ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation

Catherine Capellen, Max Schwarz, Sven Behnke

Abstract

6D object pose estimation is a prerequisite for many applications. In recent years, monocular pose estimation has attracted much research interest because it does not need depth measurements. In this work, we introduce ConvPoseCNN, a fully convolutional architecture that avoids cutting out individual objects. Instead we propose pixel-wise, dense prediction of both translation and orientation components of the object pose, where the dense orientation is represented in Quaternion form. We present different approaches for aggregation of the dense orientation predictions, including averaging and clustering schemes. We evaluate ConvPoseCNN on the challenging YCB-Video Dataset, where we show that the approach has far fewer parameters and trains faster than comparable methods without sacrificing accuracy. Furthermore, our results indicate that the dense orientation prediction implicitly learns to attend to trustworthy, occlusion-free, and feature-rich object regions.

Download


Paper Citation


in Harvard Style

Capellen C., Schwarz M. and Behnke S. (2020). ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, pages 162-172. DOI: 10.5220/0008990901620172


in Bibtex Style

@conference{visapp20,
author={Catherine Capellen and Max Schwarz and Sven Behnke},
title={ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={162-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008990901620172},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation
SN - 978-989-758-402-2
AU - Capellen C.
AU - Schwarz M.
AU - Behnke S.
PY - 2020
SP - 162
EP - 172
DO - 10.5220/0008990901620172