ML Anthology

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 2018
doi:10.1109/CVPR.2018.00039 /cvpr/2018/tulsiani2018cvpr-factoring/

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.

PDF CVPR Semantic Scholar

Cite

Text

Tulsiani et al. "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00039

Markdown

[Tulsiani et al. "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/tulsiani2018cvpr-factoring/) doi:10.1109/CVPR.2018.00039

BibTeX

@inproceedings{tulsiani2018cvpr-factoring,
  title     = {{Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene}},
  author    = {Tulsiani, Shubham and Gupta, Saurabh and Fouhey, David F. and Efros, Alexei A. and Malik, Jitendra},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00039},
  url       = {https://mlanthology.org/cvpr/2018/tulsiani2018cvpr-factoring/}
}