TY - GEN
T1 - Recovering free space of indoor scenes from a single image
AU - Hedau, Varsha
AU - Hoiem, Derek
AU - Forsyth, David
PY - 2012
Y1 - 2012
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
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -