Mutual Hypothesis Verification for 6D Pose Estimation of Natural Objects

Kiru Park, Johann Prankl, Markus Vincze; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2192-2199

Estimating the 6D pose of natural objects, such as vegetables and fruit, is a challenging problem due to the high variability of their shape. We propose a novel framework that consists of a local and a global hypothesis generation pipeline with a mutual verification step. The new local descriptor is proposed to find critical parts of the natural object while the global estimator calculates object pose directly. A novel hypothesis verification step, Mutual Hypothesis Verification, is proposed to determine the best pose. It interactively uses information from the local and the global pipelines. New hypotheses are generated by combining the global estimation and the local shape correspondences. The confidence of a pose candidate is calculated by comparing with estimation results from both pipelines. The evaluation with real fruit shows the potential for estimating the pose of any natural object while outperforming global feature based approaches.