AI RESEARCH
RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses
arXiv CS.CV
•
ArXi:2605.20823v1 Announce Type: new 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 propose RelWitness, a framework for open-vocabulary 3D scene graph generation from posed RGB-D sequences under incomplete relation supervision.