ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking
This addresses deployment efficiency for robotic bin-picking by enabling zero-shot pose estimation without object-specific training, though it is domain-specific to bin-picking.
The paper tackles the problem of 6D pose estimation for textureless, randomly stacked workpieces in bin-picking by proposing ZeroBP, a zero-shot framework that learns position-aware correspondence, resulting in a 9.1% improvement in average recall over state-of-the-art methods.
Bin-picking is a practical and challenging robotic manipulation task, where accurate 6D pose estimation plays a pivotal role. The workpieces in bin-picking are typically textureless and randomly stacked in a bin, which poses a significant challenge to 6D pose estimation. Existing solutions are typically learning-based methods, which require object-specific training. Their efficiency of practical deployment for novel workpieces is highly limited by data collection and model retraining. Zero-shot 6D pose estimation is a potential approach to address the issue of deployment efficiency. Nevertheless, existing zero-shot 6D pose estimation methods are designed to leverage feature matching to establish point-to-point correspondences for pose estimation, which is less effective for workpieces with textureless appearances and ambiguous local regions. In this paper, we propose ZeroBP, a zero-shot pose estimation framework designed specifically for the bin-picking task. ZeroBP learns Position-Aware Correspondence (PAC) between the scene instance and its CAD model, leveraging both local features and global positions to resolve the mismatch issue caused by ambiguous regions with similar shapes and appearances. Extensive experiments on the ROBI dataset demonstrate that ZeroBP outperforms state-of-the-art zero-shot pose estimation methods, achieving an improvement of 9.1% in average recall of correct poses.