Recovering the spatial layout of cluttered rooms

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

Abstract

In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing singleview 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter by modeling the global room space with a parameteric 3D "box" and by iteratively localizing clutter and refitting the box. To fit the box, we introduce a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues. On a dataset of 308 images, we demonstrate the ability of our algorithm to recover spatial layout in cluttered rooms and show several examples of estimated free space.

Original languageEnglish (US)
Title of host publication2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
Pages1849-1856
Number of pages8
DOIs
StatePublished - Dec 1 2009
Event12th International Conference on Computer Vision, ICCV 2009 - Kyoto, Japan
Duration: Sep 29 2009Oct 2 2009

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other12th International Conference on Computer Vision, ICCV 2009
CountryJapan
CityKyoto
Period9/29/0910/2/09

Fingerprint

Learning algorithms

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Hedau, V., Hoiem, D. W., & Forsyth, D. A. (2009). Recovering the spatial layout of cluttered rooms. In 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009 (pp. 1849-1856). [5459411] (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2009.5459411

Recovering the spatial layout of cluttered rooms. / Hedau, Varsha; Hoiem, Derek W; Forsyth, David Alexander.

2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. p. 1849-1856 5459411 (Proceedings of the IEEE International Conference on Computer Vision).

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

Hedau, V, Hoiem, DW & Forsyth, DA 2009, Recovering the spatial layout of cluttered rooms. in 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009., 5459411, Proceedings of the IEEE International Conference on Computer Vision, pp. 1849-1856, 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, 9/29/09. https://doi.org/10.1109/ICCV.2009.5459411
Hedau V, Hoiem DW, Forsyth DA. Recovering the spatial layout of cluttered rooms. In 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. p. 1849-1856. 5459411. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2009.5459411
Hedau, Varsha ; Hoiem, Derek W ; Forsyth, David Alexander. / Recovering the spatial layout of cluttered rooms. 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. pp. 1849-1856 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{82b1451ed5354ceda141e47594c4ab41,
title = "Recovering the spatial layout of cluttered rooms",
abstract = "In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing singleview 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter by modeling the global room space with a parameteric 3D {"}box{"} and by iteratively localizing clutter and refitting the box. To fit the box, we introduce a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues. On a dataset of 308 images, we demonstrate the ability of our algorithm to recover spatial layout in cluttered rooms and show several examples of estimated free space.",
author = "Varsha Hedau and Hoiem, {Derek W} and Forsyth, {David Alexander}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ICCV.2009.5459411",
language = "English (US)",
isbn = "9781424444205",
series = "Proceedings of the IEEE International Conference on Computer Vision",
pages = "1849--1856",
booktitle = "2009 IEEE 12th International Conference on Computer Vision, ICCV 2009",

}

TY - GEN

T1 - Recovering the spatial layout of cluttered rooms

AU - Hedau, Varsha

AU - Hoiem, Derek W

AU - Forsyth, David Alexander

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing singleview 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter by modeling the global room space with a parameteric 3D "box" and by iteratively localizing clutter and refitting the box. To fit the box, we introduce a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues. On a dataset of 308 images, we demonstrate the ability of our algorithm to recover spatial layout in cluttered rooms and show several examples of estimated free space.

AB - In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing singleview 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter by modeling the global room space with a parameteric 3D "box" and by iteratively localizing clutter and refitting the box. To fit the box, we introduce a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues. On a dataset of 308 images, we demonstrate the ability of our algorithm to recover spatial layout in cluttered rooms and show several examples of estimated free space.

UR - http://www.scopus.com/inward/record.url?scp=77953216235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953216235&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2009.5459411

DO - 10.1109/ICCV.2009.5459411

M3 - Conference contribution

AN - SCOPUS:77953216235

SN - 9781424444205

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1849

EP - 1856

BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009

ER -