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

Ahmed Samy Nassar, Sebastien Lefevre, Jan Dirk Wegner; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 6559-6568


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.

Related Material

[pdf] [supp]
author = {Nassar, Ahmed Samy and Lefevre, Sebastien and Wegner, Jan Dirk},
title = {Simultaneous Multi-View Instance Detection With Learned Geometric Soft-Constraints},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}