Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation
This work addresses accuracy issues in pose estimation for computer vision applications, but it is incremental as it builds on existing methods like CullNet and Op-Net.
The paper tackles the problem of distinguishing true and false positives in 6D object pose estimation by training a binary classifier on pose estimation outputs, improving state-of-the-art results by up to 6.06% in average precision on datasets like Siléane.
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 Siléane 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.