Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene [article]

Shubham Tulsiani, Saurabh Gupta, David Fouhey, Alexei A. Efros, Jitendra Malik
2018 arXiv   pre-print
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,
more » ... nd quantitatively and qualitatively demonstrate its merits compared to alternate representations.
arXiv:1712.01812v2 fatcat:cwpfek42s5bvzdvkh5iciy6gk4