DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes

Saumitro Dasgupta, Kuan Fang, Kevin Chen, Silvio Savarese

CVPR 2016

doi:10.1109/CVPR.2016.73 /cvpr/2016/dasgupta2016cvpr-delay/

Abstract

We consider the problem of estimating the spatial layout of an indoor scene from a monocular RGB image, modeled as the projection of a 3D cuboid. Existing solutions to this problem often rely strongly on hand-engineered features and vanishing point detection, which are prone to failure in the presence of clutter. In this paper, we present a method that uses a fully convolutional neural network (FCNN) in conjunction with a novel optimization framework for generating layout estimates. We demonstrate that our method is robust in the presence of clutter and handles a wide range of highly challenging scenes. We evaluate our method on two standard benchmarks and show that it achieves state of the art results, outperforming previous methods by a wide margin.

PDF CVPR Semantic Scholar

Cite

Text

Dasgupta et al. "DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.73

Markdown

[Dasgupta et al. "DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/dasgupta2016cvpr-delay/) doi:10.1109/CVPR.2016.73

BibTeX

@inproceedings{dasgupta2016cvpr-delay,
  title     = {{DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes}},
  author    = {Dasgupta, Saumitro and Fang, Kuan and Chen, Kevin and Savarese, Silvio},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.73},
  url       = {https://mlanthology.org/cvpr/2016/dasgupta2016cvpr-delay/}
}