Keypoint-Based Disentangled Pose Network for Category-Level 6D Object Pose Tracking.

Category-level 6D object pose tracking is very challenging in the field of 3D computer vision. Keypoint-based object pose estimation has demonstrated its effectiveness in dealing with it. However, current approaches first estimate the keypoints through a neural network and further compute the inter-frame pose change via least-squares optimization. They estimate rotation and translation in the same way, ignoring the differences between them. In this work, we propose a keypoint-based disentangled pose network (KDPNet), which disentangles the 6D object pose change to 3D rotation and 3D translation. Specifically, the translation is directly estimated by the network and the rotation is indirectly calculated by Singular Value Decomposition (SVD) according to the keypoints. Extensive experiments on NOCS-REAL275 dataset demonstrate the superiority of our method.