LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

arXiv:2312.08963v2 Announce Type: replace
Abstract: Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interaction elements, e.g., human contact, object affordance, and human-object spatial relation, primarily from the perspective of either the human or the object. Which underexploit certain correlations between the interaction counterparts (human and object), and struggle to address the uncertainty in interactions. Actually, objects' functionalities potentially affect humans' interaction intentions, which reveals …

abstract arxiv cs.cv embodied embodied ai human images modeling object perspective pivotal spatial type