Recovering free space of indoor scenes from a single image
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2807-2814
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.Keywords
This publication has 14 references indexed in Scilit:
- Rendering synthetic objects into legacy photographsACM Transactions on Graphics, 2011
- Recognition using visual phrases2011
- Sampling bedrooms2011
- Discriminative models for multi-class object layout2009
- Geometric reasoning for single image structure recovery2009
- Inferring spatial layout from a single image via depth-ordered grouping2008
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- Opportunistic Use of Vision to Push Back the Path-Planning Horizon2006
- A new approach to vanishing point detection in architectural environmentsImage and Vision Computing, 2002
- Manhattan World: compass direction from a single image by Bayesian inference1999