学习2D不变的可供性知识以实现3D可供性定位
Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
AI总结：
本文提出MIFAG框架，通过多视角交互图像提取不变可供性知识，提升3D对象可供性定位的泛化能力。
摘要：
3D对象可供性定位旨在预测3D对象的功能区域，为机器人应用奠定基础。近期研究通过学习3D区域与单个人体-对象交互图像之间的映射来解决该问题，但3D对象的几何结构和人体-对象交互图像中的对象并不总是一致，导致泛化能力差。为了解决这一问题，我们提出从同一可供性类别内的多个人体-对象交互图像中学习可泛化的不变可供性知识。具体来说，我们引入了多图像引导的不变特征感知3D可供性定位（MIFAG）框架。该框架通过识别多个人体-对象交互图像中的共同交互模式来定位3D对象的可供性区域。首先，不变可供性知识提取模块（IAM）利用迭代更新策略逐步从多个图像中提取对齐的可供性知识，并将其整合到可供性词典中。然后，可供性词典自适应融合模块（ADM）学习综合的点云表示，考虑多个图像中的所有可供性候选。此外，构建了多图像和点可供性（MIPA）基准，并在各种实验比较中，我们的方法优于现有最先进方法。
英文摘要：
3D Object Affordance Grounding aims to predict the functional regions on a 3D object and has laid the foundation for a wide range of applications in robotics. Recent advances tackle this problem via learning a mapping between 3D regions and a single human-object interaction image. However, the geometric structure of the 3D object and the object in the human-object interaction image are not always consistent, leading to poor generalization. To address this issue, we propose to learn generalizable invariant affordance knowledge from multiple human-object interaction images within the same affordance category. Specifically, we introduce the Multi-Image Guided Invariant-Feature-Aware 3D Affordance Grounding (MIFAG) framework. It grounds 3D object affordance regions by identifying common interaction patterns across multiple human-object interaction images. First, the Invariant Affordance Knowledge Extraction Module (IAM) utilizes an iterative updating strategy to gradually extract aligned affordance knowledge from multiple images and integrate it into an affordance dictionary. Then, the Affordance Dictionary Adaptive Fusion Module (ADM) learns comprehensive point cloud representations that consider all affordance candidates in multiple images. Besides, the Multi-Image and Point Affordance (MIPA) benchmark is constructed and our method outperforms existing state-of-the-art methods on various experimental comparisons.
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。
