论文标题
6DOF姿势估计的混合方法
A Hybrid Approach for 6DoF Pose Estimation
论文作者
论文摘要
我们提出了一种使用基于深度学习的实例检测器在RGB图像中分段对象实例的刚性对象的6DOF姿势估计的方法，然后是基于点对的投票方法来恢复对象的姿势。我们还使用自动方法选择，该方法选择实例检测器和训练集，因为验证集中的性能最高。这种混合方法利用了最好的学习和经典方法，使用CNN来过滤高度非结构化的数据并切断混乱，以及一种局部几何方法，具有可证明的融合以进行稳健的姿势估计。该方法在BOP核心数据集上进行评估，该数据集大大超过了基线方法，并且是BOP 2020挑战中最佳的快速方法。
We propose a method for 6DoF pose estimation of rigid objects that uses a state-of-the-art deep learning based instance detector to segment object instances in an RGB image, followed by a point-pair based voting method to recover the object's pose. We additionally use an automatic method selection that chooses the instance detector and the training set as that with the highest performance on the validation set. This hybrid approach leverages the best of learning and classic approaches, using CNNs to filter highly unstructured data and cut through the clutter, and a local geometric approach with proven convergence for robust pose estimation. The method is evaluated on the BOP core datasets where it significantly exceeds the baseline method and is the best fast method in the BOP 2020 Challenge.
