Simultaneous Multi-View Instance Detection with Learned Geometric Soft-Constraints

Abstract

We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint, lighting conditions, high similarity of neighbouring objects, and strong variability in scale. By turning object detection and instance re-identification in different views into a joint learning task, we are able to incorporate both image appearance and geometric soft constraints into a single, multi-view detection process that is learnable end-to-end. We validate our method on a new, large data set of street-level panoramas of urban objects and show superior performance compared to various baselines. Our contribution is threefold: a large-scale, publicly available data set for multi-view instance detection and re-identification; an annotation tool custom-tailored for multi-view instance detection; and a novel, holistic multi-view instance detection and re-identification method that jointly models geometry and appearance across views.

Cite

Text

Nassar et al. "Simultaneous Multi-View Instance Detection with Learned Geometric Soft-Constraints." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00666

Markdown

[Nassar et al. "Simultaneous Multi-View Instance Detection with Learned Geometric Soft-Constraints." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/nassar2019iccv-simultaneous/) doi:10.1109/ICCV.2019.00666

BibTeX

@inproceedings{nassar2019iccv-simultaneous,
  title     = {{Simultaneous Multi-View Instance Detection with Learned Geometric Soft-Constraints}},
  author    = {Nassar, Ahmed Samy and Lefevre, Sebastien and Wegner, Jan Dirk},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00666},
  url       = {https://mlanthology.org/iccv/2019/nassar2019iccv-simultaneous/}
}