Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene

Shubham Tulsiani; Saurabh Gupta; David F. Fouhey; Alexei A. Efros; Jitendra Malik

CVPR 2018poster157 citations

Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene

Shubham Tulsiani, Saurabh Gupta, David F. Fouhey, Alexei A. Efros, Jitendra Malik

Abstract

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.

BibTeX

@inproceedings{cvpr2018_factoringshapepo,
  title = {Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene},
  author = {Shubham Tulsiani and Saurabh Gupta and David F. Fouhey and Alexei A. Efros and Jitendra Malik},
  booktitle = {CVPR 2018},
  year = {2018}
}