Unsupervised Monocular Depth and Ego-Motion Learning with Structure and Semantics

Vincent Casser, Sören Pirk, Reza Mahjourian, Anelia Angelova

CVPRW 2019 pp. 381-388

doi:10.1109/CVPRW.2019.00051 /cvprw/2019/casser2019cvprw-unsupervised/

Abstract

We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically we model the motions of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. Code and models have been open sourced at: https://sites.google.com/corp/view/struct2depth.

PDF CVPRW Semantic Scholar

Cite

Text

Casser et al. "Unsupervised Monocular Depth and Ego-Motion Learning with Structure and Semantics." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00051

Markdown

[Casser et al. "Unsupervised Monocular Depth and Ego-Motion Learning with Structure and Semantics." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/casser2019cvprw-unsupervised/) doi:10.1109/CVPRW.2019.00051

BibTeX

@inproceedings{casser2019cvprw-unsupervised,
  title     = {{Unsupervised Monocular Depth and Ego-Motion Learning with Structure and Semantics}},
  author    = {Casser, Vincent and Pirk, Sören and Mahjourian, Reza and Angelova, Anelia},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {381-388},
  doi       = {10.1109/CVPRW.2019.00051},
  url       = {https://mlanthology.org/cvprw/2019/casser2019cvprw-unsupervised/}
}