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.

翻译：三维物体可供性定位旨在预测三维物体上的功能区域，为机器人学中的广泛应用奠定基础。近期研究通过建立三维区域与单张人-物交互图像之间的映射关系来解决此问题。然而，三维物体的几何结构与人-物交互图像中的物体几何结构并不总保持一致，导致泛化能力不足。为解决该问题，我们提出从同一可供性类别内的多张人-物交互图像中学习可泛化的不变可供性知识。具体而言，我们提出了多图像引导的不变特征感知三维可供性定位（MIFAG）框架。该框架通过识别多张人-物交互图像中的共性交互模式来实现三维物体可供性区域的定位。首先，不变可供性知识提取模块（IAM）采用迭代更新策略，逐步从多幅图像中提取对齐的可供性知识并整合至可供性词典中。随后，可供性词典自适应融合模块（ADM）学习综合考虑多幅图像中所有可供性候选点的全面点云表征。此外，本研究构建了多图像与点可供性（MIPA）基准数据集，实验结果表明我们的方法在各种对比实验中均优于现有最先进方法。