TY - GEN
T1 - Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
AU - Tulsiani, Shubham
AU - Gupta, Saurabh
AU - Fouhey, David
AU - Efrosefros, Alexei A.
AU - Malik, Jitendra
N1 - Funding Information:
This work was supported in part by Intel/NSF VEC award IIS-1539099, NSF Award IIS- 1212798, and the Google Fellowship to SG. We gratefully acknowledge NVIDIA corporation for the donation of Tesla GPUs used for this research.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - The goal of this paper is to take a single 2D image of a scene and recover the 3D structure in terms of a small set of factors: a layout representing the enclosing surfaces as well as a set of objects represented in terms of shape and pose. We propose a convolutional neural network-based approach to predict this representation and benchmark it on a large dataset of indoor scenes. Our experiments evaluate a number of practical design questions, demonstrate that we can infer this representation, and quantitatively and qualitatively demonstrate its merits compared to alternate representations.
AB - The goal of this paper is to take a single 2D image of a scene and recover the 3D structure in terms of a small set of factors: a layout representing the enclosing surfaces as well as a set of objects represented in terms of shape and pose. We propose a convolutional neural network-based approach to predict this representation and benchmark it on a large dataset of indoor scenes. Our experiments evaluate a number of practical design questions, demonstrate that we can infer this representation, and quantitatively and qualitatively demonstrate its merits compared to alternate representations.
UR - http://www.scopus.com/inward/record.url?scp=85060844155&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060844155&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00039
DO - 10.1109/CVPR.2018.00039
M3 - Conference contribution
AN - SCOPUS:85060844155
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 302
EP - 310
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -