REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination
This work addresses the need for robust and interpretable pose estimation in applications like robotics and augmented reality, but it is incremental as it builds on existing keypoint-based approaches.
The paper tackles the problem of object 6D pose estimation by proposing REDE, an end-to-end method that uses RGB-D data for keypoint regression and includes a differentiable outliers elimination technique to improve robustness against occlusion; it achieves slightly better performance than state-of-the-art methods on three benchmark datasets.
Object 6D pose estimation is a fundamental task in many applications. Conventional methods solve the task by detecting and matching the keypoints, then estimating the pose. Recent efforts bringing deep learning into the problem mainly overcome the vulnerability of conventional methods to environmental variation due to the hand-crafted feature design. However, these methods cannot achieve end-to-end learning and good interpretability at the same time. In this paper, we propose REDE, a novel end-to-end object pose estimator using RGB-D data, which utilizes network for keypoint regression, and a differentiable geometric pose estimator for pose error back-propagation. Besides, to achieve better robustness when outlier keypoint prediction occurs, we further propose a differentiable outliers elimination method that regresses the candidate result and the confidence simultaneously. Via confidence weighted aggregation of multiple candidates, we can reduce the effect from the outliers in the final estimation. Finally, following the conventional method, we apply a learnable refinement process to further improve the estimation. The experimental results on three benchmark datasets show that REDE slightly outperforms the state-of-the-art approaches and is more robust to object occlusion.