具有对称标注自由学习策略的通用且可操作的部件姿态估计
Generalizable and Actionable Parts Pose Estimation with Symmetry Annotation-Free Learning Strategy
AI总结:
本文提出了一种无需对称标注的通用且可操作的部件姿态估计框架SAFAG,通过分步细化两阶段框架和自监督学习策略解决对称预测问题,提升了在数据匮乏场景下的姿态估计性能和鲁棒性。
摘要:
迫切需要的通用机器人物体交互和操作要求高质量的跨类别物体感知。作为该领域的先驱,通用且可操作的部件(GAParts)理解吸引了越来越多相关研究人员的关注。然而,大多数最近的工作要么在对称问题的设计上不足,要么需要丰富的对称标注,这严重阻碍了在数据匮乏场景中精确的GAPart姿态估计。在本文中,我们提出SAFAG,一种新的无需对称标注的通用且可操作的部件姿态估计框架。具体而言,我们建议了一个分步细化的两阶段框架用于候选到最终的四元数回归,并将对称预测作为概率分布问题,通过自监督学习策略进行解决。实验结果证明了我们SAFAG的优越性能和鲁棒性。我们相信我们的工作在许多具身AI系统领域具有巨大的应用潜力。
英文摘要:
Urgently needed generalizable robot object interaction and manipulation requires high-quality Cross-Category object perception. As a pioneer of this area, Generalizable and Actionable Parts (GAParts) understanding has attracted increasing attention from relevant researchers. However, most recent works either have insufficient design regarding the symmetry issue or require rich symmetry annotation, which severely impedes precise GAPart pose estimation in data-lacking scenarios. In this paper, we propose SAFAG, a novel Symmetry Annotation-Free framework for Generalizable and Actionable Parts Pose Estimation. Specifically, we suggest a stepwise refinement two-stage framework for candidate-to-final quaternion regression, and tackle the symmetry prediction as a probability distribution problem with self-supervised learning strategy. The experimental results demonstrate the superior performance and robustness of our SAFAG. We believe that our work has the enormous potential to be applied in many areas of embodied AI system.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。