Recovering the spatial layout of cluttered rooms

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 single-view 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Hedau, Varsha, Hoiem, Derek, Forsyth, David
Format: Conference Proceeding
Language:English
Subjects:
Computer science
Floors
Humans
Image segmentation
Iterative algorithms
Labeling
Layout
Parameter estimation
Reconstruction algorithms
Robustness
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 single-view 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.
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2009.5459411