong; Fidler, Sanja; Urtasun, Raquel.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 3964-3972 7299022 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wang, S, Fidler, S & Urtasun, R 2015, Holistic 3D Scene Understanding from a Single Geo-tagged Image. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299022, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 3964-3972, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 6/7/15. https://doi.org/10.1109/CVPR.2015.7299022

@inproceedings{df76e1576faa4b37af5987710c635016,

title = "Holistic 3D Scene Understanding from a Single Geo-tagged Image",

abstract = "In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards this goal we propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well as depth reconstruction from a single image. Our approach takes advantage of large-scale crowd-sourced maps to generate dense geographic, geometric and semantic priors by rendering the 3D world. We demonstrate the effectiveness of our holistic model on the challenging KITTI dataset [13], and show significant improvements over the baselines in all metrics and tasks.",

author = "Shenlong Wang and Sanja Fidler and Raquel Urtasun",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7299022",

language = "English (US)",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "3964--3972",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

}

TY - GEN

T1 - Holistic 3D Scene Understanding from a Single Geo-tagged Image

AU - Wang, Shenlong

AU - Fidler, Sanja

AU - Urtasun, Raquel

PY - 2015/10/14

Y1 - 2015/10/14

N2 - In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards this goal we propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well as depth reconstruction from a single image. Our approach takes advantage of large-scale crowd-sourced maps to generate dense geographic, geometric and semantic priors by rendering the 3D world. We demonstrate the effectiveness of our holistic model on the challenging KITTI dataset [13], and show significant improvements over the baselines in all metrics and tasks.

AB - In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards this goal we propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well as depth reconstruction from a single image. Our approach takes advantage of large-scale crowd-sourced maps to generate dense geographic, geometric and semantic priors by rendering the 3D world. We demonstrate the effectiveness of our holistic model on the challenging KITTI dataset [13], and show significant improvements over the baselines in all metrics and tasks.

UR - http://www.scopus.com/inward/record.url?scp=84959241859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959241859&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299022

DO - 10.1109/CVPR.2015.7299022

M3 - Conference contribution

AN - SCOPUS:84959241859

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3964

EP - 3972

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Holistic 3D Scene Understanding from a Single Geo-tagged Image

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this