Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

ArXi:2408.13024v3 Announce Type: replace 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.