Probability Occupancy Maps for Occluded Depth Images

Timur Bagautdinov, Francois Fleuret, Pascal Fua

CVPR 2015

doi:10.1109/CVPR.2015.7298900 /cvpr/2015/bagautdinov2015cvpr-probability/

Abstract

We propose a novel approach to computing the probabilities of presence of multiple and potentially occluding objects in a scene from a single depth map. To this end, we use a generative model that predicts the distribution of depth images that would be produced if the probabilities of presence were known and then to optimize them so that this distribution explains observed evidence as closely as possible. This allows us to exploit very effectively the available evidence and outperform state-of-the-art methods without requiring large amounts of data, or without using the RGB signal that modern RGB-D sensors also provide.

PDF CVPR Semantic Scholar

Cite

Text

Bagautdinov et al. "Probability Occupancy Maps for Occluded Depth Images." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298900

Markdown

[Bagautdinov et al. "Probability Occupancy Maps for Occluded Depth Images." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/bagautdinov2015cvpr-probability/) doi:10.1109/CVPR.2015.7298900

BibTeX

@inproceedings{bagautdinov2015cvpr-probability,
  title     = {{Probability Occupancy Maps for Occluded Depth Images}},
  author    = {Bagautdinov, Timur and Fleuret, Francois and Fua, Pascal},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298900},
  url       = {https://mlanthology.org/cvpr/2015/bagautdinov2015cvpr-probability/}
}