Data-driven 3D primitives for single image understanding

David F. Fouhey; Abhinav Gupta; Martial Hebert

doi:10.1109/ICCV.2013.421

Data-driven 3D primitives for single image understanding

David F. Fouhey, Abhinav Gupta, Martial Hebert

Computer Science

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

Abstract

What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.

Original language	English (US)
Title of host publication	Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3392-3399
Number of pages	8
ISBN (Print)	9781479928392
DOIs	https://doi.org/10.1109/ICCV.2013.421
State	Published - 2013
Event	2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia Duration: Dec 1 2013 → Dec 8 2013

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Other

Other	2013 14th IEEE International Conference on Computer Vision, ICCV 2013
Country/Territory	Australia
City	Sydney, NSW
Period	12/1/13 → 12/8/13

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2013.421

Cite this

Fouhey, D. F., Gupta, A., & Hebert, M. (2013). Data-driven 3D primitives for single image understanding. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 3392-3399). Article 6751533 (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.421

Data-driven 3D primitives for single image understanding. / Fouhey, David F.; Gupta, Abhinav; Hebert, Martial.
Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 3392-3399 6751533 (Proceedings of the IEEE International Conference on Computer Vision).

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

Fouhey, DF, Gupta, A & Hebert, M 2013, Data-driven 3D primitives for single image understanding. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751533, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 3392-3399, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 12/1/13. https://doi.org/10.1109/ICCV.2013.421

@inproceedings{306cdd4bec614a32973bac408a5e8b82,

title = "Data-driven 3D primitives for single image understanding",

abstract = "What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.",

author = "Fouhey, {David F.} and Abhinav Gupta and Martial Hebert",

year = "2013",

doi = "10.1109/ICCV.2013.421",

language = "English (US)",

isbn = "9781479928392",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3392--3399",

booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",

note = "2013 14th IEEE International Conference on Computer Vision, ICCV 2013 ; Conference date: 01-12-2013 Through 08-12-2013",

}

TY - GEN

T1 - Data-driven 3D primitives for single image understanding

AU - Fouhey, David F.

AU - Gupta, Abhinav

AU - Hebert, Martial

PY - 2013

Y1 - 2013

N2 - What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.

AB - What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.

UR - http://www.scopus.com/inward/record.url?scp=84898832490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898832490&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.421

DO - 10.1109/ICCV.2013.421

M3 - Conference contribution

AN - SCOPUS:84898832490

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 3392

EP - 3399

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2013 14th IEEE International Conference on Computer Vision, ICCV 2013

Y2 - 1 December 2013 through 8 December 2013

ER -

Data-driven 3D primitives for single image understanding

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this