単発6D物体姿勢推定のためのニューラルネットワーク出力パラメータ化の検討
Investigations on Output Parameterizations of Neural Networks for Single Shot 6D Object Pose Estimation
単発の6D物体姿勢推定に向けてニューラルネットワークの出力パラメータ化を複数提案し、公開ベンチマークで最先端性能を達成するとともに、ICP補正なしで実ロボット把持に適用できることを示した。
著者: Kilian Kleeberger, Markus Völk, Richard Bormann, Marco F. Huber
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Single shot approaches have demonstrated tremendous success on various computer vision tasks. Finding good parameterizations for 6D object pose estimation remains an open challenge. In this work, we propose different novel parameterizations for the output of the neural network for single shot 6D object pose estimation. Our learning-based approach achieves state-of-the-art performance on two public benchmark datasets. Furthermore, we demonstrate that the pose estimates can be used for real-world robotic grasping tasks without additional ICP refinement.
