Filters








2 Hits in 3.5 sec

CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation [article]

Kartik Gupta, Lars Petersson, Richard Hartley
2019 arXiv   pre-print
This is then used to calibrate the confidence scores of the pose proposals.  ...  This new set of confidence scores is found to be significantly more reliable for accurate object pose estimation as shown by our results.  ...  CullNet to find the calibrated confidence scores, used for selecting the most accurate pose proposal.  ... 
arXiv:1909.13476v1 fatcat:mhhtvg275vc5bdh2syxhd2k7uq

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation [article]

Joy Mazumder, Mohsen Zand, Michael Greenspan
2021 arXiv   pre-print
This work presents a novel approach to improve the results of pose estimation by detecting and distinguishing between the occurrence of True and False Positive results.  ...  We demonstrate that our approach improves upon a state-of-the-art pose estimation result on the Sil\'eane dataset, outperforming a variation of the alternative CullNet method by 4.15% in average class  ...  They proposed CullNet to calibrate the confidence scores of the pose proposals. Mazumder et al.  ... 
arXiv:2106.06684v1 fatcat:nhde7fojcrejpl4psfjbwztqsq