Monocular Object Instance Segmentation and Depth Ordering with CNNs

Ziyu Zhang, Alexander G. Schwing, Sanja Fidler, Raquel Urtasun

ICCV 2015

doi:10.1109/ICCV.2015.300 /iccv/2015/zhang2015iccv-monocular/

Abstract

In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where the instance ID encodes the depth ordering within image patches. To provide a coherent single explanation of an image we develop a Markov random field which takes as input the predictions of convolutional neural nets applied at overlapping patches of different resolutions, as well as the output of a connected component algorithm. It aims to predict accurate instance-level segmentation and depth ordering. We demonstrate the effectiveness of our approach on the challenging KITTI benchmark and show good performance on both tasks.

PDF ICCV Semantic Scholar

Cite

Text

Zhang et al. "Monocular Object Instance Segmentation and Depth Ordering with CNNs." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.300

Markdown

[Zhang et al. "Monocular Object Instance Segmentation and Depth Ordering with CNNs." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/zhang2015iccv-monocular/) doi:10.1109/ICCV.2015.300

BibTeX

@inproceedings{zhang2015iccv-monocular,
  title     = {{Monocular Object Instance Segmentation and Depth Ordering with CNNs}},
  author    = {Zhang, Ziyu and Schwing, Alexander G. and Fidler, Sanja and Urtasun, Raquel},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.300},
  url       = {https://mlanthology.org/iccv/2015/zhang2015iccv-monocular/}
}