Category-level 6D Object Pose Recovery in Depth Images
This addresses the problem of robust pose estimation for unseen object instances in robotics or AR/VR, though it appears incremental as it builds on existing part-based and graph matching techniques.
The paper tackles category-level 6D object pose estimation in depth images by introducing a part-based architecture called Intrinsic Structure Adaptor (ISA) to handle intra-class variations and distribution shifts, achieving promising performance on synthetic and real datasets.
Intra-class variations, distribution shifts among source and target domains are the major challenges of category-level tasks. In this study, we address category-level full 6D object pose estimation in the context of depth modality, introducing a novel part-based architecture that can tackle the above-mentioned challenges. Our architecture particularly adapts the distribution shifts arising from shape discrepancies, and naturally removes the variations of texture, illumination, pose, etc., so we call it as "Intrinsic Structure Adaptor (ISA)". We engineer ISA based on the followings: i) "Semantically Selected Centers (SSC)" are proposed in order to define the "6D pose" at the level of categories. ii) 3D skeleton structures, which we derive as shape-invariant features, are used to represent the parts extracted from the instances of given categories, and privileged one-class learning is employed based on these parts. iii) Graph matching is performed during training in such a way that the adaptation/generalization capability of the proposed architecture is improved across unseen instances. Experiments validate the promising performance of the proposed architecture on both synthetic and real datasets.