RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses 事件

RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses arXiv:2605.20823v3 Announce Type: replace Abstract: Open-vocabulary 3D scene graph generation seeks to describe object instances and their relations with flexible natural-language predicates. The central difficulty is not only vocabulary expansion, but supervision reliability: relation annotations in 3D scene graph datasets are selective, and many valid object-pair relations are unannotated. We propos