AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
This provides a generalizable multi-view pose estimation solution for robotics and industrial applications, though it builds incrementally on existing multi-view and feature-metric concepts.
The paper tackles the problem of 6D object pose estimation from multiple RGB views, addressing limitations like depth ambiguity and lack of generalization in existing methods. It introduces AlignPose, which outperforms other published methods on four datasets, particularly on challenging industrial datasets.
Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter, and occlusions. Multi-view pose estimation methods have the potential to solve these issues, but existing works rely on precise single-view pose estimates or lack generalization to unseen objects. We address these challenges via the following three contributions. First, we introduce AlignPose, a 6D object pose estimation method that aggregates information from multiple extrinsically calibrated RGB views and does not require any object-specific training or symmetry annotation. Second, the key component of this approach is a new multi-view feature-metric refinement specifically designed for object pose. It optimizes a single, consistent world-frame object pose minimizing the feature discrepancy between on-the-fly rendered object features and observed image features across all views simultaneously. Third, we report extensive experiments on four datasets (YCB-V, T-LESS, ITODD-MV, HouseCat6D) using the BOP benchmark evaluation and show that AlignPose outperforms other published methods, especially on challenging industrial datasets where multiple views are readily available in practice.