Recovering free space of indoor scenes from a single image

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

Abstract

In this paper we consider the problem of recovering the free space of an indoor scene from its single image. We show that exploiting the box like geometric structure of furniture and constraints provided by the scene, allows us to recover the extent of major furniture objects in 3D. Our boxy detector localizes box shaped objects oriented parallel to the scene across different scales and object types, and thus blocks out the occupied space in the scene. To localize the objects more accurately in 3D we introduce a set of specially designed features that capture the floor contact points of the objects. Image based metrics are not very indicative of performance in 3D. We make the first attempt to evaluate single view based occupancy estimates for 3D errors and propose several task driven performance measures towards it. On our dataset of 592 indoor images marked with full 3D geometry of the scene, we show that: (a) our detector works well using image based metrics; (b) our refinement method produces significant improvements in localization in 3D; and (c) if one evaluates using 3D metrics, our method offers major improvements over other single view based scene geometry estimation methods.

Original languageEnglish (US)
Title of host publication2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Pages2807-2814
Number of pages8
DOIs
StatePublished - Oct 1 2012
Event2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
Duration: Jun 16 2012Jun 21 2012

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
CountryUnited States
CityProvidence, RI
Period6/16/126/21/12

Fingerprint

Detectors
Geometry
Point contacts

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Hedau, V., Hoiem, D. W., & Forsyth, D. A. (2012). Recovering free space of indoor scenes from a single image. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 (pp. 2807-2814). [6248005] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2012.6248005

Recovering free space of indoor scenes from a single image. / Hedau, Varsha; Hoiem, Derek W; Forsyth, David Alexander.

2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. p. 2807-2814 6248005 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

Hedau, V, Hoiem, DW & Forsyth, DA 2012, Recovering free space of indoor scenes from a single image. in 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012., 6248005, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2807-2814, 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012, Providence, RI, United States, 6/16/12. https://doi.org/10.1109/CVPR.2012.6248005
Hedau V, Hoiem DW, Forsyth DA. Recovering free space of indoor scenes from a single image. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. p. 2807-2814. 6248005. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2012.6248005
Hedau, Varsha ; Hoiem, Derek W ; Forsyth, David Alexander. / Recovering free space of indoor scenes from a single image. 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. pp. 2807-2814 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{70680ebfaf384fd5a0fb0a4915b4dd88,
title = "Recovering free space of indoor scenes from a single image",
abstract = "In this paper we consider the problem of recovering the free space of an indoor scene from its single image. We show that exploiting the box like geometric structure of furniture and constraints provided by the scene, allows us to recover the extent of major furniture objects in 3D. Our boxy detector localizes box shaped objects oriented parallel to the scene across different scales and object types, and thus blocks out the occupied space in the scene. To localize the objects more accurately in 3D we introduce a set of specially designed features that capture the floor contact points of the objects. Image based metrics are not very indicative of performance in 3D. We make the first attempt to evaluate single view based occupancy estimates for 3D errors and propose several task driven performance measures towards it. On our dataset of 592 indoor images marked with full 3D geometry of the scene, we show that: (a) our detector works well using image based metrics; (b) our refinement method produces significant improvements in localization in 3D; and (c) if one evaluates using 3D metrics, our method offers major improvements over other single view based scene geometry estimation methods.",
author = "Varsha Hedau and Hoiem, {Derek W} and Forsyth, {David Alexander}",
year = "2012",
month = "10",
day = "1",
doi = "10.1109/CVPR.2012.6248005",
language = "English (US)",
isbn = "9781467312264",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
pages = "2807--2814",
booktitle = "2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012",

}

TY - GEN

T1 - Recovering free space of indoor scenes from a single image

AU - Hedau, Varsha

AU - Hoiem, Derek W

AU - Forsyth, David Alexander

PY - 2012/10/1

Y1 - 2012/10/1

N2 - In this paper we consider the problem of recovering the free space of an indoor scene from its single image. We show that exploiting the box like geometric structure of furniture and constraints provided by the scene, allows us to recover the extent of major furniture objects in 3D. Our boxy detector localizes box shaped objects oriented parallel to the scene across different scales and object types, and thus blocks out the occupied space in the scene. To localize the objects more accurately in 3D we introduce a set of specially designed features that capture the floor contact points of the objects. Image based metrics are not very indicative of performance in 3D. We make the first attempt to evaluate single view based occupancy estimates for 3D errors and propose several task driven performance measures towards it. On our dataset of 592 indoor images marked with full 3D geometry of the scene, we show that: (a) our detector works well using image based metrics; (b) our refinement method produces significant improvements in localization in 3D; and (c) if one evaluates using 3D metrics, our method offers major improvements over other single view based scene geometry estimation methods.

AB - In this paper we consider the problem of recovering the free space of an indoor scene from its single image. We show that exploiting the box like geometric structure of furniture and constraints provided by the scene, allows us to recover the extent of major furniture objects in 3D. Our boxy detector localizes box shaped objects oriented parallel to the scene across different scales and object types, and thus blocks out the occupied space in the scene. To localize the objects more accurately in 3D we introduce a set of specially designed features that capture the floor contact points of the objects. Image based metrics are not very indicative of performance in 3D. We make the first attempt to evaluate single view based occupancy estimates for 3D errors and propose several task driven performance measures towards it. On our dataset of 592 indoor images marked with full 3D geometry of the scene, we show that: (a) our detector works well using image based metrics; (b) our refinement method produces significant improvements in localization in 3D; and (c) if one evaluates using 3D metrics, our method offers major improvements over other single view based scene geometry estimation methods.

UR - http://www.scopus.com/inward/record.url?scp=84866725130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866725130&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2012.6248005

DO - 10.1109/CVPR.2012.6248005

M3 - Conference contribution

AN - SCOPUS:84866725130

SN - 9781467312264

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

SP - 2807

EP - 2814

BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012

ER -