Beyond the Line of Sight: Labeling the Underlying Surfaces

Abstract

Scene understanding requires reasoning about both what we can see and what is occluded. We offer a simple and general approach to infer labels of occluded background regions. Our approach incorporates estimates of visible surrounding background, detected objects, and shape priors from transferred training regions. We demonstrate the ability to infer the labels of occluded background regions in both the outdoor StreetScenes dataset and an indoor scene dataset using the same approach. Our experiments show that our method outperforms competent baselines.

Cite

Text

Guo and Hoiem. "Beyond the Line of Sight: Labeling the Underlying Surfaces." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33715-4_55

Markdown

[Guo and Hoiem. "Beyond the Line of Sight: Labeling the Underlying Surfaces." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/guo2012eccv-beyond/) doi:10.1007/978-3-642-33715-4_55

BibTeX

@inproceedings{guo2012eccv-beyond,
  title     = {{Beyond the Line of Sight: Labeling the Underlying Surfaces}},
  author    = {Guo, Ruiqi and Hoiem, Derek},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {761-774},
  doi       = {10.1007/978-3-642-33715-4_55},
  url       = {https://mlanthology.org/eccv/2012/guo2012eccv-beyond/}
}