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

TL;DR

Multistream ValidNet enhances 6D object pose estimation accuracy by automatically validating results through a binary classifier, significantly reducing false positives and improving overall performance on benchmark datasets.

Contribution

Introduces a novel validation framework that improves existing pose estimation methods by automatically distinguishing true positives from false positives.

Findings

Outperforms CullNet by 4.15% in class accuracy

Improves Op-Net's average precision by 6.06%

Enhances pose estimation reliability on the Siléane dataset

Abstract

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. It achieves this by training a binary classifier on the output of an arbitrary pose estimation algorithm, and returns a binary label indicating the validity of the result. 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 accuracy and 0.73% in overall accuracy at validation. Applying our method can also improve the pose estimation average precision results of Op-Net by 6.06% on average.