Improving 6D Object Pose Estimation of metallic Household and Industry Objects
This addresses a domain-specific problem for industrial applications where metallic objects cause challenges like reflections, but it is incremental as it builds on existing methods and datasets.
The paper tackles the problem of reduced accuracy in 6D object pose estimation for metallic objects by creating a novel BOP-compatible dataset with additional geometric and visual cues, and demonstrates improved accuracy on this dataset by enhancing the GDRNPP algorithm with keypoint prediction and material estimation.
6D object pose estimation suffers from reduced accuracy when applied to metallic objects. We set out to improve the state-of-the-art by addressing challenges such as reflections and specular highlights in industrial applications. Our novel BOP-compatible dataset, featuring a diverse set of metallic objects (cans, household, and industrial items) under various lighting and background conditions, provides additional geometric and visual cues. We demonstrate that these cues can be effectively leveraged to enhance overall performance. To illustrate the usefulness of the additional features, we improve upon the GDRNPP algorithm by introducing an additional keypoint prediction and material estimator head in order to improve spatial scene understanding. Evaluations on the new dataset show improved accuracy for metallic objects, supporting the hypothesis that additional geometric and visual cues can improve learning.