Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data

Fabian Manhardt, Diego Martin Arroyo, Christian Rupprecht, Benjamin Busam, Tolga Birdal, Nassir Navab, Federico Tombari; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 6841-6850

Abstract


3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. This ambiguity in both detection and pose estimation means that an object instance can be perfectly described by several different poses and even classes. In this work we propose to explicitly deal with these ambiguities. For each object instance we predict multiple 6D pose outcomes to estimate the specific pose distribution generated by symmetries and repetitive textures. The distribution collapses to a single outcome when the visual appearance uniquely identifies just one valid pose. We show the benefits of our approach which provides not only a better explanation for pose ambiguity, but also a higher accuracy in terms of pose estimation.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Manhardt_2019_ICCV,
author = {Manhardt, Fabian and Arroyo, Diego Martin and Rupprecht, Christian and Busam, Benjamin and Birdal, Tolga and Navab, Nassir and Tombari, Federico},
title = {Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}